feat(marketplace): hook migration, projman commands, optimizations [BREAKING]

Remove all SessionStart and PostToolUse hooks across the marketplace,
retaining only PreToolUse safety hooks and UserPromptSubmit quality hooks.
Add /project and /adr command families, /hygiene check, /cv status.
Create 7 new projman skills for project lifecycle management.
Remove /pm-debug, /suggest-version, /proposal-status commands.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-02-06 12:28:06 -05:00
parent 442ed63b4c
commit 9ba2e660d3
60 changed files with 1061 additions and 1828 deletions

View File

@@ -38,15 +38,13 @@ Read all plugin hooks from the marketplace:
```
plugins/code-sentinel/hooks/hooks.json
plugins/doc-guardian/hooks/hooks.json
plugins/project-hygiene/hooks/hooks.json
plugins/data-platform/hooks/hooks.json
plugins/contract-validator/hooks/hooks.json
plugins/git-flow/hooks/hooks.json
plugins/cmdb-assistant/hooks/hooks.json
plugins/clarity-assist/hooks/hooks.json
```
For each hook, extract:
- Event type (PreToolUse, PostToolUse, SessionStart, etc.)
- Event type (PreToolUse, UserPromptSubmit)
- Tool matchers (Write, Edit, MultiEdit, Bash patterns)
- Hook command/script
@@ -54,12 +52,13 @@ For each hook, extract:
Create a mapping of which review layers cover which operations:
| Operation | PreToolUse Hooks | PostToolUse Hooks | Other Gates |
|-----------|------------------|-------------------|-------------|
| Write | code-sentinel | doc-guardian, project-hygiene | PR review |
| Edit | code-sentinel | doc-guardian, project-hygiene | PR review |
| MultiEdit | code-sentinel | doc-guardian | PR review |
| Bash(git *) | git-flow | — | — |
| Operation | PreToolUse Hooks | Other Gates |
|-----------|------------------|-------------|
| Write | code-sentinel | PR review |
| Edit | code-sentinel | PR review |
| MultiEdit | code-sentinel | PR review |
| Bash(git *) | git-flow | — |
| MCP(netbox create/update) | cmdb-assistant | — |
### Step 3: Read Current Permissions
@@ -94,13 +93,7 @@ flowchart LR
direction TB
CS[code-sentinel<br/>Security Scan]
GF[git-flow<br/>Branch Check]
end
subgraph post[PostToolUse Hooks]
direction TB
DG[doc-guardian<br/>Drift Detection]
PH[project-hygiene<br/>Cleanup]
DP[data-platform<br/>Schema Diff]
CA[clarity-assist<br/>Prompt Quality]
end
subgraph perm[Permission Status]
@@ -111,26 +104,22 @@ flowchart LR
end
W -->|intercepted| CS
W -->|tracked| DG
E -->|intercepted| CS
E -->|tracked| DG
BG -->|checked| GF
CS -->|passed| AA
DG -->|logged| AA
GF -->|valid| AA
BO -->|no hook| PR
classDef preHook fill:#e3f2fd,stroke:#1976d2
classDef postHook fill:#e8f5e9,stroke:#388e3c
classDef sprint fill:#fff3e0,stroke:#f57c00
classDef quality fill:#fff3e0,stroke:#f57c00
classDef prReview fill:#f3e5f5,stroke:#7b1fa2
classDef allowed fill:#c8e6c9,stroke:#2e7d32
classDef prompted fill:#fff9c4,stroke:#f9a825
classDef denied fill:#ffcdd2,stroke:#c62828
class CS,GF preHook
class DG,PH,DP postHook
class CA quality
class AA allowed
class PR prompted
class DN denied
@@ -195,11 +184,10 @@ Review Layer Status
PreToolUse Hooks (intercept before operation):
✓ code-sentinel — Write, Edit, MultiEdit
✓ git-flow — Bash(git checkout *), Bash(git commit *)
✓ cmdb-assistant — MCP(netbox create/update)
PostToolUse Hooks (track after operation):
doc-guardian — Write, Edit, MultiEdit
✓ project-hygiene — Write, Edit
✗ data-platform — not detected
UserPromptSubmit Hooks (check prompt quality):
clarity-assist — vagueness detection
Other Review Gates:
✓ Sprint Approval (projman milestone workflow)
@@ -241,7 +229,6 @@ To view:
| Element | Color | Hex |
|---------|-------|-----|
| PreToolUse hooks | Blue | #e3f2fd |
| PostToolUse hooks | Green | #e8f5e9 |
| Sprint/Planning gates | Amber | #fff3e0 |
| PR Review | Purple | #f3e5f5 |
| Auto-allowed | Light green | #c8e6c9 |

View File

@@ -1,68 +0,0 @@
#!/bin/bash
# claude-config-maintainer: enforce mandatory behavior rules
# Checks if CLAUDE.md has the rules, adds them if missing
PREFIX="[claude-config-maintainer]"
# Find CLAUDE.md in current directory or parent
CLAUDE_MD=""
if [ -f "./CLAUDE.md" ]; then
CLAUDE_MD="./CLAUDE.md"
elif [ -f "../CLAUDE.md" ]; then
CLAUDE_MD="../CLAUDE.md"
fi
# If no CLAUDE.md found, exit silently
if [ -z "$CLAUDE_MD" ]; then
exit 0
fi
# Check if mandatory rules exist
if grep -q "MANDATORY BEHAVIOR RULES" "$CLAUDE_MD" 2>/dev/null; then
# Rules exist, all good
exit 0
fi
# Rules missing - add them
RULES='## ⛔ MANDATORY BEHAVIOR RULES - READ FIRST
**These rules are NON-NEGOTIABLE. Violating them wastes the user'\''s time and money.**
### 1. WHEN USER ASKS YOU TO CHECK SOMETHING - CHECK EVERYTHING
- Search ALL locations, not just where you think it is
- Check cache directories: `~/.claude/plugins/cache/`
- Check installed: `~/.claude/plugins/marketplaces/`
- Check source directories
- **NEVER say "no" or "that'\''s not the issue" without exhaustive verification**
### 2. WHEN USER SAYS SOMETHING IS WRONG - BELIEVE THEM
- The user knows their system better than you
- Investigate thoroughly before disagreeing
- **Your confidence is often wrong. User'\''s instincts are often right.**
### 3. NEVER SAY "DONE" WITHOUT VERIFICATION
- Run the actual command/script to verify
- Show the output to the user
- **"Done" means VERIFIED WORKING, not "I made changes"**
### 4. SHOW EXACTLY WHAT USER ASKS FOR
- If user asks for messages, show the MESSAGES
- If user asks for code, show the CODE
- **Do not interpret or summarize unless asked**
**FAILURE TO FOLLOW THESE RULES = WASTED USER TIME = UNACCEPTABLE**
---
'
# Create temp file with rules + existing content
{
head -1 "$CLAUDE_MD"
echo ""
echo "$RULES"
tail -n +2 "$CLAUDE_MD"
} > "${CLAUDE_MD}.tmp"
mv "${CLAUDE_MD}.tmp" "$CLAUDE_MD"
echo "$PREFIX Added mandatory behavior rules to CLAUDE.md"

View File

@@ -1,15 +0,0 @@
{
"hooks": {
"SessionStart": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/enforce-rules.sh"
}
]
}
]
}
}

View File

@@ -119,14 +119,14 @@ This is the key section. Map upstream review processes to directory scopes:
| Directory Scope | Active Review Layers | Auto-Allow Recommendation |
|----------------|---------------------|---------------------------|
| `plugins/*/commands/*.md` | Sprint approval, PR review, doc-guardian PostToolUse | `Write(plugins/*/commands/**)`3 layers cover this |
| `plugins/*/commands/*.md` | Sprint approval, PR review | `Write(plugins/*/commands/**)`2 layers cover this |
| `plugins/*/skills/*.md` | Sprint approval, PR review | `Write(plugins/*/skills/**)` — 2 layers |
| `plugins/*/agents/*.md` | Sprint approval, PR review, contract-validator | `Write(plugins/*/agents/**)`3 layers |
| `plugins/*/agents/*.md` | Sprint approval, PR review | `Write(plugins/*/agents/**)`2 layers |
| `mcp-servers/*/mcp_server/*.py` | Code-sentinel PreToolUse, sprint approval, PR review | `Write(mcp-servers/**)` + `Edit(mcp-servers/**)` — sentinel catches secrets |
| `docs/*.md` | Doc-guardian PostToolUse, PR review | `Write(docs/**)` + `Edit(docs/**)` |
| `docs/*.md` | PR review | `Write(docs/**)` + `Edit(docs/**)` — with caution flag |
| `.claude-plugin/*.json` | validate-marketplace.sh, PR review | `Write(.claude-plugin/**)` |
| `scripts/*.sh` | Code-sentinel, PR review | `Write(scripts/**)` — with caution flag |
| `CLAUDE.md`, `CHANGELOG.md`, `README.md` | Doc-guardian, PR review | `Write(CLAUDE.md)`, `Write(CHANGELOG.md)`, `Write(README.md)` |
| `CLAUDE.md`, `CHANGELOG.md`, `README.md` | PR review | `Write(CLAUDE.md)`, `Write(CHANGELOG.md)`, `Write(README.md)` |
### Critical Rule: Hook Verification
@@ -134,10 +134,11 @@ This is the key section. Map upstream review processes to directory scopes:
Read the relevant `plugins/*/hooks/hooks.json` file:
- If code-sentinel's hook is missing or disabled, do NOT recommend auto-allowing `mcp-servers/**` writes
- If doc-guardian's hook is missing, do NOT recommend auto-allowing `docs/**` without caution
- If git-flow's hook is missing, do NOT recommend auto-allowing `Bash(git *)` operations
- If cmdb-assistant's hook is missing, do NOT recommend auto-allowing MCP netbox create/update operations
- Count the number of verified review layers before making recommendations
**Minimum threshold:** Recommend auto-allow only for scopes covered by ≥2 verified review layers.
**Minimum threshold:** Only recommend auto-allow for scopes with ≥2 verified review layers.
---
@@ -333,10 +334,9 @@ To verify which review layers are active, read these files:
| File | Hook Type | Tool Matcher | Purpose |
|------|-----------|--------------|---------|
| `plugins/code-sentinel/hooks/hooks.json` | PreToolUse | Write\|Edit\|MultiEdit | Blocks hardcoded secrets |
| `plugins/doc-guardian/hooks/hooks.json` | PostToolUse | Write\|Edit\|MultiEdit | Tracks documentation drift |
| `plugins/project-hygiene/hooks/hooks.json` | PostToolUse | Write\|Edit | Cleanup tracking |
| `plugins/data-platform/hooks/hooks.json` | PostToolUse | Edit\|Write | Schema diff detection |
| `plugins/cmdb-assistant/hooks/hooks.json` | PreToolUse | (if exists) | Input validation |
| `plugins/git-flow/hooks/hooks.json` | PreToolUse | Bash | Branch naming + commit format |
| `plugins/cmdb-assistant/hooks/hooks.json` | PreToolUse | MCP create/update | NetBox input validation |
| `plugins/clarity-assist/hooks/hooks.json` | UserPromptSubmit | (all prompts) | Vagueness detection |
### Verification Process
@@ -370,8 +370,8 @@ Count verified review layers for each scope:
|-------|-------------|
| Sprint approval | Check if projman plugin is installed (milestone workflow) |
| PR review | Check if pr-review plugin is installed |
| code-sentinel PreToolUse | hooks.json exists with PreToolUse on Write/Edit |
| doc-guardian PostToolUse | hooks.json exists with PostToolUse on Write/Edit |
| contract-validator | Plugin installed + hooks present |
| code-sentinel PreToolUse | hooks.json exists with PreToolUse on Write/Edit/MultiEdit |
| git-flow PreToolUse | hooks.json exists with PreToolUse on Bash |
| cmdb-assistant PreToolUse | hooks.json exists with PreToolUse on MCP create/update |
**Recommendation threshold:** Only recommend auto-allow for scopes with ≥2 verified layers.