fix(privacy): de-personalize installed skill payload + add PII gate

Every skill file here is written into a recipient's ~/.claude/skills/ by the
installers, so maintainer-specific prose became instructions to somebody else's
Claude — including a full client roster in concise-skill/references/copywriting.md
that reached a client's own team. A downstream scrub landed 2026-06-23; upstream
never followed, and the 2026-08-17 digest overwrote it.

- Rewrite skill prose in the second person; drop the client/project roster,
  private vault paths, and operator-specific timezone/commit/name rules.
- Replace the personal overrides block with an "Operator overrides (fill these
  in)" template so recipients configure their own.
- Genericize example values in cheat sheets and the install-flow walkthrough.
- Add scripts/check-pii.sh with two tiers: generic markers (real home paths,
  bare emails) live in the script; the private roster is supplied at runtime
  from .pii-patterns.local locally and the PII_EXTRA_PATTERNS secret in CI, so
  the list itself never ships in a public repo.
- Wire it into .github/workflows/security.yml and the pre-commit hook so a
  reintroduction fails locally and again on push.

Attribution in README/LICENSE/SECURITY/CHANGELOG is unchanged and allowlisted.

Author: fidgetcoding

.github/workflows/security.yml

@@ -48,6 +48,32 @@ jobs:
           fi
           echo "No hardcoded secrets detected"
 
+  pii-guard:
+    name: Personal-context guard
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - name: Block maintainer PII and client names in shippable files
+        env:
+          # Private marker list (client/project roster, vault name). Kept in a
+          # secret so the roster never appears in this public repo — a hardcoded
+          # list would publish the exact thing the guard protects. Generic checks
+          # (real home paths, bare emails) run even when the secret is unset.
+          PII_EXTRA_PATTERNS: ${{ secrets.PII_EXTRA_PATTERNS }}
+        run: |
+          # Every skill file here installs into somebody else's ~/.claude/skills/.
+          # Personal names, client rosters, and private vault paths must not ship.
+          # Regression on 2026-08-17: an update overwrote a downstream scrub and
+          # redistributed the client roster to 5 external installers.
+          if [ -z "${PII_EXTRA_PATTERNS:-}" ]; then
+            echo "::warning::PII_EXTRA_PATTERNS secret is unset — only generic checks ran. Set it in repo settings for full roster coverage."
+          fi
+          if ! ./scripts/check-pii.sh; then
+            echo "::error::Personal operating context detected in shippable files — see matches above"
+            exit 1
+          fi
+
   download-url-check:
     name: Verify pinned download URLs are reachable
     runs-on: ubuntu-latest

.gitignore

@@ -27,3 +27,6 @@ credentials.json
 
 # Node (defensive — step scripts may install deps)
 node_modules/
+
+# Private PII marker list for scripts/check-pii.sh — never commit.
+.pii-patterns.local

.pii-patterns.local.example

@@ -0,0 +1,32 @@
+# .pii-patterns.local.example
+#
+# Copy to `.pii-patterns.local` (gitignored) and fill in YOUR OWN private
+# markers. scripts/check-pii.sh reads that file and fails any commit or push
+# that would ship one of these strings in the pack.
+#
+# Why this file is separate: the pack is public. If the roster lived in
+# scripts/check-pii.sh, the guard would publish the exact thing it protects.
+# Keep the real list here (local) and in the PII_EXTRA_PATTERNS repo secret (CI).
+#
+# Format: one POSIX extended regex per line. Blank lines and # comments ignored.
+# They are joined with `|`, so keep each line a self-contained alternative.
+
+# --- Your name, as it must never appear in shippable skill prose -------------
+# The skills install into other people's machines; a name here becomes an
+# instruction to address THEM by YOUR name.
+#YourFirstName
+#YourFullName
+#your-macos-username
+
+# --- Your client and project codenames --------------------------------------
+# This is the important one. A client roster in a skill file can reach a
+# different client's team.
+#CLIENT-ONE
+#CLIENT-TWO
+#PROJECT-CODENAME
+
+# --- Your private vault / working directory names ----------------------------
+#MYVAULT
+
+# --- Anything else you would not want a stranger's Claude to read aloud ------
+#your-private-domain\.com

CHANGELOG.md

@@ -16,9 +16,9 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 - **`/landing-ab` skill** — self-driving landing pages per the 5-level PostHog ladder (static → watch → test → auto-iterate → personalize). Every new landing page ships with a `signup-cta`-tagged CTA, PostHog autocapture + heatmaps wired at build time, a `landing-ab` feature-flag stub, and a `docs/LP-OPS.md` carrying the L3–L5 playbook (95%+ / ≥50-exposure test calls, weekly PostHog-MCP optimizer loop, cohort personalization). Vendored at `landing-ab-skill/` (SKILL.md + companion UserPromptSubmit hook `landing-ab-intent.sh`). Listed in the `install.sh` skill summary; not yet wired into a step installer.
 - **`/agent-business` skill** — turn any app into an AI agent business via the 6-op playbook: pick market → reverse-engineer the data → stack (Claude + n8n + Postgres) → messaging hookup (LoopMessage / Twilio / Unipile) → inbound brain → proactive coach cron. Phone-number-keyed schema, log tools per signal, 2-texts-a-day cap. Vendored at `agent-business-skill/` (single SKILL.md). Listed in the `install.sh` skill summary; not yet wired into a step installer.
 - **`/bullets` skill** (step 4) — crushes a paragraph or prose blob into the shortest scannable bullets: one fact per bullet, ≤~12 words, zero fluff, every signal preserved (names, numbers, dates, paths, decisions). Always outputs bullets — built because `/concise` decides shape per reply and sometimes leaves prose, which is wrong for document handoffs where nobody should have to read a blob. Triggers on `/bullets` and in plain English ("bullet this", "bulletize", "turn this into bullets"). Vendored at `bullets-skill/` (single SKILL.md). Installed by Step 4 as an inline heredoc alongside `/w4w` and `/concise` (no network dependency); self-test asserts SKILL.md landed. Listed across `README.md`, `CHEATSHEET.md`, `README-SECTIONS/cheat-sheet.md`, `install.sh` + `update.sh` summaries, the Step 4 self-test + summary, and the `uninstall.sh` Step 4 removal loop.
-- **`/recon` skill** (step 7) — pre-build prior-art reconnaissance. On build-intent ("build / make / start a new X", "does X exist?") it offers a one-line prompt first (never auto-runs — Nate sometimes clones a known paid tool on purpose), then sweeps GitHub via the `gh` CLI + the web for existing free and paid options, ranks the top ~10 in a comparison table, finds the edge (or honestly calls it a red ocean), and ends with a GREEN/YELLOW/RED verdict. Output is a discussion, not code. Vendored at `recon-skill/` (single SKILL.md). Installed by Step 7 alongside `/gitfix` (depends on the `gh` CLI Step 7 already installs); no PAT needed. Step 7 installer downloads from `fidgetcoding/cli-maxxing/main` via curl with a local fallback, the non-interactive path installs it too, and the self-test asserts SKILL.md landed. Listed across `README.md`, `CHEATSHEET.md`, `README-SECTIONS/cheat-sheet.md`, `install.sh` + `update.sh` summaries, `step-final` self-test, and the `uninstall.sh` Step 7 removal.
+- **`/recon` skill** (step 7) — pre-build prior-art reconnaissance. On build-intent ("build / make / start a new X", "does X exist?") it offers a one-line prompt first (never auto-runs — you sometimes clone a known paid tool on purpose), then sweeps GitHub via the `gh` CLI + the web for existing free and paid options, ranks the top ~10 in a comparison table, finds the edge (or honestly calls it a red ocean), and ends with a GREEN/YELLOW/RED verdict. Output is a discussion, not code. Vendored at `recon-skill/` (single SKILL.md). Installed by Step 7 alongside `/gitfix` (depends on the `gh` CLI Step 7 already installs); no PAT needed. Step 7 installer downloads from `fidgetcoding/cli-maxxing/main` via curl with a local fallback, the non-interactive path installs it too, and the self-test asserts SKILL.md landed. Listed across `README.md`, `CHEATSHEET.md`, `README-SECTIONS/cheat-sheet.md`, `install.sh` + `update.sh` summaries, `step-final` self-test, and the `uninstall.sh` Step 7 removal.
 - **`/concise` skill** (step 4) — default chat-shape filter. No fluff, no scaffolding, no headers on simple questions, no sycophancy. Auto-suspends for copywriting deliverables (tweets, scripts, decks, client docs) so it doesn't sand down voice on output going to a human audience. Vendored at `concise-skill/` (SKILL.md + 3 references — `copywriting.md`, `inputs.md`, `code-and-commits.md`). Step 4 installer downloads from `lorecraft-io/cli-maxxing/main` via curl with a local fallback for offline / pre-publish runs. Self-test asserts SKILL.md + copywriting.md reference landed. Listed across `README.md`, `CHEATSHEET.md`, `install.sh` summary, `update.sh` summary, and `uninstall.sh` skill removal loop.
-- `pdf-skill` — markdown→PDF renderer enforcing Nate's house style (single H1 from frontmatter `title:`, strips body H1 / Purpose / Internal notes / Sources sections by default). Pandoc + WeasyPrint. Opt back in to dropped sections via `--keep-notes` / `--keep-sources`. Mirror of the global `~/.claude/skills/pdf/` skill.
+- `pdf-skill` — markdown→PDF renderer enforcing a consistent house style (single H1 from frontmatter `title:`, strips body H1 / Purpose / Internal notes / Sources sections by default). Pandoc + WeasyPrint. Opt back in to dropped sections via `--keep-notes` / `--keep-sources`. Mirror of the global `~/.claude/skills/pdf/` skill.
 - README: social-links badge strip (X · LinkedIn · YouTube · Instagram, ruvnet-style for-the-badge) inserted into the centered header block beneath the banner.
 - **`cbrain` + `cbraintg` shell shortcuts** (step 10.9) — quick-launch aliases for the Brain² + Telegram-bridged sessions.
 - Step 5 — full upstream URL verification across all five external MCPs (morgen / motion / playwright / granola / n8n).

CHEATSHEET.md

@@ -274,7 +274,7 @@ These are available in your terminal after Step 4 installs the FidgetFlo CLI.
 | Swarm not responding | Run `npx fidgetflo@latest doctor --fix` to diagnose |
 | MCP tools not connecting | Exit Claude, run `claude mcp list` to check connections, then relaunch |
 | `cbrain` not working | Run `cskip` instead, then tell Claude: "cbrain isn't working — can you figure out why and fix it?" Claude will find the problem, fix it, and get it working for future sessions. |
-| Obsidian vault not found | Vault setup lives in [2ndBrain-mogging](https://github.com/fidgetcoding/2ndBrain-mogging). Once set up, tell Claude the full path to your vault (e.g., `~/BRAIN2`). Avoid `~/Desktop/...` — macOS TCC protection breaks CLI access to the Desktop. |
+| Obsidian vault not found | Vault setup lives in [2ndBrain-mogging](https://github.com/fidgetcoding/2ndBrain-mogging). Once set up, tell Claude the full path to your vault (e.g., `~/MyVault`). Avoid `~/Desktop/...` — macOS TCC protection breaks CLI access to the Desktop. |
 | Shift+Return acts like Enter | Try Option+Enter as an alternative for multi-line input |
 
 ---

README-SECTIONS/cheat-sheet.md

@@ -204,7 +204,7 @@ These are available in your terminal after Step 4 installs the FidgetFlo CLI.
 | Swarm not responding | Run `npx fidgetflo@latest doctor --fix` to diagnose |
 | MCP tools not connecting | Exit Claude, run `claude mcp list` to check connections, then relaunch |
 | `cbrain` not working | Run `cskip` instead, then tell Claude: "cbrain isn't working — can you figure out why and fix it?" Claude will find the problem, fix it, and get it working for future sessions. |
-| Obsidian vault not found | Vault setup lives in [2ndBrain-mogging](https://github.com/fidgetcoding/2ndBrain-mogging). Once set up, tell Claude the full path to your vault (e.g., `~/BRAIN2`). Avoid `~/Desktop/...` — macOS TCC protection breaks CLI access to the Desktop. |
+| Obsidian vault not found | Vault setup lives in [2ndBrain-mogging](https://github.com/fidgetcoding/2ndBrain-mogging). Once set up, tell Claude the full path to your vault (e.g., `~/MyVault`). Avoid `~/Desktop/...` — macOS TCC protection breaks CLI access to the Desktop. |
 | Shift+Return acts like Enter | Try Option+Enter as an alternative for multi-line input |
 
 ---

agent-business-skill/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: agent-business
-description: Turn any app or human service into an AI agent business (Angus Sewell 6-op playbook, 2026-07-03). Use whenever Nate wants to build an AI agent that texts clients, a texting coach/tutor/advisor/consultant agent, an SMS/iMessage/WhatsApp agent, a service-as-an-agent business, or says "turn this app into an agent", "AI coach business", "agent that replaces a [coach/tutor/advisor]", or wants the app-to-agent playbook applied to a market. Also invocable directly as /agent-business.
+description: Turn any app or human service into an AI agent business (Angus Sewell 6-op playbook, 2026-07-03). Use whenever the user wants to build an AI agent that texts clients, a texting coach/tutor/advisor/consultant agent, an SMS/iMessage/WhatsApp agent, a service-as-an-agent business, or says "turn this app into an agent", "AI coach business", "agent that replaces a [coach/tutor/advisor]", or wants the app-to-agent playbook applied to a market. Also invocable directly as /agent-business.
 ---
 
 # /agent-business — turn any app into an AI agent business
 
 Every winning app is a cheap self-serve version of a service humans pay far more for. Rebuild that human service as an AI agent living between app and human: same outcome, fraction of the human's price. Worked example: texting AI fitness coach at $700/mo vs a $1,500+/mo human coach.
 
-**Source of truth:** `/Users/nathandavidovich/BRAIN2/02-Sources/SRC-2026-07-03-agent-business-build-guide.md` (archived PDF alongside).
+**Source:** Angus Sewell's app-to-agent build guide (2026-07-03).
 
 Run the 6 ops in order. Each op below = objective + the moves. Verbatim prompts live in the source note — pull them when executing.
 

bullets-skill/SKILL.md

@@ -53,4 +53,4 @@ Each bullet ≤ ~12 words. If one runs long, it's two facts → split. A dense p
 
 ## Boundaries
 
-This is chat/handoff formatting, not a copy deliverable — `/copywriting` does not apply. Nate overrides still hold: "Nate" never "Nathan", absolute paths, EST timestamps, no UTC.
+This is chat/handoff formatting, not a copy deliverable — `/copywriting` does not apply. Your operator overrides still hold: name/spelling rules, absolute paths, your timezone convention.