fix: portable paths, TTS toggle, junction merge, skill descriptions (issues #2 #3 #4, PR #1)

- Replace all hardcoded C:/Projects/memstack paths with $MEMSTACK_PATH in 7 skills
- Add MEMSTACK_DISABLE_TTS=true env var toggle to pre-tool-notify.sh
- Fix start-memstack.bat junction logic: merge rules into existing .claude dirs
- Expand api-integration skill description with auth/circuit-breaker details
- Add Pro upsell note to secrets-scanner skill

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: cwinvestments

.claude/hooks/pre-tool-notify.sh

@@ -1,6 +1,11 @@
 #!/bin/bash
 # Pre-tool TTS notification — reads config from .claude/tts-config.json
 
+# TTS notifications can be disabled by setting MEMSTACK_DISABLE_TTS=true
+if [ "$MEMSTACK_DISABLE_TTS" = "true" ]; then
+  exit 0
+fi
+
 CONFIG_FILE="${BASH_SOURCE%/*}/../tts-config.json"
 
 # Default message

skills/automation/api-integration/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: memstack-automation-api-integration
-description: "Use this skill when the user says 'API integration', 'connect APIs', 'sync data', 'data mapping', 'rate limiting', or needs system-to-system connectors with authentication, rate limit handling, and error recovery. Do NOT use for visual n8n workflows or webhook receiving."
+description: "Use this skill when the user says 'API integration', 'connect APIs', 'sync data', 'data mapping', 'rate limiting', or needs system-to-system connectors with authentication, rate limit handling, and error recovery. Generates API integration code with authentication (OAuth, API key, JWT), request/response mapping, rate limit handling, error recovery with circuit breakers, and sync monitoring. Do NOT use for visual n8n workflows or webhook receiving."
 version: 1.0.0
 license: "Proprietary — MemStack™ Pro by CW Affiliate Investments LLC. See LICENSE.txt"
 ---

skills/diary/SKILL.md

@@ -89,17 +89,17 @@ When the user asks to save a diary, keep these in mind:
 
 4. **Save to SQLite database** (primary storage):
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py add-session '{"project":"<name>","date":"<YYYY-MM-DD>","accomplished":"<bullets>","files_changed":"<bullets>","commits":"<bullets>","decisions":"<bullets>","problems":"<bullets>","next_steps":"<bullets>","duration":"<estimate>","raw_markdown":"<full text>"}'
+   python "$MEMSTACK_PATH/db/memstack-db.py" add-session '{"project":"<name>","date":"<YYYY-MM-DD>","accomplished":"<bullets>","files_changed":"<bullets>","commits":"<bullets>","decisions":"<bullets>","problems":"<bullets>","next_steps":"<bullets>","duration":"<estimate>","raw_markdown":"<full text>"}'
    ```
 
 5. **Also save decisions as insights** for cross-project search:
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py add-insight '{"project":"<name>","type":"decision","content":"<decision>","context":"Session <date>","tags":"<project>"}'
+   python "$MEMSTACK_PATH/db/memstack-db.py" add-insight '{"project":"<name>","type":"decision","content":"<decision>","context":"Session <date>","tags":"<project>"}'
    ```
 
 6. **Update project context** with last session date:
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py set-context '{"project":"<name>","last_session_date":"<YYYY-MM-DD>"}'
+   python "$MEMSTACK_PATH/db/memstack-db.py" set-context '{"project":"<name>","last_session_date":"<YYYY-MM-DD>"}'
    ```
 
 7. **Also save markdown copy** to `memory/sessions/{date}-{project}.md` (export format, human-readable backup)

skills/echo/SKILL.md

@@ -47,7 +47,7 @@ If you're thinking any of these, STOP — you're about to skip the protocol:
 
 Try LanceDB vector search first for best-quality results:
 ```bash
-python C:/Projects/memstack/skills/echo/search.py "<keywords>" --top-k 5
+python "$MEMSTACK_PATH/skills/echo/search.py "<keywords>" --top-k 5
 ```
 
 If this returns results, present them with scores, dates, and source files.
@@ -56,15 +56,15 @@ If this returns results, present them with scores, dates, and source files.
 
 Always run SQLite search to supplement vector results or as fallback if Step 1 fails:
 ```bash
-python C:/Projects/memstack/db/memstack-db.py search "<keywords>" --project <project>
+python "$MEMSTACK_PATH/db/memstack-db.py" search "<keywords>" --project <project>
 ```
 
 ### Step 3: Recent Sessions and Insights
 
 For additional context:
 ```bash
-python C:/Projects/memstack/db/memstack-db.py get-sessions <project> --limit 5
-python C:/Projects/memstack/db/memstack-db.py get-insights <project>
+python "$MEMSTACK_PATH/db/memstack-db.py" get-sessions <project> --limit 5
+python "$MEMSTACK_PATH/db/memstack-db.py" get-insights <project>
 ```
 
 ### Step 4: Markdown Fallback
@@ -90,19 +90,19 @@ If nothing found across all sources — say clearly: "No session logs found for
 
 To re-index sessions after new diary entries (normally done automatically):
 ```bash
-python C:/Projects/memstack/skills/echo/index-sessions.py
+python "$MEMSTACK_PATH/skills/echo/index-sessions.py
 ```
 
 Use `--force` to re-embed all content (e.g., after changing embedding model):
 ```bash
-python C:/Projects/memstack/skills/echo/index-sessions.py --force
+python "$MEMSTACK_PATH/skills/echo/index-sessions.py --force
 ```
 
 ## Inputs
 - Keywords from the user's prompt (project name, feature name, date range)
-- Vector DB: `C:\Projects\memstack\memory\vectors\lancedb\` (via LanceDB)
-- Database: `C:\Projects\memstack\db\memstack.db` (via memstack-db.py)
-- Fallback: `C:\Projects\memstack\memory\` (legacy markdown files)
+- Vector DB: `$MEMSTACK_PATH/memory\vectors\lancedb\` (via LanceDB)
+- Database: `$MEMSTACK_PATH/db\memstack.db` (via memstack-db.py)
+- Fallback: `$MEMSTACK_PATH/memory\` (legacy markdown files)
 
 ## Outputs
 - Ranked results with semantic similarity scores

skills/familiar/SKILL.md

@@ -24,7 +24,7 @@ Then execute the protocol below.
    - Working directory path
    - Full task description with acceptance criteria
    - Any shared context (database schema, API contracts, types)
-   - MemStack activation line: `Read C:\Projects\memstack\MEMSTACK.md`
+   - MemStack activation line: `Read $MEMSTACK_PATH/MEMSTACK.md`
    - CC Monitor reporting snippet (if configured in config.json)
 4. **Add coordination notes** — specify what each session should NOT touch to avoid conflicts
 5. **Define merge order** — which session's work should be committed first

skills/forge/SKILL.md

@@ -34,7 +34,7 @@ Then execute the protocol below.
    - Example usage
    - Level history starting at Lv.1
 
-3. **Write the file** to `C:\Projects\memstack\skills\{name}.md`
+3. **Write the file** to `$MEMSTACK_PATH/skills/{name}.md`
 
 4. **Update MEMSTACK.md** — add a new row to the Skill Index table
 

skills/project/SKILL.md

@@ -29,7 +29,7 @@ Then execute the protocol below.
 2. **Run git status** to capture uncommitted state
 3. **Save project context to SQLite:**
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py set-context '{"project":"<name>","status":"active","current_branch":"<branch>","last_session_date":"<YYYY-MM-DD>","known_issues":"<issues>","backlog":"<next tasks>"}'
+   python "$MEMSTACK_PATH/db/memstack-db.py" set-context '{"project":"<name>","status":"active","current_branch":"<branch>","last_session_date":"<YYYY-MM-DD>","known_issues":"<issues>","backlog":"<next tasks>"}'
    ```
 4. **Also save markdown handoff** to `memory/projects/{project}-{date}.md`
 5. **Present the ready-to-paste prompt** for the next CC session
@@ -38,15 +38,15 @@ Then execute the protocol below.
 
 1. **Load project context from SQLite:**
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py get-context <project>
+   python "$MEMSTACK_PATH/db/memstack-db.py" get-context <project>
    ```
 2. **Load recent sessions:**
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py get-sessions <project> --limit 3
+   python "$MEMSTACK_PATH/db/memstack-db.py" get-sessions <project> --limit 3
    ```
 3. **Load plan if exists:**
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py get-plan <project>
+   python "$MEMSTACK_PATH/db/memstack-db.py" get-plan <project>
    ```
 4. **Fallback:** Check `memory/projects/` for markdown handoffs
 5. **Present combined state** so CC can continue immediately
@@ -70,8 +70,8 @@ Then execute the protocol below.
 Saved: memory/projects/adminstack-2026-02-18.md
 
 --- PASTE INTO NEXT CC SESSION ---
-Working directory: C:\Projects\AdminStack
-Read C:\Projects\memstack\MEMSTACK.md
+Working directory: /path/to/your-project
+Read $MEMSTACK_PATH/MEMSTACK.md
 
 Resume AdminStack. Last session completed:
 - Built CC Monitor page with auto-refresh

skills/quill/SKILL.md

@@ -37,7 +37,7 @@ Then execute the protocol below.
 
 5. **Save to SQLite** (primary):
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py set-context '{"project":"<client>","last_quote_date":"<date>","quote_summary":"<scope>"}'
+   python "$MEMSTACK_PATH/db/memstack-db.py" set-context '{"project":"<client>","last_quote_date":"<date>","quote_summary":"<scope>"}'
    ```
 6. **Also save markdown copy** to `memory/projects/{client}-quote-{date}.md` (human-readable backup)
 7. **Present formatted** for copy-paste into email or PDF export

skills/security/secrets-scanner/SKILL.md

@@ -437,3 +437,7 @@ This manual skill remains available for **deep audits** — git history analysis
 - **Lv.1** — Base: 7-check scan (hardcoded secrets, .env audit, config/docs, env validation, client exposure, git history, Docker), pattern reference for 14+ secret formats, .env.example generation, remediation guide. Derived from real credential incidents across AdminStack, EpsteinScan, and 10+ production projects. (Origin: MemStack Pro v1.0, Mar 2026)
 - **Lv.2** — Audit feedback: Added deployment platform config scan (Netlify, Vercel, Railway, Render, Fly.io), base64-encoded secret detection, private key block detection (RSA/EC/DSA/OpenSSH PEM), pre-rotation checklist with dependency mapping and priority matrix. (Origin: AdminStack audit, Mar 2026)
 - **Lv.3** — Hook integration: Documented automated pre-commit and pre-push hook coverage (700+ credential formats), fallback behavior, and relationship between manual skill audits and automated hook scanning. (Origin: MemStack Pro v3.3.3, Mar 2026)
+
+## Pro Feature
+
+Pro: Secrets scanning hooks run automatically before every commit and push, covering 700+ credential formats across every major cloud provider and API service. Free version requires manual scanning only.

skills/work/SKILL.md

@@ -34,7 +34,7 @@ Before executing ANY mode, silently gather current state. Do NOT present finding
 2. Read the project's `CLAUDE.md` (if it exists) — conventions, architecture decisions
 3. Check recent diary:
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py get-sessions <project> --limit 3
+   python "$MEMSTACK_PATH/db/memstack-db.py" get-sessions <project> --limit 3
    ```
 4. Check git state:
    ```bash
@@ -51,7 +51,7 @@ Before executing ANY mode, silently gather current state. Do NOT present finding
 1. Parse the entire plan into individual numbered tasks
 2. For each task, save to SQLite:
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py add-plan-task '{"project":"<name>","task_number":<n>,"description":"<task>","status":"pending"}'
+   python "$MEMSTACK_PATH/db/memstack-db.py" add-plan-task '{"project":"<name>","task_number":<n>,"description":"<task>","status":"pending"}'
    ```
 3. Confirm with task count
 4. Also write a markdown copy to `memory/projects/{project}-plan.md` for human readability
@@ -64,11 +64,11 @@ Before executing ANY mode, silently gather current state. Do NOT present finding
 
 1. Read current plan from SQLite:
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py get-plan <project>
+   python "$MEMSTACK_PATH/db/memstack-db.py" get-plan <project>
    ```
 2. Update individual task statuses:
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py update-task '{"project":"<name>","task_number":<n>,"status":"completed"}'
+   python "$MEMSTACK_PATH/db/memstack-db.py" update-task '{"project":"<name>","task_number":<n>,"status":"completed"}'
    ```
 3. Add new tasks if needed via `add-plan-task`
 4. No size limits needed — SQLite handles scale
@@ -79,7 +79,7 @@ Before executing ANY mode, silently gather current state. Do NOT present finding
 
 1. Load plan from SQLite:
    ```bash
-   python C:/Projects/memstack/db/memstack-db.py get-plan <project>
+   python "$MEMSTACK_PATH/db/memstack-db.py" get-plan <project>
    ```
 2. Parse the JSON output for task statuses
 3. Output a summary:
@@ -103,8 +103,8 @@ Before executing ANY mode, silently gather current state. Do NOT present finding
 
 ## Inputs
 - Plan text (copy mode) or project name (append/resume)
-- Database: `C:\Projects\memstack\db\memstack.db` (via memstack-db.py)
-- Fallback: `C:\Projects\memstack\memory\projects\` (legacy markdown)
+- Database: `$MEMSTACK_PATH/db\memstack.db` (via memstack-db.py)
+- Fallback: `$MEMSTACK_PATH/memory\projects\` (legacy markdown)
 
 ## Outputs
 - Formatted task list with status indicators