diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/codex-portability.md b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/codex-portability.md new file mode 100644 index 00000000..b94adcd1 --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/codex-portability.md @@ -0,0 +1,49 @@ +# Codex portability — before and after the router fix + +The skill triggered on Codex from the start, but rendered nothing. Root cause: the +'read an action's file before running it' rule had been moved into skill-authoring.md, +a contract no executing host ever reads. Codex read SKILL.md and stopped. + +## Before — Codex reads SKILL.md and stops + +```text +I'm using `aidd-context:00-onboard` because you asked to be onboarded. +[reads .../skills/00-onboard/SKILL.md] +[no banner, no setup block, no foundations screen — improvises a generic answer] +``` + +Full capture: `headless-runs-codex.txt` (all eight states, pre-fix). + +## After — the router carries the operative line + +`SKILL.md`: `Run the actions in that order, looping. Read an action's file in \`actions/\` before running it.` + +```text + █████╗ ██╗██████╗ ██████╗ +██╔══██╗██║██╔══██╗██╔══██╗ +███████║██║██║ ██║██║ ██║ +██╔══██║██║██║ ██║██║ ██║ +██║ ██║██║██████╔╝██████╔╝ +╚═╝ ╚═╝╚═╝╚═════╝ ╚═════╝ + AI-Driven Development 🇫🇷 + +exec +/bin/zsh -lc "test -f AGENTS.md && sed -n '1,160p' AGENTS.md || true" in /private/tmp/aidd-demo/01-greenfield +exec +/bin/zsh -lc "test -f RTK.md && sed -n '1,220p' RTK.md || true" in /private/tmp/aidd-demo/01-greenfield + succeeded in 0ms: + succeeded in 0ms: +exec +/bin/zsh -lc "find . -maxdepth 2 -type f -o -type d | sort | sed -n '1,160p'" in /private/tmp/aidd-demo/01-greenfield + succeeded in 0ms: +. +./.git +./.git/HEAD +./.git/config +./.git/description +./.git/hooks +./.git/info +``` + +Probes: READ THE ACTIONS ✓ · BANNER ✓ · SETUP BLOCK ✓ · FOUNDATIONS ✓ +Identical shape to the Claude run in `headless-runs.md`. diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/headless-runs-codex.txt b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/headless-runs-codex.txt new file mode 100644 index 00000000..7b7638ee --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/headless-runs-codex.txt @@ -0,0 +1,1449 @@ +# Onboard — headless runs on Codex, every state + +Verbatim output of `codex exec "onboard me"` per fixture. +MCP auth errors (vercel, figma) and hook chatter are stripped as environment noise. +Generated 2026-07-10 10:44. + +### 01-greenfield + +> Empty repo, git only. + +```text +Reading additional input from stdin... +OpenAI Codex v0.143.0 +-------- +workdir: /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/01-greenfield +model: gpt-5.5 +provider: openai +approval: never +sandbox: read-only +reasoning effort: high +reasoning summaries: none +session id: 019f4b33-13d6-7470-80f8-47896e286b8b +-------- +user +onboard me +warning: Skill descriptions were shortened to fit the 2% skills context budget. Codex can still see every skill, but some descriptions are shorter. Disable unused skills or plugins to leave more room for the rest. +codex +I’m using `aidd-context:00-onboard` because you asked to be onboarded. I’ll read its local instructions first, then run the greenfield onboarding flow with sensible defaults. +exec +/bin/zsh -lc "pwd && sed -n '1,240p' /Users/baptistelafourcade/.codex/plugins/cache/aidd-framework/aidd-context/2.2.0/skills/00-onboard/SKILL.md && sed -n '1,200p' RTK.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/01-greenfield + exited 1 in 0ms: +/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/01-greenfield +--- +name: 00-onboard +description: Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface. +argument-hint: scan | assess | present | run +--- + +# Onboard + +```mermaid +flowchart LR + scan --> assess --> present --> run --> scan +``` + +## Actions + +| # | Action | Does | +| -- | ------- | -------------------- | +| 01 | scan | read the project | +| 02 | assess | decide the next step | +| 03 | present | show the screen | +| 04 | run | act on the reply | + +## Transversal rules + +- Guide, do not lecture or dump. +- Name real commands only, never invented ones. +- Never run a GUIDED step unattended. +- Never test a plugin version against a registry. +- Never trust a stale status. +- Wait for an explicit reply before running anything. +sed: RTK.md: No such file or directory + +exec +/bin/zsh -lc 'wc -l /Users/baptistelafourcade/.codex/plugins/cache/aidd-framework/aidd-context/2.2.0/skills/00-onboard/SKILL.md' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/01-greenfield + succeeded in 0ms: + 30 /Users/baptistelafourcade/.codex/plugins/cache/aidd-framework/aidd-context/2.2.0/skills/00-onboard/SKILL.md + +exec +/bin/zsh -lc 'ls -la' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/01-greenfield + succeeded in 0ms: +total 0 +drwxr-xr-x 3 baptistelafourcade wheel 96 Jul 10 10:37 . +drwxr-xr-x 10 baptistelafourcade wheel 320 Jul 10 10:37 .. +drwxr-xr-x 9 baptistelafourcade wheel 288 Jul 10 10:37 .git + +codex +You’re in an empty greenfield repo: only `.git` exists. The project also references `RTK.md` from `AGENTS.md`, but that file is missing. + +Recommended next step: **bootstrap the project** into an `INSTALL.md` with product goal, stack, architecture, env vars, and first implementation path. + +Choose one: + +1. **Bootstrap SaaS**: define product + architecture from scratch. +2. **Create project memory**: set up durable context files first. +3. **Plan a feature**: start from a concrete feature idea. +4. **Just explain AIDD**: quick orientation, no files. + +One constraint: this session is currently read-only, so I can guide and inspect, but I can’t create files until write access is available. +19 308 +You’re in an empty greenfield repo: only `.git` exists. The project also references `RTK.md` from `AGENTS.md`, but that file is missing. + +Recommended next step: **bootstrap the project** into an `INSTALL.md` with product goal, stack, architecture, env vars, and first implementation path. + +Choose one: + +1. **Bootstrap SaaS**: define product + architecture from scratch. +2. **Create project memory**: set up durable context files first. +3. **Plan a feature**: start from a concrete feature idea. +4. **Just explain AIDD**: quick orientation, no files. + +One constraint: this session is currently read-only, so I can guide and inspect, but I can’t create files until write access is available. +``` + +### 02-existing-no-memory + +> Code present, no memory bank. + +```text +Reading additional input from stdin... +OpenAI Codex v0.143.0 +-------- +workdir: /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory +model: gpt-5.5 +provider: openai +approval: never +sandbox: read-only +reasoning effort: high +reasoning summaries: none +session id: 019f4b33-9853-7981-9ed4-9b3ce6e5e2e0 +-------- +user +onboard me +warning: Skill descriptions were shortened to fit the 2% skills context budget. Codex can still see every skill, but some descriptions are shorter. Disable unused skills or plugins to leave more room for the rest. +codex +I’ll use `aidd-context:00-onboard` because this is the project onboarding flow. I’m going to read the project instructions and the skill’s workflow first, then I’ll inspect the repo without making changes. +exec +/bin/zsh -lc "sed -n '1,220p' /Users/baptistelafourcade/.codex/plugins/cache/aidd-framework/aidd-context/2.2.0/skills/00-onboard/SKILL.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory +exec +/bin/zsh -lc 'pwd && ls' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory + succeeded in 0ms: +/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory +package.json +src + + succeeded in 0ms: +--- +name: 00-onboard +description: Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface. +argument-hint: scan | assess | present | run +--- + +# Onboard + +```mermaid +flowchart LR + scan --> assess --> present --> run --> scan +``` + +## Actions + +| # | Action | Does | +| -- | ------- | -------------------- | +| 01 | scan | read the project | +| 02 | assess | decide the next step | +| 03 | present | show the screen | +| 04 | run | act on the reply | + +## Transversal rules + +- Guide, do not lecture or dump. +- Name real commands only, never invented ones. +- Never run a GUIDED step unattended. +- Never test a plugin version against a registry. +- Never trust a stale status. +- Wait for an explicit reply before running anything. + +exec +/bin/zsh -lc "sed -n '1,220p' RTK.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory + exited 1 in 0ms: +sed: RTK.md: No such file or directory + +codex +The local `RTK.md` referenced by the instructions is not present in this fixture root, so I’ll proceed with the visible project files and call out that missing instruction file in the onboarding status. Next I’m checking the package metadata and source shape so the next-step recommendation is based on this repo, not a template. +exec +/bin/zsh -lc "sed -n '1,220p' package.json" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory + succeeded in 0ms: +{"name":"demo","version":"1.0.0"} + +exec +/bin/zsh -lc 'rg --files' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory + succeeded in 0ms: +src/index.js +package.json + +exec +/bin/zsh -lc 'find .. -name RTK.md -print' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory + succeeded in 0ms: +codex +This is a very small Node fixture: `package.json` plus one source file, with no visible memory artifacts or test setup yet. I’m reading the source file now, then I’ll give you the onboarding screen and wait for your chosen next step. +exec +/bin/zsh -lc "sed -n '1,220p' src/index.js" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory + succeeded in 0ms: +export const hi = () => "hi" + +exec +/bin/zsh -lc 'find . -maxdepth 3 -type d -print' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory + succeeded in 0ms: +. +./.git +./.git/objects +./.git/objects/58 +./.git/objects/02 +./.git/objects/pack +./.git/objects/info +./.git/objects/96 +./.git/objects/ce +./.git/objects/4f +./.git/info +./.git/logs +./.git/logs/refs +./.git/hooks +./.git/refs +./.git/refs/heads +./.git/refs/tags +./src + +exec +/bin/zsh -lc 'git status --short --branch' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory + succeeded in 0ms: +## main + +codex +**Onboarding Status** + +I scanned the repo. Current state: + +- Project is a tiny Node fixture: `package.json` and [src/index.js](/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory/src/index.js:1) +- `package.json` only has `name` and `version` +- No tests, scripts, README, or project memory files are present +- Git worktree is clean on `main` +- `AGENTS.md` referenced `@RTK.md`, but no `RTK.md` exists in or above this fixture + +Recommended next step: initialize project memory, because this repo has no durable project context yet. + +Choose one: + +1. `memory` - create/refresh project memory +2. `explore` - deeper read-only repo survey +3. `plan` - make a concrete implementation plan for a feature +4. `skip` - tell me what you want to build directly +20 436 +**Onboarding Status** + +I scanned the repo. Current state: + +- Project is a tiny Node fixture: `package.json` and [src/index.js](/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/02-existing-no-memory/src/index.js:1) +- `package.json` only has `name` and `version` +- No tests, scripts, README, or project memory files are present +- Git worktree is clean on `main` +- `AGENTS.md` referenced `@RTK.md`, but no `RTK.md` exists in or above this fixture + +Recommended next step: initialize project memory, because this repo has no durable project context yet. + +Choose one: + +1. `memory` - create/refresh project memory +2. `explore` - deeper read-only repo survey +3. `plan` - make a concrete implementation plan for a feature +4. `skip` - tell me what you want to build directly +``` + +### 03-drift-tool-unwired + +> Memory wired for claude. .codex/ present, no AGENTS.md. + +```text +Reading additional input from stdin... +OpenAI Codex v0.143.0 +-------- +workdir: /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired +model: gpt-5.5 +provider: openai +approval: never +sandbox: read-only +reasoning effort: high +reasoning summaries: none +session id: 019f4b34-4e4c-71e3-9fbc-6eeeb381e9a9 +-------- +user +onboard me +warning: Skill descriptions were shortened to fit the 2% skills context budget. Codex can still see every skill, but some descriptions are shorter. Disable unused skills or plugins to leave more room for the rest. +codex +I’ll use the AIDD onboarding skill and first read the local project instructions so the walkthrough matches this fixture. +exec +/bin/zsh -lc "sed -n '1,240p' /Users/baptistelafourcade/.codex/plugins/cache/aidd-framework/aidd-context/2.2.0/skills/00-onboard/SKILL.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +--- +name: 00-onboard +description: Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface. +argument-hint: scan | assess | present | run +--- + +# Onboard + +```mermaid +flowchart LR + scan --> assess --> present --> run --> scan +``` + +## Actions + +| # | Action | Does | +| -- | ------- | -------------------- | +| 01 | scan | read the project | +| 02 | assess | decide the next step | +| 03 | present | show the screen | +| 04 | run | act on the reply | + +## Transversal rules + +- Guide, do not lecture or dump. +- Name real commands only, never invented ones. +- Never run a GUIDED step unattended. +- Never test a plugin version against a registry. +- Never trust a stale status. +- Wait for an explicit reply before running anything. + +exec +/bin/zsh -lc "pwd && rg --files -g 'AGENTS.md' -g 'RTK.md' -g 'CLAUDE.md' -g 'README*' -g 'package.json' -g 'pyproject.toml' -g 'go.mod'" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired +CLAUDE.md +package.json + +codex +The onboarding skill is intentionally lightweight: scan the project, assess the current state, then present concrete next options and wait before running guided work. I’m reading the local context and package metadata now. +exec +/bin/zsh -lc "sed -n '1,260p' CLAUDE.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired +exec +/bin/zsh -lc "sed -n '1,240p' package.json" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +{"name":"demo","version":"1.0.0"} + + succeeded in 0ms: +# CLAUDE.md + +## Memory Management + + +@aidd_docs/memory/architecture.md +@aidd_docs/memory/browsing.md +@aidd_docs/memory/codebase-map.md +@aidd_docs/memory/coding-assertions.md +@aidd_docs/memory/deployment.md +@aidd_docs/memory/project-brief.md +@aidd_docs/memory/testing.md +@aidd_docs/memory/vcs.md + + +exec +/bin/zsh -lc "find . -maxdepth 3 -type f | sort | sed 's#"'^./##'"'" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +.codex/.keep +.git/COMMIT_EDITMSG +.git/HEAD +.git/config +.git/description +.git/hooks/applypatch-msg.sample +.git/hooks/commit-msg.sample +.git/hooks/fsmonitor-watchman.sample +.git/hooks/post-update.sample +.git/hooks/pre-applypatch.sample +.git/hooks/pre-commit.sample +.git/hooks/pre-merge-commit.sample +.git/hooks/pre-push.sample +.git/hooks/pre-rebase.sample +.git/hooks/pre-receive.sample +.git/hooks/prepare-commit-msg.sample +.git/hooks/push-to-checkout.sample +.git/hooks/sendemail-validate.sample +.git/hooks/update.sample +.git/index +.git/info/exclude +.git/logs/HEAD +CLAUDE.md +aidd_docs/memory/architecture.md +aidd_docs/memory/browsing.md +aidd_docs/memory/codebase-map.md +aidd_docs/memory/coding-assertions.md +aidd_docs/memory/deployment.md +aidd_docs/memory/project-brief.md +aidd_docs/memory/testing.md +aidd_docs/memory/vcs.md +package.json +src/index.js + +exec +/bin/zsh -lc 'git status --short --branch' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +## main + +codex +This is a small fixture with AIDD memory already referenced from `CLAUDE.md`. I’m checking those memory files against the actual source so I can identify whether onboarding should start with setup, drift repair, testing, or feature work. +exec +/bin/zsh -lc "sed -n '1,240p' aidd_docs/memory/project-brief.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired +exec +/bin/zsh -lc "sed -n '1,240p' aidd_docs/memory/codebase-map.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired +exec +/bin/zsh -lc "sed -n '1,240p' aidd_docs/memory/architecture.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +# project-brief + +Real content for the project-brief memory file of this demo project. + + succeeded in 0ms: +# codebase-map + +Real content for the codebase-map memory file of this demo project. + + succeeded in 0ms: +# architecture + +Real content for the architecture memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,240p' aidd_docs/memory/testing.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +# testing + +Real content for the testing memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,240p' aidd_docs/memory/coding-assertions.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +# coding-assertions + +Real content for the coding-assertions memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,240p' src/index.js" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +export const hi = () => "hi" + +codex +The memory files exist but contain placeholder “real content” rather than actionable project facts. I’m doing one more pass over the remaining memory and available scripts before I present the onboarding screen. +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/browsing.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +# browsing + +Real content for the browsing memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/deployment.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/vcs.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +# deployment + +Real content for the deployment memory file of this demo project. + + succeeded in 0ms: +# vcs + +Real content for the vcs memory file of this demo project. + +exec +/bin/zsh -lc 'git log --oneline -5' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +5a509fb init + +exec +/bin/zsh -lc 'npm run --silent 2>/dev/null || true' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/03-drift-tool-unwired + succeeded in 0ms: +codex +**Onboarding Screen** + +Current state: +- Repo is on `main`, clean, one commit: `5a509fb init`. +- `CLAUDE.md` wires AIDD memory files under `aidd_docs/memory/`. +- Those memory files exist, but they’re placeholders rather than useful project facts. +- `package.json` has no scripts. +- Source is minimal: `src/index.js` exports `hi()`. +- `AGENTS.md` references `RTK.md`, but no `RTK.md` is present in this workspace. + +Recommended next step: **repair project memory drift**. The project is wired for AIDD, but the memory content does not describe the actual codebase. + +Pick one: + +1. **Refresh memory**: regenerate useful `aidd_docs/memory/*` content from the repo. +2. **Explore first**: produce a read-only project map and identify gaps. +3. **Add tests/scripts**: wire basic npm scripts and a minimal test path. +4. **Audit**: run a read-only quality scan and report risks. + +Reply with `1`, `2`, `3`, or `4`. +23 389 +**Onboarding Screen** + +Current state: +- Repo is on `main`, clean, one commit: `5a509fb init`. +- `CLAUDE.md` wires AIDD memory files under `aidd_docs/memory/`. +- Those memory files exist, but they’re placeholders rather than useful project facts. +- `package.json` has no scripts. +- Source is minimal: `src/index.js` exports `hi()`. +- `AGENTS.md` references `RTK.md`, but no `RTK.md` is present in this workspace. + +Recommended next step: **repair project memory drift**. The project is wired for AIDD, but the memory content does not describe the actual codebase. + +Pick one: + +1. **Refresh memory**: regenerate useful `aidd_docs/memory/*` content from the repo. +2. **Explore first**: produce a read-only project map and identify gaps. +3. **Add tests/scripts**: wire basic npm scripts and a minimal test path. +4. **Audit**: run a read-only quality scan and report risks. + +Reply with `1`, `2`, `3`, or `4`. +``` + +### 04-drift-block-offshape + +> Memory synced, CLAUDE.md block off canonical shape. + +```text +Reading additional input from stdin... +OpenAI Codex v0.143.0 +-------- +workdir: /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape +model: gpt-5.5 +provider: openai +approval: never +sandbox: read-only +reasoning effort: high +reasoning summaries: none +session id: 019f4b35-5173-7281-88bc-02074997578d +-------- +user +onboard me +warning: Skill descriptions were shortened to fit the 2% skills context budget. Codex can still see every skill, but some descriptions are shorter. Disable unused skills or plugins to leave more room for the rest. +codex +I’ll use the `aidd-context:00-onboard` skill because this is an AIDD onboarding request. I’m going to read the project instructions and the onboarding skill first, then I’ll inspect the repo enough to give you the right next step. +exec +/bin/zsh -lc "sed -n '1,260p' /Users/baptistelafourcade/.codex/plugins/cache/aidd-framework/aidd-context/2.2.0/skills/00-onboard/SKILL.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + succeeded in 0ms: +--- +name: 00-onboard +description: Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface. +argument-hint: scan | assess | present | run +--- + +# Onboard + +```mermaid +flowchart LR + scan --> assess --> present --> run --> scan +``` + +## Actions + +| # | Action | Does | +| -- | ------- | -------------------- | +| 01 | scan | read the project | +| 02 | assess | decide the next step | +| 03 | present | show the screen | +| 04 | run | act on the reply | + +## Transversal rules + +- Guide, do not lecture or dump. +- Name real commands only, never invented ones. +- Never run a GUIDED step unattended. +- Never test a plugin version against a registry. +- Never trust a stale status. +- Wait for an explicit reply before running anything. + +exec +/bin/zsh -lc "sed -n '1,260p' RTK.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + exited 1 in 0ms: +sed: RTK.md: No such file or directory + +exec +/bin/zsh -lc "pwd && rg --files -g 'RTK.md' -g 'AGENTS.md' -g 'CLAUDE.md' -g 'README*' -g 'package.json' -g 'pyproject.toml' -g 'go.mod' -g 'Cargo.toml'" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + succeeded in 0ms: +/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape +CLAUDE.md +package.json + +codex +The onboarding skill is intentionally lightweight: scan the project, assess the next step, present options, and wait for your explicit choice before running guided work. The referenced `RTK.md` is not present in this fixture, so I’m using the available project files instead. +exec +/bin/zsh -lc "sed -n '1,260p' package.json" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape +exec +/bin/zsh -lc "sed -n '1,260p' CLAUDE.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + succeeded in 0ms: +{"name":"demo","version":"1.0.0"} + + succeeded in 0ms: +# CLAUDE.md + + +@aidd_docs/memory/architecture.md +@aidd_docs/memory/browsing.md +@aidd_docs/memory/codebase-map.md +@aidd_docs/memory/coding-assertions.md +@aidd_docs/memory/deployment.md +@aidd_docs/memory/project-brief.md +@aidd_docs/memory/testing.md +@aidd_docs/memory/vcs.md + + +exec +/bin/zsh -lc 'rg --files' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + succeeded in 0ms: +src/index.js +CLAUDE.md +aidd_docs/memory/deployment.md +aidd_docs/memory/project-brief.md +aidd_docs/memory/browsing.md +aidd_docs/memory/testing.md +aidd_docs/memory/codebase-map.md +aidd_docs/memory/coding-assertions.md +aidd_docs/memory/architecture.md +aidd_docs/memory/vcs.md +package.json + +exec +/bin/zsh -lc 'find . -maxdepth 3 -type d | sort' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + succeeded in 0ms: +. +./.git +./.git/hooks +./.git/info +./.git/logs +./.git/logs/refs +./.git/objects +./.git/objects/12 +./.git/objects/29 +./.git/objects/37 +./.git/objects/4f +./.git/objects/58 +./.git/objects/6e +./.git/objects/74 +./.git/objects/87 +./.git/objects/8b +./.git/objects/95 +./.git/objects/96 +./.git/objects/9f +./.git/objects/a6 +./.git/objects/c3 +./.git/objects/ce +./.git/objects/e9 +./.git/objects/info +./.git/objects/pack +./.git/refs +./.git/refs/heads +./.git/refs/tags +./aidd_docs +./aidd_docs/memory +./src + +codex +This is a very small Node fixture with an AIDD memory bank already wired through `CLAUDE.md`. I’m reading those memory files and the current source so the onboarding recommendation is based on the project’s recorded state, not just the directory shape. +exec +/bin/zsh -lc "sed -n '1,260p' aidd_docs/memory/project-brief.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape +exec +/bin/zsh -lc "sed -n '1,260p' aidd_docs/memory/codebase-map.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape +exec +/bin/zsh -lc "sed -n '1,260p' aidd_docs/memory/deployment.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + succeeded in 0ms: +# codebase-map + +Real content for the codebase-map memory file of this demo project. + + succeeded in 0ms: +# project-brief + +Real content for the project-brief memory file of this demo project. + + succeeded in 0ms: +# deployment + +Real content for the deployment memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,260p' aidd_docs/memory/architecture.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape +exec +/bin/zsh -lc "sed -n '1,260p' aidd_docs/memory/vcs.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + succeeded in 0ms: +# architecture + +Real content for the architecture memory file of this demo project. + + succeeded in 0ms: +# vcs + +Real content for the vcs memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,260p' aidd_docs/memory/coding-assertions.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape +exec +/bin/zsh -lc "sed -n '1,260p' src/index.js" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + succeeded in 0ms: +# coding-assertions + +Real content for the coding-assertions memory file of this demo project. + + succeeded in 0ms: +export const hi = () => "hi" + +exec +/bin/zsh -lc "sed -n '1,260p' aidd_docs/memory/testing.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape +exec +/bin/zsh -lc "sed -n '1,260p' aidd_docs/memory/browsing.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + succeeded in 0ms: +# testing + +Real content for the testing memory file of this demo project. + + succeeded in 0ms: +# browsing + +Real content for the browsing memory file of this demo project. + +exec +/bin/zsh -lc 'git status --short --branch' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape + succeeded in 0ms: +## main +M CLAUDE.md + +codex +You’re onboarded to the current fixture. + +Current state: +- AIDD memory is wired in [CLAUDE.md](/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape/CLAUDE.md:1). +- Memory files exist under `aidd_docs/memory/`, but their contents are placeholder-style. +- Codebase is tiny: [src/index.js](/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape/src/index.js:1) exports `hi()`. +- `package.json` has no scripts. +- Git is on `main` with `CLAUDE.md` modified. +- The referenced `RTK.md` from `AGENTS.md` instructions is not present in this workspace. + +Recommended next step: refresh or validate the AIDD memory, because the project is initialized but the memory content does not yet describe the real codebase. + +Reply with one: + +1. `refresh memory` - rebuild the AIDD memory files from the current project. +2. `explore` - give you a fuller project map without editing files. +3. `plan feature` - start from a feature idea and produce an implementation plan. +4. `audit` - review the current project for gaps and risks. +23 168 +You’re onboarded to the current fixture. + +Current state: +- AIDD memory is wired in [CLAUDE.md](/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape/CLAUDE.md:1). +- Memory files exist under `aidd_docs/memory/`, but their contents are placeholder-style. +- Codebase is tiny: [src/index.js](/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/04-drift-block-offshape/src/index.js:1) exports `hi()`. +- `package.json` has no scripts. +- Git is on `main` with `CLAUDE.md` modified. +- The referenced `RTK.md` from `AGENTS.md` instructions is not present in this workspace. + +Recommended next step: refresh or validate the AIDD memory, because the project is initialized but the memory content does not yet describe the real codebase. + +Reply with one: + +1. `refresh memory` - rebuild the AIDD memory files from the current project. +2. `explore` - give you a fuller project map without editing files. +3. `plan feature` - start from a feature idea and produce an implementation plan. +4. `audit` - review the current project for gaps and risks. +``` + +### 05-midwork + +> plan status: in-progress, an uncommitted file. + +```text +Reading additional input from stdin... +OpenAI Codex v0.143.0 +-------- +workdir: /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork +model: gpt-5.5 +provider: openai +approval: never +sandbox: read-only +reasoning effort: high +reasoning summaries: none +session id: 019f4b36-86ce-72b1-835b-a5deb516275f +-------- +user +onboard me +warning: Skill descriptions were shortened to fit the 2% skills context budget. Codex can still see every skill, but some descriptions are shorter. Disable unused skills or plugins to leave more room for the rest. +codex +I’ll use the `aidd-context:00-onboard` skill for this, and first I’m going to read the project instructions plus the onboarding skill so I follow the repo’s intended workflow. +exec +/bin/zsh -lc "pwd && rg --files -g 'AGENTS.md' -g 'RTK.md' -g 'SKILL.md'" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork + exited 1 in 0ms: +/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork + +exec +/bin/zsh -lc "sed -n '1,240p' /Users/baptistelafourcade/.codex/plugins/cache/aidd-framework/aidd-context/2.2.0/skills/00-onboard/SKILL.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork + succeeded in 0ms: +--- +name: 00-onboard +description: Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface. +argument-hint: scan | assess | present | run +--- + +# Onboard + +```mermaid +flowchart LR + scan --> assess --> present --> run --> scan +``` + +## Actions + +| # | Action | Does | +| -- | ------- | -------------------- | +| 01 | scan | read the project | +| 02 | assess | decide the next step | +| 03 | present | show the screen | +| 04 | run | act on the reply | + +## Transversal rules + +- Guide, do not lecture or dump. +- Name real commands only, never invented ones. +- Never run a GUIDED step unattended. +- Never test a plugin version against a registry. +- Never trust a stale status. +- Wait for an explicit reply before running anything. + +codex +The onboarding skill is intentionally lightweight: scan the project, assess the next useful step, present options, then wait before running any guided action. I’m checking what exists in this fixture so the recommendation is based on the actual state rather than a generic path. +exec +/bin/zsh -lc 'find .. -name AGENTS.md -o -name RTK.md -o -name CLAUDE.md -o -name README.md -o -name package.json -o -name pyproject.toml -o -name Cargo.toml -o -name go.mod -o -name .git -o -name .aidd -maxdepth 4' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork + succeeded in 0ms: +../03-drift-tool-unwired/package.json +../03-drift-tool-unwired/.git +../03-drift-tool-unwired/CLAUDE.md +../01-greenfield/.git +../02-existing-no-memory/package.json +../02-existing-no-memory/.git +../04-drift-block-offshape/package.json +../04-drift-block-offshape/.git +../04-drift-block-offshape/CLAUDE.md +../08-no-vcs/package.json +../08-no-vcs/CLAUDE.md +../07-plan-broken-status/package.json +../07-plan-broken-status/.git +../07-plan-broken-status/CLAUDE.md +../06-idle/package.json +../06-idle/.git +../06-idle/CLAUDE.md +../05-midwork/package.json +../05-midwork/.git +../05-midwork/CLAUDE.md + +exec +/bin/zsh -lc 'rg --files' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork + succeeded in 0ms: +src/wip.js +src/index.js +CLAUDE.md +aidd_docs/memory/deployment.md +aidd_docs/memory/project-brief.md +aidd_docs/memory/browsing.md +aidd_docs/memory/testing.md +aidd_docs/memory/codebase-map.md +aidd_docs/memory/coding-assertions.md +aidd_docs/memory/architecture.md +aidd_docs/memory/vcs.md +aidd_docs/tasks/2026_07/demo/plan.md +package.json + +exec +/bin/zsh -lc 'ls -la' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork + succeeded in 0ms: +total 16 +drwxr-xr-x 7 baptistelafourcade wheel 224 Jul 10 10:37 . +drwxr-xr-x 10 baptistelafourcade wheel 320 Jul 10 10:37 .. +drwxr-xr-x 12 baptistelafourcade wheel 384 Jul 10 10:37 .git +-rw-r--r-- 1 baptistelafourcade wheel 338 Jul 10 10:37 CLAUDE.md +drwxr-xr-x 4 baptistelafourcade wheel 128 Jul 10 10:37 aidd_docs +-rw-r--r-- 1 baptistelafourcade wheel 34 Jul 10 10:37 package.json +drwxr-xr-x 4 baptistelafourcade wheel 128 Jul 10 10:37 src + +codex +This project already has AIDD memory and an active-looking task plan, so I’m reading those before I recommend the next step. I also checked for the referenced `RTK.md`; it does not appear to be present in this fixture. +exec +/bin/zsh -lc "sed -n '1,220p' CLAUDE.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork +exec +/bin/zsh -lc "sed -n '1,260p' aidd_docs/tasks/2026_07/demo/plan.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork + succeeded in 0ms: +--- +status: in-progress +--- + +# Plan: demo + + succeeded in 0ms: +# CLAUDE.md + +## Memory Management + + +@aidd_docs/memory/architecture.md +@aidd_docs/memory/browsing.md +@aidd_docs/memory/codebase-map.md +@aidd_docs/memory/coding-assertions.md +@aidd_docs/memory/deployment.md +@aidd_docs/memory/project-brief.md +@aidd_docs/memory/testing.md +@aidd_docs/memory/vcs.md + + +exec +/bin/zsh -lc 'git status --short --branch' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork + succeeded in 0ms: +## main +?? src/wip.js + +exec +/bin/zsh -lc "for f in aidd_docs/memory/*.md; do printf '\\n## %s\\n' \""'$f"; sed -n '"'1,180p' \""'$f"; done' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork + succeeded in 0ms: + +## aidd_docs/memory/architecture.md +# architecture + +Real content for the architecture memory file of this demo project. + +## aidd_docs/memory/browsing.md +# browsing + +Real content for the browsing memory file of this demo project. + +## aidd_docs/memory/codebase-map.md +# codebase-map + +Real content for the codebase-map memory file of this demo project. + +## aidd_docs/memory/coding-assertions.md +# coding-assertions + +Real content for the coding-assertions memory file of this demo project. + +## aidd_docs/memory/deployment.md +# deployment + +Real content for the deployment memory file of this demo project. + +## aidd_docs/memory/project-brief.md +# project-brief + +Real content for the project-brief memory file of this demo project. + +## aidd_docs/memory/testing.md +# testing + +Real content for the testing memory file of this demo project. + +## aidd_docs/memory/vcs.md +# vcs + +Real content for the vcs memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,220p' package.json && sed -n '1,220p' src/index.js && sed -n '1,220p' src/wip.js" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/05-midwork + succeeded in 0ms: +{"name":"demo","version":"1.0.0"} +export const hi = () => "hi" +export const wip = 1 + +codex +**Onboarding** + +You’re in a mid-work AIDD project. + +Current state: +- AIDD memory is wired through `CLAUDE.md` and all memory files exist. +- Active plan: `aidd_docs/tasks/2026_07/demo/plan.md` +- Plan status: `in-progress`, but it has no real steps or acceptance criteria. +- Git branch: `main` +- Worktree: one untracked file, `src/wip.js` +- `AGENTS.md` references `RTK.md`, but `RTK.md` is not present in this fixture. + +Best next step: clarify or repair the active plan before implementing anything. Otherwise there is no reliable target to continue from. + +Reply with one of these: +- `assess plan` - I’ll inspect whether the current plan is usable. +- `continue work` - I’ll proceed from the current code and plan as best as possible. +- `refresh memory` - I’ll regenerate/validate project memory first. +22 254 +**Onboarding** + +You’re in a mid-work AIDD project. + +Current state: +- AIDD memory is wired through `CLAUDE.md` and all memory files exist. +- Active plan: `aidd_docs/tasks/2026_07/demo/plan.md` +- Plan status: `in-progress`, but it has no real steps or acceptance criteria. +- Git branch: `main` +- Worktree: one untracked file, `src/wip.js` +- `AGENTS.md` references `RTK.md`, but `RTK.md` is not present in this fixture. + +Best next step: clarify or repair the active plan before implementing anything. Otherwise there is no reliable target to continue from. + +Reply with one of these: +- `assess plan` - I’ll inspect whether the current plan is usable. +- `continue work` - I’ll proceed from the current code and plan as best as possible. +- `refresh memory` - I’ll regenerate/validate project memory first. +``` + +### 06-idle + +> Everything committed, nothing pending. + +```text +Reading additional input from stdin... +OpenAI Codex v0.143.0 +-------- +workdir: /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle +model: gpt-5.5 +provider: openai +approval: never +sandbox: read-only +reasoning effort: high +reasoning summaries: none +session id: 019f4b37-5fd9-7441-b287-3e136eac5140 +-------- +user +onboard me +warning: Skill descriptions were shortened to fit the 2% skills context budget. Codex can still see every skill, but some descriptions are shorter. Disable unused skills or plugins to leave more room for the rest. +codex +I’ll use the `aidd-context:00-onboard` skill because this is the project onboarding flow. I’m going to read its instructions and the local project guidance first so the onboarding matches this repo. +exec +/bin/zsh -lc "sed -n '1,220p' RTK.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle +exec +/bin/zsh -lc "sed -n '1,220p' /Users/baptistelafourcade/.codex/plugins/cache/aidd-framework/aidd-context/2.2.0/skills/00-onboard/SKILL.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle + succeeded in 0ms: +--- +name: 00-onboard +description: Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface. +argument-hint: scan | assess | present | run +--- + +# Onboard + +```mermaid +flowchart LR + scan --> assess --> present --> run --> scan +``` + +## Actions + +| # | Action | Does | +| -- | ------- | -------------------- | +| 01 | scan | read the project | +| 02 | assess | decide the next step | +| 03 | present | show the screen | +| 04 | run | act on the reply | + +## Transversal rules + +- Guide, do not lecture or dump. +- Name real commands only, never invented ones. +- Never run a GUIDED step unattended. +- Never test a plugin version against a registry. +- Never trust a stale status. +- Wait for an explicit reply before running anything. + + exited 1 in 0ms: +sed: RTK.md: No such file or directory + +exec +/bin/zsh -lc "pwd && rg --files -g '"'!*node_modules*'"' -g '"'!*.git*'"'" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle + succeeded in 0ms: +/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle +src/index.js +CLAUDE.md +aidd_docs/memory/deployment.md +aidd_docs/memory/project-brief.md +aidd_docs/memory/browsing.md +aidd_docs/memory/testing.md +aidd_docs/memory/codebase-map.md +aidd_docs/memory/coding-assertions.md +aidd_docs/memory/architecture.md +aidd_docs/memory/vcs.md +package.json + +codex +`RTK.md` is referenced by the local instructions but is not present in this fixture. The repo does have AIDD memory files, so I’m reading those plus the small code surface to assess the current state. +exec +/bin/zsh -lc "sed -n '1,220p' src/index.js" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle + succeeded in 0ms: +export const hi = () => "hi" + +exec +/bin/zsh -lc "sed -n '1,220p' package.json" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle +exec +/bin/zsh -lc "sed -n '1,220p' CLAUDE.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle + succeeded in 0ms: +{"name":"demo","version":"1.0.0"} + + succeeded in 0ms: +# CLAUDE.md + +## Memory Management + + +@aidd_docs/memory/architecture.md +@aidd_docs/memory/browsing.md +@aidd_docs/memory/codebase-map.md +@aidd_docs/memory/coding-assertions.md +@aidd_docs/memory/deployment.md +@aidd_docs/memory/project-brief.md +@aidd_docs/memory/testing.md +@aidd_docs/memory/vcs.md + + +exec +/bin/zsh -lc "for f in aidd_docs/memory/*.md; do printf '\\n## %s\\n' \""'$f"; sed -n '"'1,220p' \""'$f"; done' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle + succeeded in 0ms: + +## aidd_docs/memory/architecture.md +# architecture + +Real content for the architecture memory file of this demo project. + +## aidd_docs/memory/browsing.md +# browsing + +Real content for the browsing memory file of this demo project. + +## aidd_docs/memory/codebase-map.md +# codebase-map + +Real content for the codebase-map memory file of this demo project. + +## aidd_docs/memory/coding-assertions.md +# coding-assertions + +Real content for the coding-assertions memory file of this demo project. + +## aidd_docs/memory/deployment.md +# deployment + +Real content for the deployment memory file of this demo project. + +## aidd_docs/memory/project-brief.md +# project-brief + +Real content for the project-brief memory file of this demo project. + +## aidd_docs/memory/testing.md +# testing + +Real content for the testing memory file of this demo project. + +## aidd_docs/memory/vcs.md +# vcs + +Real content for the vcs memory file of this demo project. + +codex +This is a very small demo fixture: one exported function, a bare `package.json`, and placeholder-style AIDD memory files. I’m doing one quick status check now so the recommended next step is based on the actual workspace state, not a stale assumption. +exec +/bin/zsh -lc 'ls -la' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle + succeeded in 0ms: +total 16 +drwxr-xr-x 7 baptistelafourcade wheel 224 Jul 10 10:37 . +drwxr-xr-x 10 baptistelafourcade wheel 320 Jul 10 10:37 .. +drwxr-xr-x 12 baptistelafourcade wheel 384 Jul 10 10:37 .git +-rw-r--r-- 1 baptistelafourcade wheel 338 Jul 10 10:37 CLAUDE.md +drwxr-xr-x 3 baptistelafourcade wheel 96 Jul 10 10:37 aidd_docs +-rw-r--r-- 1 baptistelafourcade wheel 34 Jul 10 10:37 package.json +drwxr-xr-x 3 baptistelafourcade wheel 96 Jul 10 10:37 src + +exec +/bin/zsh -lc 'git status --short --branch' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle + succeeded in 0ms: +## main + +exec +/bin/zsh -lc 'find .. -name RTK.md -maxdepth 4 -print' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle + succeeded in 0ms: +codex +**Onboarding** + +Current project state: + +- Repo is clean on `main`. +- `RTK.md` is referenced but missing. +- AIDD memory exists under `aidd_docs/memory/`, but the files contain demo placeholder text. +- Code surface is tiny: [src/index.js](/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle/src/index.js:1) exports `hi = () => "hi"`. +- `package.json` has no scripts, dependencies, test command, or module metadata beyond name/version. +- Current workspace is read-only, so I can assess and guide, but not modify files unless permissions change. + +Best next step: refresh project memory so AIDD has real architecture, testing, deployment, and codebase context instead of placeholders. + +Choose one: + +1. `scan` - I’ll do a deeper read-only project survey and report what is real. +2. `assess` - I’ll turn the current state into prioritized next steps. +3. `memory` - I’ll tell you exactly what should be written into each AIDD memory file. +4. `feature` - Give me a feature/bug, and I’ll plan it against this repo. +21 107 +**Onboarding** + +Current project state: + +- Repo is clean on `main`. +- `RTK.md` is referenced but missing. +- AIDD memory exists under `aidd_docs/memory/`, but the files contain demo placeholder text. +- Code surface is tiny: [src/index.js](/private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/06-idle/src/index.js:1) exports `hi = () => "hi"`. +- `package.json` has no scripts, dependencies, test command, or module metadata beyond name/version. +- Current workspace is read-only, so I can assess and guide, but not modify files unless permissions change. + +Best next step: refresh project memory so AIDD has real architecture, testing, deployment, and codebase context instead of placeholders. + +Choose one: + +1. `scan` - I’ll do a deeper read-only project survey and report what is real. +2. `assess` - I’ll turn the current state into prioritized next steps. +3. `memory` - I’ll tell you exactly what should be written into each AIDD memory file. +4. `feature` - Give me a feature/bug, and I’ll plan it against this repo. +``` + +### 07-plan-broken-status + +> plan.md carries a garbage status field. + +```text +Reading additional input from stdin... +OpenAI Codex v0.143.0 +-------- +workdir: /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status +model: gpt-5.5 +provider: openai +approval: never +sandbox: read-only +reasoning effort: high +reasoning summaries: none +session id: 019f4b38-0df7-7be3-bf94-e4a0f2427d3e +-------- +user +onboard me +warning: Skill descriptions were shortened to fit the 2% skills context budget. Codex can still see every skill, but some descriptions are shorter. Disable unused skills or plugins to leave more room for the rest. +codex +I’ll use the `aidd-context:00-onboard` skill for the onboarding flow and first read its instructions plus the repo’s local `RTK.md` guidance. +exec +/bin/zsh -lc "sed -n '1,240p' /Users/baptistelafourcade/.codex/plugins/cache/aidd-framework/aidd-context/2.2.0/skills/00-onboard/SKILL.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status +exec +/bin/zsh -lc "sed -n '1,240p' RTK.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +--- +name: 00-onboard +description: Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface. +argument-hint: scan | assess | present | run +--- + +# Onboard + +```mermaid +flowchart LR + scan --> assess --> present --> run --> scan +``` + +## Actions + +| # | Action | Does | +| -- | ------- | -------------------- | +| 01 | scan | read the project | +| 02 | assess | decide the next step | +| 03 | present | show the screen | +| 04 | run | act on the reply | + +## Transversal rules + +- Guide, do not lecture or dump. +- Name real commands only, never invented ones. +- Never run a GUIDED step unattended. +- Never test a plugin version against a registry. +- Never trust a stale status. +- Wait for an explicit reply before running anything. + + exited 1 in 0ms: +sed: RTK.md: No such file or directory + +exec +/bin/zsh -lc "rg --files -g '"'!*node_modules*'"' -g '"'!*.png'"' -g '"'!*.jpg'"' -g '"'!*.jpeg'"' -g '"'!*.gif'"' -g '"'!*.pdf'"'" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +src/index.js +CLAUDE.md +aidd_docs/memory/deployment.md +aidd_docs/memory/project-brief.md +aidd_docs/memory/browsing.md +aidd_docs/memory/testing.md +aidd_docs/memory/codebase-map.md +aidd_docs/memory/coding-assertions.md +aidd_docs/memory/architecture.md +aidd_docs/memory/vcs.md +aidd_docs/tasks/2026_07/demo/plan.md +package.json + +codex +The onboard skill is intentionally lightweight: scan, assess, present options, then wait. `RTK.md` was not in this fixture root, so I’m checking the nearby project files and memory instead of assuming those instructions. +exec +/bin/zsh -lc "sed -n '1,220p' CLAUDE.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status +exec +/bin/zsh -lc "sed -n '1,220p' package.json" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +# CLAUDE.md + +## Memory Management + + +@aidd_docs/memory/architecture.md +@aidd_docs/memory/browsing.md +@aidd_docs/memory/codebase-map.md +@aidd_docs/memory/coding-assertions.md +@aidd_docs/memory/deployment.md +@aidd_docs/memory/project-brief.md +@aidd_docs/memory/testing.md +@aidd_docs/memory/vcs.md + + + succeeded in 0ms: +{"name":"demo","version":"1.0.0"} + +exec +/bin/zsh -lc 'find .. -name RTK.md -print' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +exec +/bin/zsh -lc "sed -n '1,260p' aidd_docs/tasks/2026_07/demo/plan.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +--- +status: ??? garbage +--- + +# Plan: demo + +codex +This fixture is small and looks intentionally broken: the only task plan has `status: ??? garbage`. I’m reading the project memory now to determine the correct next step rather than treating that status as valid. +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/project-brief.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/coding-assertions.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +# project-brief + +Real content for the project-brief memory file of this demo project. + + succeeded in 0ms: +# coding-assertions + +Real content for the coding-assertions memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/architecture.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +# architecture + +Real content for the architecture memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/codebase-map.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +# codebase-map + +Real content for the codebase-map memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/vcs.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/testing.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +# vcs + +Real content for the vcs memory file of this demo project. + + succeeded in 0ms: +# testing + +Real content for the testing memory file of this demo project. + +codex +The memory files are present but placeholder-level. I’m doing one last structural check so the onboarding screen can point at concrete commands and the malformed plan status accurately. +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/deployment.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +# deployment + +Real content for the deployment memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,220p' aidd_docs/memory/browsing.md" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +# browsing + +Real content for the browsing memory file of this demo project. + +exec +/bin/zsh -lc "sed -n '1,220p' src/index.js" in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +export const hi = () => "hi" + +exec +/bin/zsh -lc 'git status --short' in /private/tmp/claude-501/-Users-baptistelafourcade-Projects-freelance-aidd-aidd-framework/e56b2570-3814-4f77-9b5e-5b026f1c7453/scratchpad/fixtures/07-plan-broken-status + succeeded in 0ms: +codex +**Onboarding** + +I found a tiny demo project with AIDD memory wired through `CLAUDE.md`, one source file, and one task plan: + +- Code: `src/index.js` +- Memory: `aidd_docs/memory/*.md` +- Plan: `aidd_docs/tasks/2026_07/demo/plan.md` +- Current issue: the plan frontmatter has an invalid status: `??? garbage` + +I would not trust that plan status. The next step should be to decide how to recover it. + +Choose one: + +1. **Repair plan status**: inspect the intended AIDD status values and normalize the broken plan. +2. **Refresh memory**: rebuild or validate the project memory before touching the plan. +3. **Explore only**: produce a short project map and recommended next actions. + +Reply with `1`, `2`, or `3`. +23 131 +**Onboarding** + +I found a tiny demo project with AIDD memory wired through `CLAUDE.md`, one source file, and one task plan: + +- Code: `src/index.js` +- Memory: `aidd_docs/memory/*.md` +- Plan: `aidd_docs/tasks/2026_07/demo/plan.md` +- Current issue: the plan frontmatter has an invalid status: `??? garbage` + +I would not trust that plan status. The next step should be to decide how to recover it. + +Choose one: + +1. **Repair plan status**: inspect the intended AIDD status values and normalize the broken plan. +2. **Refresh memory**: rebuild or validate the project memory before touching the plan. +3. **Explore only**: produce a short project map and recommended next actions. + +Reply with `1`, `2`, or `3`. +``` + +### 08-no-vcs + +> Code and memory, no git repository. + +```text +Reading additional input from stdin... +Not inside a trusted directory and --skip-git-repo-check was not specified. +``` + +CAPTURE_DONE diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/headless-runs.md b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/headless-runs.md new file mode 100644 index 00000000..8fb0cea3 --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/headless-runs.md @@ -0,0 +1,226 @@ +# Onboard — headless runs, every state + +Each block is the verbatim output of `claude -p "onboard me"` in a purpose-built fixture. +Generated 2026-07-10 10:43. + +### 01-greenfield + +> Empty repo, git only. No code, no memory, no tool config. + +```text +``` + █████╗ ██╗██████╗ ██████╗ +██╔══██╗██║██╔══██╗██╔══██╗ +███████║██║██║ ██║██║ ██║ +██╔══██║██║██║ ██║██║ ██║ +██║ ██║██║██████╔╝██████╔╝ +╚═╝ ╚═╝╚═╝╚═════╝ ╚═════╝ + AI-Driven Development 🇫🇷 + +👋 Welcome. AIDD guides a project from first setup to shipped code, one step at a time. + +Your AIDD setup: + AI tools none yet + Plugins aidd-context · aidd-dev · aidd-pm · aidd-refine · aidd-vcs · aidd-orchestrator ✅ + Memory ❌ not set up yet + +Empty repo — greenfield. Three foundation steps before the dev flow opens. + +Foundations — step 1 of 3 + + tech stack design and validate the architecture into INSTALL.md + (every later step reads this) + + step 2 project memory — capture the project knowledge into aidd_docs/memory/ + step 3 memory wiring — load that knowledge into your AI tool's context file + +👉 Type [1] to start. skip [s] · what's this [?] · OK walks all 3 · flow [m] +``` +``` + +### 02-existing-no-memory + +> Code present, no memory bank. The memory-first path. + +```text +```txt + █████╗ ██╗██████╗ ██████╗ +██╔══██╗██║██╔══██╗██╔══██╗ +███████║██║██║ ██║██║ ██║ +██╔══██║██║██║ ██║██║ ██║ +██║ ██║██║██████╔╝██████╔╝ +╚═╝ ╚═╝╚═╝╚═════╝ ╚═════╝ + AI-Driven Development 🇫🇷 +``` + +👋 Welcome. AIDD gives your project a memory, then a flow to ship features through. + +Your AIDD setup: +```txt + AI tools none yet + Plugins aidd-context · aidd-dev · aidd-pm · aidd-refine · aidd-vcs ✅ + Memory ❌ not set up yet +``` + +Code exists, memory does not. AI reads project fresh every session. + +**Foundations — step 1 of 2** +```txt + project knowledge saved read codebase, write memory bank + (AI stop guessing your stack, structure, conventions) + + step 2 knowledge loaded by the AI — wire memory into your AI tool's context file +``` + +👉 Type **[1]** to start. skip [s] · what's this [?] · OK walks both · flow [m] +``` + +### 03-drift-tool-unwired + +> Memory wired for claude. .codex/ present with no AGENTS.md. + +```text +```txt + █████╗ ██╗██████╗ ██████╗ +██╔══██╗██║██╔══██╗██╔══██╗ +███████║██║██║ ██║██║ ██║ +██╔══██║██║██║ ██║██║ ██║ +██║ ██║██║██████╔╝██████╔╝ +╚═╝ ╚═╝╚═╝╚═════╝ ╚═════╝ + AI-Driven Development 🇫🇷 + +👋 AIDD walks your project from setup to shipped code, one step at a time. + +Your AIDD setup: + AI tools codex ❌ + Plugins aidd-context · aidd-dev · aidd-pm · aidd-refine · aidd-vcs ✅ + Memory aidd_docs · 8 synced ✅ + +⚠️ Memory written, but codex can't read it — no AGENTS.md carries the memory block. + → Type [1] to wire memory into codex. + +👉 Type [1] to start. skip [s] · what's this [?] · flow [m] +``` +``` + +### 04-drift-block-offshape + +> Memory bank synced, but the CLAUDE.md block is off canonical shape. + +```text +```txt + █████╗ ██╗██████╗ ██████╗ +██╔══██╗██║██╔══██╗██╔══██╗ +███████║██║██║ ██║██║ ██║ +██╔══██║██║██║ ██║██║ ██║ +██║ ██║██║██████╔╝██████╔╝ +╚═╝ ╚═╝╚═╝╚═════╝ ╚═════╝ + AI-Driven Development 🇫🇷 + +👋 AIDD guides your project from setup to shipped code. Here is where you stand. + +Your AIDD setup: + AI tools none yet + Plugins aidd-context · aidd-dev · aidd-pm · aidd-refine · aidd-vcs ✅ + Memory aidd_docs · 8 synced ✅ + +Foundations are met. Nothing is in flight. Your code has no tests. + +👉 Next: cover src/ with tests [1] + start new work [2] · audit [3] · explore [4] · what's this [?] · flow [m] +``` +``` + +### 05-midwork + +> Full setup, plan status: in-progress, an uncommitted file. + +```text +🔍 Mid-work. Plan `demo` is `in-progress` — code started (`src/wip.js` untracked), not yet asserted. + +```txt + Flow: brainstorm ✅ → spec* → plan ✅ → [implement] → assert → review → commit → PR + + Setup: AI tools claude ✅ + Memory aidd_docs · 8 synced ✅ +``` + +👉 Next: finish implementing the plan `[1]` + assert instead `[2]` · no tests in repo, add coverage `[3]` · flow `[m]` · what's this `[?]` +``` + +### 06-idle + +> Full setup, everything committed, nothing pending. + +```text +```txt + █████╗ ██╗██████╗ ██████╗ +██╔══██╗██║██╔══██╗██╔══██╗ +███████║██║██║ ██║██║ ██║ +██╔══██║██║██║ ██║██║ ██║ +██║ ██║██║██████╔╝██████╔╝ +╚═╝ ╚═╝╚═╝╚═════╝ ╚═════╝ + AI-Driven Development 🇫🇷 + +👋 AIDD guides your project from setup to shipped code. Here is where you stand. + +Your AIDD setup: + AI tools none yet + Plugins aidd-context · aidd-dev · aidd-pm · aidd-refine · aidd-vcs · aidd-orchestrator ✅ + Memory aidd_docs · 8 synced ✅ + +Foundations done, no work in flight. Your source has no tests. + +👉 Next: add test coverage [1] + improve the project [2] · start new work [3] · explore [4] · what's this [?] · flow [m] +``` +``` + +### 07-plan-broken-status + +> Full setup, plan.md carries a garbage status field. + +```text +🔍 Plan exists but its status is unreadable — flow pinned at `plan`. + +```txt + Flow: brainstorm ✅ → spec* ✅ → [plan] → implement → assert → review → commit → PR +``` + +⚠️ `aidd_docs/tasks/2026_07/demo/plan.md` has `status: ??? garbage` — not a valid status, so the flow can't place you. + Valid: `pending` · `in-progress` · `implemented` · `reviewed` · `blocked` + +→ Type **[1]** to repair the status field (you edit it, I show the line). + re-plan from scratch [2] · what's this [?] · stop +``` + +### 08-no-vcs + +> Code and memory, but no git repository at all. + +```text +```txt + █████╗ ██╗██████╗ ██████╗ +██╔══██╗██║██╔══██╗██╔══██╗ +███████║██║██║ ██║██║ ██║ +██╔══██║██║██║ ██║██║ ██║ +██║ ██║██║██████╔╝██████╔╝ +╚═╝ ╚═╝╚═╝╚═════╝ ╚═════╝ + AI-Driven Development 🇫🇷 + +👋 AIDD guides your project from setup to shipped code. Here is where yours stands. + +Your AIDD setup: + AI tools none yet + Plugins aidd-context · aidd-dev · aidd-pm · aidd-refine · aidd-vcs ✅ + Memory aidd_docs · 8 synced ✅ + +Foundations met. Code in src/, no tests yet, and no version control — so no review or pull-request stage to read. + +👉 Next: cover src/ with tests [1] + init the repo [2] · audit the code [3] · what's this [?] · flow [m] +``` +``` + +CAPTURE_DONE diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/onboard-mockups.html b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/onboard-mockups.html new file mode 100644 index 00000000..debbd052 --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/onboard-mockups.html @@ -0,0 +1,376 @@ +AIDD Onboard — Tutorial Mockups + + +
+
+
AIDD · onboard skill
+

Onboard as a guided tutorial

+

Every screen the reworked onboard shows a user, from a bare repo to shipping a feature. It announces itself, shows the project's AIDD setup up front, then walks the official flow one step at a time. Mockups for review — not final wording.

+
+ present & wired + present, not wired — carries a fix + required, missing + [k] reply key +
+
+ +
+
01

Existing project · adopting AIDD

the common case — code already here, so memory comes first

+
+ +
+
existing repo · launch
+
 █████╗ ██╗██████╗ ██████╗
+██╔══██╗██║██╔══██╗██╔══██╗
+███████║██║██║  ██║██║  ██║
+██╔══██║██║██║  ██║██║  ██║
+██║  ██║██║██████╔╝██████╔╝
+╚═╝  ╚═╝╚═╝╚═════╝ ╚═════╝ 
+ AI-Driven Development
+
+👋  I'll walk you through AIDD step by step — nothing runs until you reply.
+
+Your AIDD setup:
+  AI tools   claude 
+  Plugins    aidd-context · pm · refine · dev · vcs   
+  Memory      not set up yet
+
+You already have code — AIDD just has no memory of it yet.
+
+  Let's teach the AI about your project first. Every command relies on it.
+    Type [1] to generate your project memory.   see the flow [m]
+
+ +
+
foundations · step 1 of 2
+
Foundations — step 1 of 2
+
+  project memory     scan your existing code into a memory bank the AI reads
+                     (architecture, testing, conventions — so commands don't guess)
+
+👉  Type [1] to start.   what's this [?]
+
+No "design the stack" step — your stack already exists, so it's skipped.
+
+ +
+
foundations · step 2 of 2
+
  Project memory saved.
+
+Foundations — step 2 of 2
+
+  connect it to the AI     wire the memory into claude's context file (CLAUDE.md)
+                           so it loads automatically every session
+
+👉  Type [1] to start.   skip [s]
+
+ +
+
+ +
+
02

Brand-new project · greenfield

empty repo — design the stack first, then memory

+
+ +
+
greenfield · launch
+
 █████╗ ██╗██████╗ ██████╗
+██╔══██╗██║██╔══██╗██╔══██╗
+███████║██║██║  ██║██║  ██║
+██╔══██║██║██║  ██║██║  ██║
+██║  ██║██║██████╔╝██████╔╝
+╚═╝  ╚═╝╚═╝╚═════╝ ╚═════╝ 
+ AI-Driven Development
+
+👋  I'll walk you through AIDD step by step — nothing runs until you reply.
+
+Your AIDD setup:
+  AI tools   claude    codex 
+  Plugins    aidd-context · pm · refine · dev · vcs   
+  Memory      not set up yet
+
+  Your AI tools have no project memory yet.
+    Type [1] to set up the foundations.   see the flow [m]
+
+ +
+
foundations · step 1 of 3
+
Foundations — step 1 of 3
+
+  design your tech stack     pick your technologies & architecture
+                             (saved to INSTALL.md — everything builds on it)
+
+👉  Type [1] to start (asks you a few questions).   skip [s] · what's this [?]
+
+ +
+
foundations · step 2 of 3
+
  Tech stack set.
+
+Foundations — step 2 of 3
+
+  save project knowledge     generate the memory files the AI reads
+                             (so commands work with real context, not guesses)
+
+👉  Type [1] to start.   skip [s]
+
+ +
+
foundations · step 3 of 3
+
  Project knowledge saved.
+
+Foundations — step 3 of 3
+
+  connect it to the AI       wire the memory into each AI tool's context file
+                             (CLAUDE.md, AGENTS.md — so it loads automatically)
+
+👉  Type [1] to start.   skip [s]
+
+ +
+
+ +
+
03

Coming back to build

foundations ready — the official flow

+
+ +
+
established · welcome back · the flow
+
 █████╗ ██╗██████╗ ██████╗
+██╔══██╗██║██╔══██╗██╔══██╗
+███████║██║██║  ██║██║  ██║
+██╔══██║██║██║  ██║██║  ██║
+██║  ██║██║██████╔╝██████╔╝
+╚═╝  ╚═╝╚═╝╚═════╝ ╚═════╝ 
+ AI-Driven Development
+
+👋  Welcome back.
+
+Your AIDD setup:
+  AI tools   claude 
+  Plugins    aidd-context · pm · refine · dev · vcs   
+  Memory     aidd_docs/ · 8 files synced   
+
+All set. Build your next feature — the AIDD flow:
+
+  brainstorm      turn a vague idea into something precise
+      │
+  spec            the contract of what to build          (optional)
+      │
+  plan            break it into phases
+      │
+  implement       build it, phase by phase
+      │
+  assert          check it behaves
+      │
+  review          verdict before shipping
+      │
+  commit          save the work
+      │
+  pull request    ship it
+
+Run it:
+   [1]  Walk it with me — one step at a time, I explain each.
+   [2]  Let SDLC drive the whole flow from one request.
+   map [m] · explore all commands [?] · stop [x]
+
+ +
+
walk · step 1 of 8
+
Your first feature — step 1 of 8: Brainstorm.
+
+  What:  turn your rough idea into something precise enough to build.
+  Why:   a fuzzy idea makes every next step guess.
+
+👉  Type [1] to start.   whole flow [m] · skip to spec [s]
+
+ +
+
walk · step 4 of 8
+
Feature flow — step 4 of 8: Implement.   (brainstorm  · spec  · plan )
+
+  What:  build the plan, phase by phase.
+  Why:   small verified phases beat one big leap.
+
+👉  Type [1] to start.   whole flow [m] · back [<]
+
+ +
+
map · the flow at a glance
+
AIDD feature flow:
+
+  brainstorm  spec*  plan  implement  assert  review  commit  PR
+  (* optional)
+
+  back [<]
+
+ +
+

The map view is the same canonical sequence shown as a standalone cookbook — one source, two doors.

+
+ +
+
04

Where you are, mid-work

the flow tracks your progress

+
+ +
+
building · unsaved changes
+
🔍  Healthy — unsaved changes in progress.
+
+  Flow:  brainstorm  · spec  · plan  · [implement] · assert · review · commit · PR
+
+👉  Next: finish your changes   [1]
+    review them [2] · both [OK] · more [?]
+
+ +
+
ready to review
+
🔍  Healthy — changes ready to review.
+
+  Flow:  brainstorm  · spec  · plan  · implement  · assert  · [review] · commit · PR
+
+👉  Next: review your changes   [1]
+    ship them [2] · both [OK] · more [?]
+
+ +
+
ready to ship
+
🔍  Healthy — reviewed, ready to ship.
+
+  Flow:  brainstorm  · … · review  · commit  · [pull request]
+
+👉  Next: open a pull request   [1]   (you run this one yourself)
+    more [?]
+
+ +
+
+ +
+
05

Warnings that carry a fix

every ⚠ says what's wrong and the next action

+
+ +
+
tool installed, not wired
+
👋  Welcome back.
+
+Your AIDD setup:
+  AI tools   claude    codex 
+  Plugins    aidd-context · pm · refine · dev · vcs   
+  Memory     aidd_docs/ · 8 files synced   
+
+  codex is installed but its memory isn't wired (no AGENTS.md).
+    Type [1] to wire it.   build a feature instead [m]
+
+ +
+
memory block drifted
+
👋  Welcome back.
+
+Your AIDD setup:
+  AI tools   claude 
+  Plugins    aidd-context · pm · refine · dev · vcs   
+  Memory     aidd_docs/ · 8 files synced   
+
+  claude's memory block drifted from the canonical shape.
+    Type [1] to re-wire it.
+
+ +
+
healthy, but no tests
+
🔍  Healthy — but no tests yet.
+
+  Flow:  ready for new work.
+
+  This project has no tests, so changes aren't protected.
+    Next: add tests   [1]
+      start new work [2] · improve the project [3] · explore [?]
+
+ +
+
+ +
+
06

Detail on demand

[?] opens the full view — ids, tiers, reasons

+
+ +
+
[?] expanded
+
Details —
+
+  1. finish your changes   aidd-dev:02-implement   (it will ask you a few questions)
+  2. review your changes   aidd-dev:05-review      (runs on its own)
+
+  AI tools   claude 
+  Plugins    aidd-context · pm · refine · dev · vcs   
+  Memory     aidd_docs/ · 8 files synced   
+
+  explain <n> · recap · stop · back [<]
+
+ +
+
+ + +
diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-1.md b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-1.md new file mode 100644 index 00000000..1ab7b6c6 --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-1.md @@ -0,0 +1,59 @@ +--- +status: done +--- + + + +# Instruction: Update the skill-authoring contract + +## Architecture projection + +> Tree of the final files. ✅ create · ✏️ modify · ❌ delete + +```txt +plugins/aidd-context/skills/04-skill-generate/references/ +└── ✏️ skill-authoring.md # relax R3, add conditional-load + notation rules +``` + +## Tasks to do + +### `1)` Relax the one-level reference rule + +> References may nest so a step loads only what it needs. + +1. Rewrite R3: references MAY sit in sub-folders (`references//`); a reference still never `@`-chains another reference. +2. State the load-locality rule: split a file from another ONLY when some execution path needs one without the other; co-loaded content stays one file. + +### `2)` Add the notation rule + +> Sanction terse notation and diagrams. + +1. Add a rule: reference/action bodies use telegraphic notation (tables, `→` for linear chains, fragments), never at the cost of a load-bearing condition. +2. Add: use a Mermaid diagram only for branching logic, not for a linear chain. + +### `3)` Define the router (SKILL.md) format + +> A leaner, self-evident action format — no field to interpret. + +1. Frontmatter: official keys only (`name`, `description`, `argument-hint`); forbid an invented `kind`-style flag. +2. Body: a tiny `# Title`, then the chaining shown as a one-line arrow schema for a pipeline (`a → b → c ↺`) or the line `Pick one per request.` for a menu; no separate flow prose. +3. Actions table columns `# | Action | Does`, `Does` verb-led and telegraphic; drop the restated intro sentence and the `Input` column (it lives in each action's `## Input`). +4. Move "read an action's file just before running it" to a standing contract rule, not repeated per skill. + +### `4)` Reconcile the rest of the contract + +> Keep R1-R13 coherent after the edits. + +1. Re-read R13 (includes) against nested paths; adjust wording so an action cites a nested reference by its full `@`. +2. Confirm no other rule contradicts nesting; renumber or note scope if needed. + +## Test acceptance criteria + + + +| Task | Acceptance criteria | +| ---- | ----------------------------------------------------------------------------------- | +| 1 | R3 permits a `references//file.md` and still bans reference-to-reference `@`-chains. | +| 2 | The contract names the telegraphic-notation rule and the Mermaid-only-for-branching rule. | +| 3 | The router format is specified: tiny title, arrow-schema for a pipeline or "pick one" for a menu, verb-led `Does`, no intro sentence, no `Input` column, no invented frontmatter flag. | +| 4 | No rule in the contract contradicts nested references; R13 covers nested `@` citation. | diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-2.md b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-2.md new file mode 100644 index 00000000..5c60f11c --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-2.md @@ -0,0 +1,53 @@ +--- +status: done +--- + + + +# Instruction: Scan action + state refs + +## Architecture projection + +> Tree of the final files. ✅ create · ✏️ modify · ❌ delete + +```txt +plugins/aidd-context/skills/00-onboard/ +├── actions/ +│ └── ✏️ 01-scan.md # loads state/ refs conditionally, adds AI-tools detection +└── references/ + ├── ✅ state/zones.md # the check catalogue per zone (from checks.md) + ├── ✅ state/detection.md # AI-tool roots + per-tool wiring status + ├── ✅ state/done-rule.md # session ledger / re-nag kill (from checks.md) + ├── ✅ state/hedge.md # plan-status build-to-ship pin (from checks.md) + └── ❌ checks.md # content split into state/ and order/ (order/ in phase 3) +``` + +## Tasks to do + +### `1)` Carve the state references out of checks.md + +> Tiny files, one concern each. + +1. `state/zones.md`: the zone checks as a terse table (met/drift rule, deliverable, command, tier); keep the state-aware architecture rule (established => tech stack ✓, greenfield => ❌). +2. `state/detection.md`: roots `.claude .codex .cursor .opencode .github/copilot-instructions.md .github/{instructions,agents,skills,prompts}` => tool; per-tool wiring = its context file carries the memory block. Glyphs: `✓` used+wired · `⚠` used, not wired · `✗` required missing. Unused optional tools omitted. +3. `state/done-rule.md`: a step is done when disk proves it OR the session ledger recorded it run/left; 01 reads, 03 writes; no file. +4. `state/hedge.md`: plan `status:` => `in-progress` pins Build alone, `implemented`/open-PR pins Review-then-Ship, unreadable pins Build-then-Review. + +### `2)` Rewrite 01-scan to load state refs conditionally + +> Pay only for what the scan needs. + +1. Load `state/zones.md` and `state/detection.md` every scan; `state/hedge.md` only when a plan exists; re-read `state/done-rule.md`'s ledger every scan. +2. Add the detection step: resolve each AI-tool root to a tool and its wiring status. +3. Keep cross-branch scoping: only the current branch's PR sets the dev-flow pin. + +## Test acceptance criteria + + + +| Task | Acceptance criteria | +| ---- | -------------------------------------------------------------------------------------------- | +| 1 | Each `state/*.md` holds exactly one concern and no `@`-chain to another reference. | +| 2 | The snapshot carries per-tool detection (`✓/⚠/✗`) with unused tools absent, not crossed. | +| 2 | A plan `status: in-progress` yields Build-alone; a repo-wide PR on another branch sets no pin. | +| 2 | A step recorded in the session ledger is absent from the next scan's actionable set. | diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-3.md b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-3.md new file mode 100644 index 00000000..a430c1b5 --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-3.md @@ -0,0 +1,73 @@ +--- +status: done +--- + + + +# Instruction: Assess + run actions + +## Architecture projection + +> Tree of the final files. ✅ create · ✏️ modify · ❌ delete + +```txt +plugins/aidd-context/skills/00-onboard/ +├── actions/ +│ ├── ✅ 02-assess.md # snapshot => decision (state class, ranked next, chosen screen) +│ ├── ✅ 04-run.md # renamed from 03-run.md, executes the reply +│ └── ❌ 03-run.md +└── references/ + ├── ✅ order/ranking.md # next-action order (from checks.md) + ├── ✅ order/idle-menu.md # 3 umbrellas + explore (from checks.md) + ├── ✅ order/screen-map.md # Mermaid: state => which screen + ├── ✅ run/replies.md # key routing (from run-tiers.md) + ├── ✅ run/tiers.md # auto/guided/manual + default-overridable (from run-tiers.md) + ├── ✅ run/return.md # return-to-onboard on GUIDED handoff (from run-tiers.md) + └── ❌ run-tiers.md # content split into run/ +``` + +## User Journey + +```mermaid +flowchart TD + SN[01 scan snapshot] --> AS[02 assess] + AS --> PR[03 present] + PR --> RP{reply} + RP -->|number| RUN[04 run: step or umbrella] + RP -->|OK| WALK[04 run: walk pending] + RP -->|?/back| PR + RP -->|recap/explain/stop| RO[read-only] + RUN --> SN + WALK --> SN +``` + +## Tasks to do + +### `1)` Build the assess action + order refs + +> Turn the raw snapshot into one decision. + +1. `order/ranking.md`: 1 unmet foundation, 2 earliest dev-flow step, 3 fired health tool, 4 idle menu; hold 2-4 while a foundation is unmet. +2. `order/idle-menu.md`: umbrellas `start new work [1]` · `improve the project [2]` · `customize the AI [3]` · `explore [?]`; an umbrella pick re-renders its installed members. +3. `order/screen-map.md`: a Mermaid `stateDiagram` mapping state (greenfield / existing / drift / idle / mid-work) to the screen to render. +4. `02-assess.md`: read the `01-scan` snapshot, load `order/`, output the decision (state class, ranked next-action, chosen screen); hand to `03-present`. No rendering here. + +### `2)` Carve the run refs + build 04-run + +> Execute a reply, delegate the how. + +1. `run/replies.md`: keys `[n] [OK] [?] recap explain skip stop`, each's effect; read-only vs re-scan; `[?]`/`back` re-render via `03-present` without re-assessing. +2. `run/tiers.md`: AUTO/GUIDED/MANUAL semantics; tier is a default, overridable when the skill supports the other mode. +3. `run/return.md`: on a GUIDED handoff, tell the user to re-run onboard to return; the ledger drops the handed-off step. +4. Rename `03-run.md` => `04-run.md`: load `run/replies.md` always, `run/tiers.md` only when running a step, `run/return.md` only on a GUIDED handoff; write the ledger per `state/done-rule.md` after each handled step. + +## Test acceptance criteria + + + +| Task | Acceptance criteria | +| ---- | --------------------------------------------------------------------------------------- | +| 1 | `02-assess` outputs a decision and renders nothing; `screen-map.md` is a Mermaid diagram. | +| 1 | Ranking holds dev-flow/health/idle while a foundation is unmet; an umbrella pick re-renders a member sub-list. | +| 2 | `[?]`/`back` re-render via `03-present` with no re-scan and no re-assess. | +| 2 | A GUIDED handoff emits the return-to-onboard line; the re-scan does not re-recommend the handed-off step. | diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-4.md b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-4.md new file mode 100644 index 00000000..19a8ad6a --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-4.md @@ -0,0 +1,84 @@ +--- +status: done +--- + + + +# Instruction: Present action (tutorial render) + +## Architecture projection + +> Tree of the final files. ✅ create · ✏️ modify · ❌ delete + +```txt +plugins/aidd-context/skills/00-onboard/ +├── actions/ +│ ├── ✅ 03-present.md # renamed from 02-report.md, renders the screen assess chose +│ └── ❌ 02-report.md +├── references/ +│ └── ✅ flow.md # 8-step curriculum + 2 foundation paths, source of [map] +└── assets/ + ├── ✏️ report.md # the screen shapes (state block, foundations, flow, next, [?], warnings) + └── ✅ banner.txt # AIDD ASCII banner, injected +``` + +## Wireframe + + + +```txt +The confirmed screens are the mockup gallery: ./onboard-mockups.html +(18 screens, 6 sections, colleague-approved). Render to match it. Canonical examples: + + █████╗ ██╗██████╗ ██████╗ <- banner.txt + AI-Driven Development + +👋 Welcome back. + +Your AIDD setup: + AI tools claude ✓ codex ⚠ + Plugins aidd-context · pm · refine · dev · vcs ✓ + Memory aidd_docs/ · 8 files synced ✓ + +⚠ codex is installed but its memory isn't wired (no AGENTS.md). + → Type [1] to wire it. + +--- flow (walk vs SDLC) --- + brainstorm → spec* → plan → implement → assert → review → commit → PR + [1] Walk it with me [2] Let SDLC drive it map [m] · [?] +``` + +## Tasks to do + +### `1)` Write the curriculum reference + +> The teaching content, on-demand only. + +1. `flow.md`: the 8 steps (brainstorm, spec*, plan, implement, assert, review, commit, PR) each with a one-line what/why; the vertical annotated layout (tutorial) and the horizontal compact layout (`[map]`). +2. Add the two foundation paths: existing => memory-first (2 steps, bootstrap skipped); greenfield => stack, memory, wire (3 steps). + +### `2)` Author the render shapes + +> Rich screens, terse rules. + +1. `assets/banner.txt`: the AIDD ASCII banner as a plain injected block. +2. `assets/report.md`: the state block (glyph semantics + warning-carries-a-fix line), the framing line (first report only), foundations-step screen, the flow screen, the `Next` line with keys, the `[?]` detail. Keep load-bearing rules; examples live in `flow.md`, banner in `banner.txt`. + +### `3)` Rewrite 03-present + +> Render the screen assess chose, delegate the shape. + +1. Rename `02-report.md` => `03-present.md`; render the screen named in the `02-assess` decision, filling `assets/report.md`. +2. Load `banner.txt` only on entry screens; `flow.md` only on flow/walk screens. +3. Every `⚠` renders with its plain cause and a fix action; unused tools omitted. + +## Test acceptance criteria + + + +| Task | Acceptance criteria | +| ---- | ----------------------------------------------------------------------------------------- | +| 1 | `flow.md` lists all 8 steps with what/why and both layouts; both foundation paths present. | +| 2 | A rendered `⚠` line names the cause and offers a keyed fix; the framing line shows only on the first report. | +| 3 | An existing repo renders memory as foundation step 1 of 2; a greenfield renders the stack first. | +| 3 | The banner appears on entry screens only; a warning screen loads no `flow.md`. | diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-5.md b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-5.md new file mode 100644 index 00000000..d411fdd1 --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/phase-5.md @@ -0,0 +1,51 @@ +--- +status: done +--- + + + +# Instruction: Router, description, docs, budget + +## Architecture projection + +> Tree of the final files. ✅ create · ✏️ modify · ❌ delete + +```txt +plugins/aidd-context/skills/00-onboard/ +├── ✏️ SKILL.md # router: short description, action table (scan|present|run), refs/assets, principles +└── ✏️ README.md # human doc, tutorial framing +plugins/aidd-context/ +└── ✏️ CATALOG.md # auto-synced by the pre-commit hook +``` + +## Tasks to do + +### `1)` Rewrite the router + +> Lean SKILL.md; the only always-on cost is the description. + +1. Description: verb-led, `Use when` triggers led by "onboard me", `Not for` clause; target <= ~65 tokens. +2. Body in the phase-1 router format: tiny `# Onboard` title, the pipeline schema `scan → assess → present → run ↺`, then the `# | Action | Does` table with verb-led telegraphic `Does`. No intro sentence, no `Input` column. +3. List the nested references and assets; transversal rules as principles only, no render detail; `argument-hint: scan | assess | present | run`. + +### `2)` Update the human doc + +1. README: reframe onboard as a guided tutorial (banner, state block, flow, walk-or-SDLC); it is not model-loaded, so no token budget applies. + +### `3)` Verify the token budget and links + +> Prove the economy, not assert it. + +1. Measure: description tokens (always-on) and the model-loaded total; record the before/after delta against the noob-first checkpoint. +2. Run the markdown-link check across the skill; every nested `@` resolves. + +## Test acceptance criteria + + + +| Task | Acceptance criteria | +| ---- | --------------------------------------------------------------------------------------- | +| 1 | SKILL.md is a pure router in the phase-1 format (tiny title, `scan → assess → present → run ↺` schema, verb-led `Does`, no intro/`Input`); the description is <= ~65 tokens and leads triggers with "onboard me". | +| 2 | README describes the tutorial flow and names no token rule for itself. | +| 3 | The measured model-loaded total is recorded with its delta; the link check reports zero broken links. | +| regress | Cross-branch PR scoping, session ledger, state-aware foundations, plan-status hedge, tier default+override, framing line, warnings-carry-a-fix, recap reply, and return-to-onboard all still hold end-to-end. | diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/plan.md b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/plan.md new file mode 100644 index 00000000..204cc9a3 --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/plan.md @@ -0,0 +1,40 @@ +--- +objective: "onboard is rebuilt as a token-optimized guided tutorial over a granular, conditional-load file tree that teaches the AIDD flow, every current behavior preserved, and the skill-authoring contract updated to sanction the new structure." +status: implemented +--- + + + +# Plan: Onboard tutorial rebuild + +## Overview + +| Field | Value | +| ---------- | ----------------------------------------------------------------------------------------- | +| **Goal** | Turn onboard from a status dashboard into a didactic, token-lean tutorial teaching the AIDD flow. | +| **Source** | This conversation's agreed design; mockup gallery [`onboard-mockups.html`](./onboard-mockups.html) (colleague-approved). | + +## Phases + +| # | Phase | File | +| --- | ---------------------------------- | ---------------------------- | +| 1 | Update the skill-authoring contract | [`phase-1.md`](./phase-1.md) | +| 2 | Scan action + state refs | [`phase-2.md`](./phase-2.md) | +| 3 | Assess + run actions (order/ + run/) | [`phase-3.md`](./phase-3.md) | +| 4 | Present action (tutorial render) | [`phase-4.md`](./phase-4.md) | +| 5 | Router, description, docs, budget | [`phase-5.md`](./phase-5.md) | + +## Decisions + + + +| Decision | Why | +| -------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- | +| Stay Markdown; no JSON/XML format swap | Measured (tiktoken): XML +16..29%, JSON content-dependent (+12% tabular). Format is a trap. | +| Two token surfaces: always-on = description only; everything else on-demand | The description loads for every skill each session; the body/refs load only when used. | +| Split files only along conditional-load boundaries | Split A from B only if a path needs A without B; co-loaded content stays one file. | +| State-aware foundations order: existing repo => memory first (bootstrap skipped); greenfield => stack, memory, wire | Memory feeds on the project; empty repo has nothing to memorize, so the stack comes first. | +| Update `skill-generate/references/skill-authoring.md` to allow nested references | The granular tree needs `references/state|order|run/`, which today's R3 forbids. | +| Tutorial verbosity (banner, curriculum) lives in on-demand assets/refs, never in SKILL.md | Keeps the always-on and router surfaces lean while the tutorial stays rich. | +| Four actions, one per responsibility and file group: scan (state/), assess (order/), present (assets/+flow), run (run/) | `[?]`/`back` re-renders via present without re-deciding, so present is a real boundary from assess. | +| Router format: tiny title, an arrow schema (`a → b ↺` pipeline) or "pick one" (menu), verb-led telegraphic `Does`; drop the intro, the `Input` column, and any invented frontmatter flag | The mode reads itself with no field to interpret; official frontmatter keys only. | diff --git a/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/review.md b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/review.md new file mode 100644 index 00000000..354696ae --- /dev/null +++ b/aidd_docs/tasks/2026_07/2026_07_08_onboard-tutorial-rebuild/review.md @@ -0,0 +1,61 @@ +# Review: Onboard tutorial rebuild + +- **Verdict**: approve +- **Diff**: `eee269d...HEAD` +- **Axes run**: code, functional, relevancy +- **Date**: 2026_07_09 +- **Findings**: 0 critical, 0 warning, 0 minor (review-round findings resolved below) + +## Phases + +### Phase 1 — Update the skill-authoring contract + +- [x] R3 permits `references//file.md` and still bans ref→ref `@`-chains — `skill-authoring.md:9` +- [x] Contract names telegraphic-notation and mermaid-only-for-branching — `skill-authoring.md:28` (R14) +- [x] Router format specified (tiny title, arrow/pick-one schema, verb-led Does, no intro/Input, official frontmatter only) — `skill-authoring.md:50` +- [x] No rule contradicts nesting; R13 covers nested `@` — `skill-authoring.md:26` + +### Phase 2 — Scan action + state refs + +- [x] Each `state/*.md` one concern, no ref→ref `@`-chain — `references/state/` +- [x] Snapshot carries per-tool `✓/⚠`, unused tools absent — `01-scan.md:19`, `state/detection.md` +- [x] Plan `in-progress` pins Implement-alone; repo-wide PR on another branch sets no pin — `state/hedge.md`, `state/zones.md:14` +- [x] Ledger-recorded step absent next scan — `state/done-rule.md`, `01-scan.md:16` + +### Phase 3 — Assess + run actions + +- [x] `02-assess` outputs a decision, renders nothing; `screen-map.md` is mermaid — `actions/02-assess.md`, `order/screen-map.md` +- [x] Ranking holds dev-flow/health/idle while a foundation unmet; umbrella pick re-renders — `order/ranking.md`, `order/idle-menu.md` +- [x] `?`/`back` re-render via present, no re-scan/assess — `run/replies.md`, `04-run.md` +- [x] GUIDED handoff emits the return line — `run/return.md`, `04-run.md:14` + +### Phase 4 — Present action + +- [x] `flow.md` lists 8 steps with what/why, both layouts, both foundation paths — `references/flow.md` +- [x] `⚠️` renders cause + keyed fix; framing first report only — `assets/report.md:38`, `03-present.md` +- [x] Existing repo memory step 1 of 2; greenfield stack first — `flow.md`, `order/screen-map.md` +- [x] Banner on entry screens only; warning screen no `flow.md` — `03-present.md:11` + +### Phase 5 — Router, description, docs, budget + +- [x] SKILL.md pure router in the new format; description leads "onboard me" — `SKILL.md` (66 tok, at the ~65 target) +- [x] README describes the tutorial, no token rule for itself — `README.md` +- [x] Measured total recorded with delta; link check zero broken — commit `963c661` + +## Findings + +| Sev | Kind | Phase | Location | Issue | Outcome | +| --- | ---- | ----- | -------- | ----- | ------- | +| 🟡 | conform | 4 | `state/detection.md`, `state/zones.md`, `assets/report.md` | Glyph semantics defined three times in two vocabularies; breaks R6 one-home | fixed — state refs describe status in words; the display glyph legend single-homed in `report.md` | +| 🟡 | fit | 2 | `state/zones.md` | Dev-flow stages `brainstorm`/`assert`/`commit` have no cheap disk signal, yet presented as detectable | fixed — `zones.md` splits disk-detectable from inferred pins | +| 🟢 | rot | 3 | `run/tiers.md`, `assets/report.md` | Tier→clause mapping duplicated | fixed — `report.md` points to `run/tiers.md` | +| 🟢 | code | 4 | `assets/report.md` | where-you-are screen uses `🔍`/`Flow:` | no_change_needed — matches the approved mockup (state screens use `🔍`, welcome uses `👋` by design) | + +## Verification + +| Metric | Value | +| ------------- | ---------------------------------------------------------------------------- | +| Verified | 100% (17/17) | +| Files checked | SKILL.md, README.md, actions/*, references/state/*, references/order/*, references/run/*, references/flow.md, assets/report.md, assets/banner.txt, skill-authoring.md | +| Unchecked | none (description at 66 tok is within the `~65` target, not-applicable) | +| Unplanned | CATALOG.md regenerated by the summarize-plugin-catalogs hook (expected); parasitic `aidd_docs/plans` deletions restored, not in any commit | diff --git a/plugins/aidd-context/CATALOG.md b/plugins/aidd-context/CATALOG.md index 78647903..07249a81 100644 --- a/plugins/aidd-context/CATALOG.md +++ b/plugins/aidd-context/CATALOG.md @@ -1,6 +1,6 @@ # aidd-context catalog -Auto-generated index of skills, agents, references and assets shipped by the `aidd-context` plugin. +Auto-generated framework content: agents, commands, rules, skills, and templates. > This file is automatically updated by the `scripts/summarize-markdown.js` script. @@ -45,12 +45,13 @@ Auto-generated index of skills, agents, references and assets shipped by the `ai | Group | File | Description | |-------|------|---| | `actions` | [01-scan.md](skills/00-onboard/actions/01-scan.md) | - | -| `actions` | [02-report.md](skills/00-onboard/actions/02-report.md) | - | -| `actions` | [03-run.md](skills/00-onboard/actions/03-run.md) | - | +| `actions` | [02-assess.md](skills/00-onboard/actions/02-assess.md) | - | +| `actions` | [03-present.md](skills/00-onboard/actions/03-present.md) | - | +| `actions` | [04-run.md](skills/00-onboard/actions/04-run.md) | - | +| `assets` | [banner.txt](skills/00-onboard/assets/banner.txt) | - | | `assets` | [report.md](skills/00-onboard/assets/report.md) | - | -| `references` | [checks.md](skills/00-onboard/references/checks.md) | - | -| `references` | [run-tiers.md](skills/00-onboard/references/run-tiers.md) | - | -| `-` | [SKILL.md](skills/00-onboard/SKILL.md) | `Scan an AIDD project into a diagnostic of what is set up and missing, then run the recommended next commands in order. Use when the user asks where to start, what to do next, how the project stands, or to onboard onto AIDD. Not for listing every installed surface.` | +| `references` | [flow.md](skills/00-onboard/references/flow.md) | - | +| `-` | [SKILL.md](skills/00-onboard/SKILL.md) | `Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface.` | #### `skills/01-bootstrap` diff --git a/plugins/aidd-context/skills/00-onboard/SKILL.md b/plugins/aidd-context/skills/00-onboard/SKILL.md index 76bc2e2a..6dfb04a6 100644 --- a/plugins/aidd-context/skills/00-onboard/SKILL.md +++ b/plugins/aidd-context/skills/00-onboard/SKILL.md @@ -1,42 +1,32 @@ --- name: 00-onboard -description: Scan an AIDD project into a diagnostic of what is set up and missing, then run the recommended next commands in order. Use when the user asks where to start, what to do next, how the project stands, or to onboard onto AIDD. Not for listing every installed surface. -argument-hint: scan | report | run +description: Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface. +argument-hint: scan | assess | present | run --- # Onboard -Scans the current project against the AIDD framework, reports what is present, drifting, or missing as an explicit checklist, hands back a single ordered list of the commands to run next, and runs them on request. +```mermaid +flowchart LR + scan --> assess --> present --> run --> scan +``` ## Actions -| # | Action | Role | Input | -| --- | -------- | ---------------------------------------------------------------------------------------- | ---------------- | -| 01 | `scan` | Read the project once, silently, into a snapshot: every check in `checks.md`, status per zone | project root | -| 02 | `report` | Render the loud diagnostic plus one ordered command list, foundations then dev flow | the 01 snapshot | -| 03 | `run` | Run the user's pick per its tier, `OK` walks the whole list pausing at each GUIDED step, then re-scan | the user's reply | +Run the actions in that order, looping. Read an action's file in `actions/` before running it. -Run `01 → 02 → 03`, then loop back to `01` after each run until the user stops. Run each action's `## Test` before the next. Before running an action, read its file in `actions/`, not only the table or assets. - -## References - -- `references/checks.md`: the diagnostic catalogue, four zones ordered, each check with its met rule, drift rule, deliverable, command, and run tier. -- `references/run-tiers.md`: the AUTO, GUIDED, and MANUAL run tiers, how `OK` chains them, the loop, and explain-on-demand. - -## Assets - -- `assets/report.md`: the report shape action 02 renders. +| # | Action | Does | +| -- | ------- | -------------------- | +| 01 | scan | read the project | +| 02 | assess | decide the next step | +| 03 | present | show the screen | +| 04 | run | act on the reply | ## Transversal rules -- Report, do not lecture. State status as glyphs, never a raw label or snapshot. A plain-language explanation of a step appears only when the user asks for it. -- Name real commands only. Never name a command whose skill `01` did not find installed; name a missing one as a gap by function. -- Never run a GUIDED step unattended, and never test a plugin version against a registry. -- Re-scan after a run, never trust a stale status. Wait for an explicit reply before running anything. -- Requires only the `aidd-context` plugin installed and a working directory rooted in the target project. The `aidd_docs/` memory bank is not a prerequisite: on a project without it, the first recommendation is to set it up. Onboard is the entry point, so it works before anything else exists. - -Detail lives in the references: the check catalogue and ranking in `checks.md`, the run tiers and `OK` walk in `run-tiers.md`, the render shape and glyphs in `assets/report.md`. - -## External data - -- `../02-project-memory/references/memory-block.md`: the canonical `` block shape the form-drift check compares against. +- Guide, do not lecture or dump. +- Name real commands only, never invented ones. +- Never run a GUIDED step unattended. +- Never test a plugin version against a registry. +- Never trust a stale status. +- Wait for an explicit reply before running anything. diff --git a/plugins/aidd-context/skills/00-onboard/actions/01-scan.md b/plugins/aidd-context/skills/00-onboard/actions/01-scan.md index afea78a6..891caff1 100644 --- a/plugins/aidd-context/skills/00-onboard/actions/01-scan.md +++ b/plugins/aidd-context/skills/00-onboard/actions/01-scan.md @@ -1,29 +1,27 @@ # 01 - Scan -Read the project once, silently, into a reusable snapshot. No questions, no writes, no visible output. +Read the project into a snapshot. ## Input -The project root, the current working directory. +The project root. ## Output -A silent snapshot, never printed: the status (`✓ ⚠ ✗` or not-applicable) of every check in `@../references/checks.md`, the installed AIDD plugins and skills each with its description, and the project name and purpose from the brief when memory is synced. +The project snapshot, printed nowhere. ## Process -1. **Check.** Evaluate every check in `@../references/checks.md` by its own met and drift rules: a met fact (disk, or a cheap VCS read where the row says so) sets `✓`, a missing artifact sets `✗`, and only the row's stated drift case sets `⚠`. Scope each check to the paths the row names, never an installed-plugin tree. -2. **Drift.** For the context block, compare the AI context file's `` block against the canonical shape. - - ```md - @../../02-project-memory/references/memory-block.md - ``` - -3. **List.** Gather the enabled AIDD plugins and skills, each with its description, via the tool's native discovery. This is what `02` resolves each command against. -4. **Hold.** Keep the snapshot in context, read this fully only once a session, and hand to `02-report`. Print nothing. +1. **Zones.** Evaluate the checks per `@../references/state/zones.md`. +2. **Detect.** Resolve AI tools and wiring per `@../references/state/detection.md`. +3. **Ledger.** Drop done steps per `@../references/state/done-rule.md`. +4. **Hedge.** If a plan exists, pin the build-to-ship stage per `@../references/state/hedge.md`. +5. **List.** Gather installed AIDD plugins and skills via native discovery. +6. **Hold.** Keep the snapshot in context. Print nothing. ## Test -- Zero user-visible output: no snapshot, no checklist, no status appears. -- The snapshot carries a status for every check in `checks.md` and the installed skills with descriptions. -- No report or command is emitted by this action. +- Scan prints nothing. +- The snapshot carries a status per check. +- It carries the detected AI tools with wiring, and the installed skills. +- A ledgered step and a cross-branch PR never enter the snapshot's actionable set. diff --git a/plugins/aidd-context/skills/00-onboard/actions/02-assess.md b/plugins/aidd-context/skills/00-onboard/actions/02-assess.md new file mode 100644 index 00000000..4ba9902c --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/actions/02-assess.md @@ -0,0 +1,25 @@ +# 02 - Assess + +Turn the snapshot into one decision. + +## Input + +The project snapshot. + +## Output + +The decision, ready to render. + +## Process + +1. **Classify.** State class per `@../references/order/screen-map.md`. +2. **Rank.** Top next action per `@../references/order/ranking.md`. + - Idle: build the menu per `@../references/order/idle-menu.md`. +3. **Resolve.** Match each command to an installed skill. + - Absent: name a gap by function, never invent a command. + +## Test + +- Assess renders nothing. +- Dev-flow, health, and idle stay back while a foundation is unmet. +- An idle decision offers the three umbrellas plus explore. diff --git a/plugins/aidd-context/skills/00-onboard/actions/02-report.md b/plugins/aidd-context/skills/00-onboard/actions/02-report.md deleted file mode 100644 index 943cafe4..00000000 --- a/plugins/aidd-context/skills/00-onboard/actions/02-report.md +++ /dev/null @@ -1,26 +0,0 @@ -# 02 - Report - -Show the loud diagnostic and one ordered command list. Concrete, scannable, no lecture. - -## Input - -The snapshot from `01-scan` (statuses + installed skills), held in context, not printed. - -## Process - -1. **Resolve.** For each check, resolve its canonical command in `@../references/checks.md` against the installed skills from `01`. A match keeps the command. No match names a gap by function, never an invented command. -2. **Order.** Rank the recommended list per the `## Ranking` policy in `@../references/checks.md`. -3. **Tag.** Give each recommended line its tier badge from `@../references/checks.md`: `⚡ auto`, `💬 guided`, or `🖐 manual`. -4. **Render.** Fill `@../assets/report.md`, following its glyph vocabularies, collapse, and footer rules. -5. **Wait.** Offer the report and wait for a reply. Never auto-advance. Hand the reply to `03-run`. - -## Output - -The rendered report per `@../assets/report.md`: emoji section headers, a foundations checklist, an optional context-artifacts row, a dev-flow track, one ordered `Do this next` list of command plus tier badge plus plain purpose, and a one-line footer. No internal names or raw statuses beyond the glyphs. - -## Test - -- Foundations render above dev flow; every recommended line carries a concrete installed command, a tier badge, and a plain purpose, or is a gap named by function. -- Context artifacts stay info only, collapsed to "none yet" when all absent, never in `Do this next`. -- Nothing uninstalled is named as a command. -- The footer is present, one line, and states what `OK` does in this state. diff --git a/plugins/aidd-context/skills/00-onboard/actions/03-present.md b/plugins/aidd-context/skills/00-onboard/actions/03-present.md new file mode 100644 index 00000000..8372be56 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/actions/03-present.md @@ -0,0 +1,38 @@ +# 03 - Present + +Render the screen the decision names. + +## Input + +The current decision. + +## Output + +The rendered screen, and the user's reply. + +## Process + +1. **Shape.** Fill the chosen screen from `@../assets/report.md`. + - Framing line on the first report of the session only. + - Exactly one action block per screen, carrying its key once. + - The idle menu is a next-action block. Slot 1 is the action line, slots 2 to 4 join the options line. Never a list. + - Glyphs: ✅ met · ⚠️ present, not wired · ❌ missing. + - A used tool that lacks the block is `⚠️`, never `❌`. Only a missing required foundation takes `❌`. + - Every `⚠️` shows its cause and a keyed fix. + - Short lines. + - The options line is the last line. Print nothing after it, no detail block, no state snapshot, no hint about what comes next. + - Command ids, tier clauses, and lookahead only under `[?]`. +2. **Inject.** + - Entry screen takes `@../assets/banner.txt`. + - Flow or walk screen loads `@../references/flow.md`. +3. **Wait.** Offer the screen, take the reply. + +## Test + +- The framing line shows on the first report of the session only. +- An existing repo renders memory as step 1 of 2. +- A greenfield repo renders the stack first. +- The banner shows on entry screens only. +- Every `⚠️` carries a keyed fix. +- The key appears once per screen. +- Nothing renders after the options line. diff --git a/plugins/aidd-context/skills/00-onboard/actions/03-run.md b/plugins/aidd-context/skills/00-onboard/actions/03-run.md deleted file mode 100644 index 6e34f3e3..00000000 --- a/plugins/aidd-context/skills/00-onboard/actions/03-run.md +++ /dev/null @@ -1,25 +0,0 @@ -# 03 - Run - -Carry out the user's reply per its tier, then loop back to scanning. - -## Input - -- The user's reply from `02-report`: `OK`, a step number, an explain request, or stop. -- The resolved command per line, or a gap when no installed skill fits. -- The snapshot from `01-scan`, held in context. - -## Process - -1. **Route.** Carry out the reply per `@../references/run-tiers.md`: `OK` walks the list, a number runs one step, explain and stop stay read-only. -2. **Guard.** Run or name only skills `01` found installed. A gap never invokes a skill: offer explain or stop. Never run a MANUAL step, only show it. -3. **Loop.** After any step or the `OK` walk runs, re-scan (`→ 01`) and re-render so a resolved `✗` flips to `✓`. A read-only reply does not re-scan. - -## Output - -One outcome per `@../references/run-tiers.md`, always ending with the refreshed report or a clean stop. - -## Test - -- `OK` walks the whole list, runs AUTO steps unattended, and pauses at each GUIDED step for input rather than running it unattended. -- A MANUAL step is shown, never run; a gap invokes nothing. -- After a step or the `OK` walk runs, the re-scan flips resolved statuses; a read-only reply does not re-scan. diff --git a/plugins/aidd-context/skills/00-onboard/actions/04-run.md b/plugins/aidd-context/skills/00-onboard/actions/04-run.md new file mode 100644 index 00000000..1bb70b26 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/actions/04-run.md @@ -0,0 +1,33 @@ +# 04 - Run + +Carry out the reply. + +## Input + +- The user's reply, per `@../references/run/replies.md`. +- The current decision, its resolved commands or a gap. + +## Output + +The reply carried out. + +## Process + +1. **Route.** Carry out the reply per `@../references/run/replies.md`. +2. **Guard.** + - Run only installed skills. + - A gap invokes nothing. + - A MANUAL step is shown, not run. +3. **Tier.** Running a step, apply `@../references/run/tiers.md`. +4. **Return.** On a GUIDED handoff, emit the return line per `@../references/run/return.md`. +5. **Record.** Write the handled step to the ledger per `@../references/state/done-rule.md`. +6. **Loop.** After a run or `OK` walk, re-scan. + - A read-only reply or umbrella pick does not. + +## Test + +- `OK` runs AUTO unattended and pauses at each GUIDED. +- A MANUAL step is shown, never run. +- A gap invokes nothing. +- `?`/`back` re-render with no re-scan. +- A GUIDED handoff emits the return line. diff --git a/plugins/aidd-context/skills/00-onboard/assets/banner.txt b/plugins/aidd-context/skills/00-onboard/assets/banner.txt new file mode 100644 index 00000000..42283623 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/assets/banner.txt @@ -0,0 +1,7 @@ + █████╗ ██╗██████╗ ██████╗ +██╔══██╗██║██╔══██╗██╔══██╗ +███████║██║██║ ██║██║ ██║ +██╔══██║██║██║ ██║██║ ██║ +██║ ██║██║██████╔╝██████╔╝ +╚═╝ ╚═╝╚═╝╚═════╝ ╚═════╝ + AI-Driven Development 🇫🇷 diff --git a/plugins/aidd-context/skills/00-onboard/assets/report.md b/plugins/aidd-context/skills/00-onboard/assets/report.md index e7a595c2..811a6751 100644 --- a/plugins/aidd-context/skills/00-onboard/assets/report.md +++ b/plugins/aidd-context/skills/00-onboard/assets/report.md @@ -1,34 +1,65 @@ - + -🔍 — AIDD checkup +## Entry — greenfield · existing · idle · drift -🏗️ Foundations - ... -🧩 Context artifacts (optional) - <✓/✗ per artifact, inline> +```txt + -🚦 Dev flow - +👋 -✨ Do this next - 1. - ... +Your AIDD setup: + AI tools + Plugins ✅ + Memory - ↳ " · "explain project" (only when memory is filled) · stop> + - +```txt +Foundations — step of + + + () + + > + +👉 Type [1] to start. skip [s] +``` + +## Action block — warning with a fix + +```txt +⚠️ + → Type [1] to . +``` + +## Action block — next action + +```txt +👉 [1] +``` + +## Where you are — mid-work + +```txt +🔍 + + Flow: + +👉 Next: [1] + +``` + +## [?] detail + +```txt +Details — + 1. () + + explain · explain project · recap · stop · back [<] +``` diff --git a/plugins/aidd-context/skills/00-onboard/references/checks.md b/plugins/aidd-context/skills/00-onboard/references/checks.md deleted file mode 100644 index 34d5f304..00000000 --- a/plugins/aidd-context/skills/00-onboard/references/checks.md +++ /dev/null @@ -1,68 +0,0 @@ -# Diagnostic catalogue - -Every check `01-scan` captures and `02-report` renders, in report order. Four zones. Foundations first, then dev flow, then health. - -Each row carries: the **met** rule (a disk fact = `✓`), the **drift** rule (`⚠`, missing or off-format), the **deliverable** named to the user, the canonical **command**, and the **tier** (see `run-tiers.md`). A command resolves to the installed skill by its id, or is named a gap by function when that skill is not installed. - -## Ranking - -The order of the `Do this next` list, the single home for this policy: - -1. Unmet zone-1 foundations, in table order. -2. The earliest unmet dev-flow step. -3. Any health tool whose signal fired. - -While any zone-1 foundation is unmet, hold the dev-flow and health steps back, so a bare repo lists only its setup steps. Zone-2 artifacts never enter this list; surface one only when the user picks it. - -## Zone 1: AIDD context (foundations) - -| Check | Met (`✓`) | Drift (`⚠`) | Deliverable | Command | Tier | -| ------------- | ----------------------------------------------- | -------------------------------------------------------- | ---------------- | -------------------------- | ------ | -| architecture | `aidd_docs/INSTALL.md` exists | — | stack design | `aidd-context:01-bootstrap` | GUIDED | -| memory bank | `aidd_docs/memory/` exists with real content | files empty or placeholder | project memory | `aidd-context:02-project-memory` | GUIDED | -| context block | `` block present in the AI context file, on the canonical shape | block present but off the canonical shape, see external data (absent block or no context file is `✗`, not `⚠`) | memory wiring | `aidd-context:02-project-memory` | GUIDED | - -Architecture is only `❌` on a truly greenfield repo: no source code **and** no synced memory bank. An established project (code present, or the memory bank already synced) has moved past stack design, so the check is **not applicable** (`➖`), not a loud `❌`, and never recommends bootstrap. Keys on files on disk, not commit history. - -## Zone 2: Context-gen artifacts (foundations, optional) - -Scoped to **project-level** artifacts only, under the tool's own config root (`.claude/`, `.cursor/`, `.github/`, `AGENTS.md`). Never count a plugin's shipped source: an artifact under `plugins/*/` or any installed-plugin directory is the framework's product, not this project's context, and does not meet these checks. - -| Check | Met (`✓`) | Deliverable | Command | Tier | -| -------- | -------------------------------------------------- | ----------- | --------------------------- | ------ | -| rules | a project rule file present | rules | `aidd-context:05-rule-generate` | GUIDED | -| agents | a project agent under `.claude/agents/` (or peer) | agents | `aidd-context:06-agent-generate` | GUIDED | -| skills | a project skill under `.claude/skills/` (or peer) | skills | `aidd-context:04-skill-generate` | GUIDED | -| hooks | a `hooks` entry in the tool's settings | hooks | `aidd-context:08-hook-generate` | GUIDED | -| commands | a project command under `.claude/commands/` (or peer) | commands | `aidd-context:07-command-generate` | GUIDED | - -These are optional and **info only**: show their status in the checklist, never a loud `✗`. Ranking (above) keeps them out of `Do this next` and the `OK` walk. - -## Zone 3: Dev flow - -The per-work sequence, in order. Each step resolves to an installed skill by function; the commands below are the canonical resolution. - -| Step | Present when | Command (canonical) | Tier | -| ------- | ----------------------------------- | ---------------------------------- | ------ | -| clarify | a spec or refined need under `aidd_docs/` | `aidd-pm:04-spec` | GUIDED | -| track | a tracked item exists | `aidd-pm:02-user-stories` | GUIDED | -| plan | a `plan.md` under `aidd_docs/` | `aidd-dev:01-plan` | GUIDED | -| build | code present against the plan | `aidd-dev:02-implement` | GUIDED | -| review | build looks done, nothing reviewed | `aidd-dev:05-review` | AUTO | -| ship | an open PR, or merged and unreleased | `aidd-vcs:02-pull-request` | MANUAL | - -Stages are cumulative. A downstream artifact implies the upstream stages are met, so a project with a plan starts the flow at build, not clarify. Build never proves review or ship, so surface both when code looks done and let the user pick. - -`clarify` and `track` have no direct disk signal; they are the place only when no downstream artifact exists, never a loud default. `review` and `ship` read cheap VCS state (an open PR), not a pure disk fact. - -## Zone 4: Health (tools, not steps) - -A fired health tool enters `Do this next` ranked **after** the earliest dev-flow step, never above it, and never while a zone-1 foundation is unmet (the held-back rule in `## Ranking` applies to health too). It is a beside-the-flow tool, never the ordered default. Scan **project source only**. Exclude templates, fixtures, examples, generated output, and any installed-plugin tree (`plugins/*/`, `.claude/plugins/`, `node_modules/`); a marker inside example or template content is not a real marker. - -| Signal | Met when | Deliverable | Command | Tier | -| ----------------- | ------------------------------------- | ----------- | ------------------- | ---- | -| no tests | no real test files | add tests | `aidd-dev:06-test` | GUIDED | -| bug markers | `TODO` / `FIXME` or reported errors in project source | debug | `aidd-dev:08-debug` | GUIDED | -| messy code sample | a file far longer or deeper than siblings | audit | `aidd-dev:04-audit` | AUTO | - -Reading memory-file contents to judge drift and a single bounded code sample are the only sanctioned non-cheap reads. diff --git a/plugins/aidd-context/skills/00-onboard/references/flow.md b/plugins/aidd-context/skills/00-onboard/references/flow.md new file mode 100644 index 00000000..c8dac4c0 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/flow.md @@ -0,0 +1,27 @@ +# AIDD flow curriculum + +## Foundations (state-aware) + +- Existing (code present): memory first, stack skipped. `project memory` → `connect to the AI`. +- Greenfield (empty): `design tech stack` → `project memory` → `connect to the AI`. + +## Feature flow — 8 steps + +| Step | What | Why | +| ------------ | --------------------------- | ------------------------------ | +| brainstorm | vague idea → precise | fuzzy idea makes every step guess | +| spec* | the contract of what to build | one agreed definition, no drift | +| plan | break into phases | small units that ship + verify | +| implement | build phase by phase | verified phases beat one leap | +| assert | check it behaves | catch breakage before review | +| review | verdict before shipping | ship or iterate, decided | +| commit | save the work | atomic, reversible record | +| pull request | ship it | open for merge | + +`[map]`: `brainstorm → spec* → plan → implement → assert → review → commit → PR` + +`*`: optional + +## Run it + +`[1]` walk with me, step by step · `[2]` hand the whole flow to `aidd-dev:00-sdlc` diff --git a/plugins/aidd-context/skills/00-onboard/references/order/idle-menu.md b/plugins/aidd-context/skills/00-onboard/references/order/idle-menu.md new file mode 100644 index 00000000..1601a00e --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/order/idle-menu.md @@ -0,0 +1,14 @@ +# Idle menu + +When ranks 1-3 are clear, the idle menu offers four choices. + +| Slot | Choice | Opens (installed members) | +| ---- | ------------------- | -------------------------------------------------------------------- | +| 1 | start new work | `aidd-dev:00-sdlc`, or `aidd-refine:01-brainstorm` for a fuzzy idea | +| 2 | improve the project | `aidd-dev:` `04-audit` · `06-test` · `07-refactor` | +| 3 | customize the AI | the **missing** `aidd-context:` generators: rule `05-rule-generate`, workflow `04-skill-generate`, agent `06-agent-generate`, command `07-command-generate`, hook `08-hook-generate` | +| 4 | explore | `aidd-context:11-explore` + anything not in 1-3 | + +- Slots 2 and 3 are umbrellas: a pick re-renders the member sub-list, a member pick runs. Slots 1 and 4 run directly. +- Installed members only. Drop an empty umbrella. +- Choices, not a chain: `OK` never walks the idle menu. diff --git a/plugins/aidd-context/skills/00-onboard/references/order/ranking.md b/plugins/aidd-context/skills/00-onboard/references/order/ranking.md new file mode 100644 index 00000000..d62a726f --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/order/ranking.md @@ -0,0 +1,10 @@ +# Next-action order + +First match wins. + +1. Unmet foundation, in `zones.md` order. +2. Earliest unmet dev-flow stage, hedged by `state/hedge.md`. +3. A fired health tool. +4. Idle menu (see `idle-menu.md`) — only when 1-3 are all clear. + +While any foundation is unmet, hold 2-4 back: a bare repo lists only its setup steps. diff --git a/plugins/aidd-context/skills/00-onboard/references/order/screen-map.md b/plugins/aidd-context/skills/00-onboard/references/order/screen-map.md new file mode 100644 index 00000000..0637cff4 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/order/screen-map.md @@ -0,0 +1,9 @@ +# Screen map + +| State class | When | Screen | +| ----------- | ---------------------------- | --------------------------------------------------- | +| greenfield | no code, no memory | welcome + foundations, stack first (3 steps) | +| existing | code present, memory missing | welcome + foundations, memory first (2 steps) | +| drift | a foundation is ⚠ | welcome + the warning-with-fix | +| midwork | a dev-flow step pending | where-you-are on the flow + the next step | +| idle | all clear | welcome + the flow (walk or SDLC), or the idle menu | diff --git a/plugins/aidd-context/skills/00-onboard/references/run-tiers.md b/plugins/aidd-context/skills/00-onboard/references/run-tiers.md deleted file mode 100644 index a03e6905..00000000 --- a/plugins/aidd-context/skills/00-onboard/references/run-tiers.md +++ /dev/null @@ -1,38 +0,0 @@ -# Run tiers - -How `03-run` carries out the user's pick. Every step in `checks.md` carries one tier. Only ever run or name a skill that `01` found installed. - -## The three tiers - -| Tier | What it is | How onboard runs it | -| ------ | ------------------------------------------- | -------------------------------------------------------------------------- | -| AUTO | Non-interactive, safe to spawn and walk away | Invoke the resolved skill, let it run to completion, then move on | -| GUIDED | Interactive, drives its own Q&A | Launch the resolved skill in this session, let the user drive it, resume when it returns | -| MANUAL | Side-effecting or outward-facing | Show the exact command, do not run it, move on and leave it for the user | - -The run mechanism is per step, not one size. An AUTO step may invoke its skill directly or fan out to `aidd-dev:10-todo`; onboard follows the command the check names, never forces a single orchestrator. - -## The `OK` walk - -When the user replies `OK` to the report, walk the ordered list top to bottom, one step at a time: - -1. **AUTO step:** run it to completion, then continue to the next. -2. **GUIDED step:** launch it and hand control to the user. When it returns, continue to the next. -3. **MANUAL step:** show the command, run nothing, note it is left for the user, continue. -4. After the walk, re-scan (`→ 01`) and render the refreshed report. - -`OK` drives the whole list, not just a prefix. It pauses at each GUIDED step for the user's input and resumes after, so a greenfield project's setup chain runs end to end from one `OK`. State up front how many steps the walk covers and which need input. - -## Other replies - -| Reply | What happens | -| --------------- | --------------------------------------------------------------------------------------------- | -| a step number | Run that one step per its tier | -| explain a step | Describe the step and its command in two or three plain lines, then re-offer. Never runs a skill | -| explain project | Summarize the project from its memory bank, read-only, then re-offer. Only when memory is filled | -| stop | One-line close, end the loop | -| a gap | The step has no installed skill. Say it needs a plugin, by function only. Offer explain or stop | - -## Loop - -After any step runs, re-scan (`→ 01`) and re-render the report so a resolved `✗` flips to `✓`. A read-only reply (explain, stop) does not re-scan. Wait for an explicit reply before running anything. diff --git a/plugins/aidd-context/skills/00-onboard/references/run/replies.md b/plugins/aidd-context/skills/00-onboard/references/run/replies.md new file mode 100644 index 00000000..a7776ec2 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/run/replies.md @@ -0,0 +1,14 @@ +# Replies + +| Reply | Effect | +| ------------- | --------------------------------------------------------------------------------- | +| a number `[n]`| run that step, or open an idle-menu umbrella | +| `OK` | walk the pending steps (ranks 1-3) in order, never the idle menu | +| `?` | expand the full detail (command ids, tier clauses, per-check reasons), read-only | +| `back` / `<` | re-render the prior screen, read-only, no re-scan | +| `recap` | summarize this session's conversation, read-only, only when a prior conversation exists | +| `explain ` | describe a step in two or three plain lines, read-only | +| `explain project` | summarize the project from its memory bank, read-only, only when memory is filled | +| `skip` | record the step left in the ledger, it does not re-fire | +| `stop` | one-line close, end the loop | +| a gap | no installed skill, say it needs a plugin by function, offer explain or stop | diff --git a/plugins/aidd-context/skills/00-onboard/references/run/return.md b/plugins/aidd-context/skills/00-onboard/references/run/return.md new file mode 100644 index 00000000..8654e287 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/run/return.md @@ -0,0 +1,3 @@ +# Return to onboard + +A GUIDED step hands off to a skill that may not return control. So on every handoff, tell the user one line: re-run onboard to come back (the sure path is its slash command). The re-scan drops the handed-off step, so they resume, not repeat. diff --git a/plugins/aidd-context/skills/00-onboard/references/run/tiers.md b/plugins/aidd-context/skills/00-onboard/references/run/tiers.md new file mode 100644 index 00000000..94ce4345 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/run/tiers.md @@ -0,0 +1,12 @@ +# Tiers + +The tier is a default, overridable. + +| Tier | Clause | How it runs | +| ------ | --------------------------------- | ------------------------------------------------------------ | +| AUTO | (runs on its own) | invoke, run to completion, continue | +| GUIDED | (it will ask you a few questions) | launch, hand to the user, resume on return (see `return.md`) | +| MANUAL | (you run this one yourself) | show the command, run nothing, leave it for the user | + +- A dual-mode skill (interactive by default, unattended on request, e.g. `aidd-dev:00-sdlc`) runs the other way when the user asks and the skill supports it. +- On the `OK` walk, state up front how many steps it covers and which need input. diff --git a/plugins/aidd-context/skills/00-onboard/references/state/detection.md b/plugins/aidd-context/skills/00-onboard/references/state/detection.md new file mode 100644 index 00000000..f6601115 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/state/detection.md @@ -0,0 +1,18 @@ +# AI tool detection + +Which AI tools the project uses, and whether each has its memory wired. For the state block's AI-tools line. + +A tool is used when its own dir exists, or when a file only that tool reads exists. A file several tools read (`AGENTS.md`) is a wiring target, never a detection signal. + +| Tool | Used when | Wired when this file has the block | +| -------- | ------------------------------------------------------------------------------------ | ---------------------------------- | +| claude | `.claude/` or `CLAUDE.md` | `CLAUDE.md` | +| codex | `.codex/` | `AGENTS.md` | +| cursor | `.cursor/` or `.cursorrules` | `AGENTS.md` | +| opencode | `.opencode/` | `AGENTS.md` | +| copilot | `.github/copilot-instructions.md` or `.github/{instructions,agents,skills,prompts}/` | `.github/copilot-instructions.md` | + +- Detected tools only. An unused optional tool is omitted, never crossed. +- No tool detected at all: the row reads `none yet`, uncrossed. The memory row's `❌` already carries the gap. +- A used tool whose file lacks the block is not wired, and needs wiring. +- Missing memory is a foundation status, not a tool row (see `zones.md`). diff --git a/plugins/aidd-context/skills/00-onboard/references/state/done-rule.md b/plugins/aidd-context/skills/00-onboard/references/state/done-rule.md new file mode 100644 index 00000000..9070e4d4 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/state/done-rule.md @@ -0,0 +1,6 @@ +# Done rule (session ledger) + +Stops onboard from re-recommending a step already handled this session. In-context state, no file. + +- Done = a disk signal proves it, OR the ledger recorded it run or left (a read-only review, a MANUAL step left, a skip). +- Re-read every scan, so a step recorded since drops out. Disk and VCS facts refresh on change, not every loop. diff --git a/plugins/aidd-context/skills/00-onboard/references/state/hedge.md b/plugins/aidd-context/skills/00-onboard/references/state/hedge.md new file mode 100644 index 00000000..fe44590d --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/state/hedge.md @@ -0,0 +1,12 @@ +# Plan-status hedge + +The plan's `status:` frontmatter refines the build-to-ship pin, so review is never skipped nor premature. + +| Plan `status:` | Pin | +| ---------------------------- | ------------------------------------- | +| `pending` | To implement | +| `in-progress` | Implement alone | +| `implemented` | Review | +| `reviewed` | Ship (commit, pull request) | +| `blocked` | surface the blocker, not a normal pin | +| the field is missing or unreadable | surface the plan as broken, not a normal pin | diff --git a/plugins/aidd-context/skills/00-onboard/references/state/zones.md b/plugins/aidd-context/skills/00-onboard/references/state/zones.md new file mode 100644 index 00000000..c0f57b54 --- /dev/null +++ b/plugins/aidd-context/skills/00-onboard/references/state/zones.md @@ -0,0 +1,41 @@ +# State zones + +Disk/VCS checks that place the project. Each check is met, drift (present, off canonical shape), or missing. + +## Foundations + +State-aware order: existing repo (code) => memory first, stack skipped. Greenfield => stack → memory → wire. + +| Check | Met when | Drift when | Deliverable | Command | +| -------------- | ------------------------------------------------------------- | ------------------------ | -------------------------- | -------------------------------- | +| tech stack | `INSTALL.md` exists OR repo established (code or synced memory) | — | tech stack | `aidd-context:01-bootstrap` | +| project memory | `aidd_docs/memory/` has real content | files empty/placeholder | project knowledge saved | `aidd-context:02-project-memory` | +| memory wiring | the standard `` block in each used tool's context file | block present, off shape | knowledge loaded by the AI | `aidd-context:02-project-memory` | + +- tech stack missing only on greenfield (no code AND no synced memory). +- memory wiring: no block or no context file = missing. Drift = a block present but not the standard one that imports the memory files. + +## Dev flow + +Cumulative: a downstream artifact implies the upstream stages met. The pin sits on the furthest reached. + +| Stage | Detected when | +| --------- | --------------------------------------------- | +| spec | a spec under `aidd_docs/`, nothing downstream | +| plan | `plan.md`, no code against it | +| implement | code against the plan | +| review | code done, current branch PR awaits review | +| PR | current branch has an open PR | + +- `review` and `PR` read VCS **current branch only** — ignore repo-wide PRs and review queues (another branch is another dev). +- `brainstorm`, `assert`, and `commit` have no cheap signal. The plan `status:` hedge and cumulative state place the pin (see `hedge.md`). + +## Health + +Beside-the-flow tools, surfaced only when their signal fires. Scan project source only, not templates, fixtures, examples, generated output, or installed-plugin trees. + +| Signal | Fires when | Command | +| ----------- | ------------------------------------------- | ------------------- | +| no tests | no real test files | `aidd-dev:06-test` | +| bug markers | `TODO`/`FIXME` or reported errors in source | `aidd-dev:08-debug` | +| messy code | a file far longer/deeper than siblings | `aidd-dev:04-audit` | diff --git a/plugins/aidd-ui/CHANGELOG.md b/plugins/aidd-ui/CHANGELOG.md index 4c711514..d3745adb 100644 --- a/plugins/aidd-ui/CHANGELOG.md +++ b/plugins/aidd-ui/CHANGELOG.md @@ -8,6 +8,20 @@ * **framework:** read action files before running, across all skills ([#389](https://github.com/ai-driven-dev/framework/issues/389)) ([9d592a6](https://github.com/ai-driven-dev/framework/commit/9d592a6d8c1ca3d0ac8f8aaf54e30e7186a8eb48)) +### Miscellaneous + +* release main ([#392](https://github.com/ai-driven-dev/framework/issues/392)) ([484928c](https://github.com/ai-driven-dev/framework/commit/484928c8429999194cbe163782099b26c89e4105)) +* release main ([#393](https://github.com/ai-driven-dev/framework/issues/393)) ([426c604](https://github.com/ai-driven-dev/framework/commit/426c604dba9f5f1c586ade768e55c90f914a4562)) +* release main ([#404](https://github.com/ai-driven-dev/framework/issues/404)) ([5f6d84f](https://github.com/ai-driven-dev/framework/commit/5f6d84f3a7cad604c45ee7b4831c77f7cf281717)) + +## [0.1.0-alpha.0](https://github.com/ai-driven-dev/framework/compare/aidd-ui-v0.1.0-alpha.0...aidd-ui-v0.1.0-alpha.0) (2026-07-07) + + +### Features + +* **framework:** read action files before running, across all skills ([#389](https://github.com/ai-driven-dev/framework/issues/389)) ([9d592a6](https://github.com/ai-driven-dev/framework/commit/9d592a6d8c1ca3d0ac8f8aaf54e30e7186a8eb48)) + + ### Miscellaneous * release main ([#392](https://github.com/ai-driven-dev/framework/issues/392)) ([484928c](https://github.com/ai-driven-dev/framework/commit/484928c8429999194cbe163782099b26c89e4105))