Grey Haven Plugin Audit Report
Description
**Generated:** 2026-01-08 **Claude Code Version Target:** v2.1.0 **Plugins Audited:** 16 **Overall Health Score:** 72/100 ---
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
Repository README
This is the README for greyhaven-ai/claude-code-config, shared by 2 entries
in this directory. It describes the repository, not this entry specifically.
Grey Haven Plugin Audit Report
**Generated:** 2026-01-08 **Claude Code Version Target:** v2.1.0 **Plugins Audited:** 16 **Overall Health Score:** 72/100
Executive Summary
| Metric | Count | Status |
|---|---|---|
| Total Plugins | 16 | ✅ |
| Total Agents | 48 | ✅ |
| Total Commands | 56 | ✅ |
| Total Skills | 43 | ✅ |
| Deprecations Found | 34 | ⚠️ |
| High Priority Issues | 10 | 🔴 |
| Medium Priority Issues | 44 | 🟡 |
| Low Priority Issues | 7 | 🟢 |
Critical Issues (High Priority)
1. Agents Missing `tools:` Field (10 agents)
These agents have no tool restrictions, allowing unrestricted access to all tools:
| Agent | Plugin | Risk |
|---|---|---|
ci-cd-analyzer.md |
cloudflare-deployment-observability | HIGH |
deployment-monitor.md |
cloudflare-deployment-observability | HIGH |
performance-tracker.md |
cloudflare-deployment-observability | HIGH |
documentation-alignment-verifier.md |
core | MEDIUM |
git-diff-documentation-agent.md |
core | MEDIUM |
multi-agent-synthesis-orchestrator.md |
research | MEDIUM |
tech-docs-maintainer.md |
research | MEDIUM |
tech-docs-orchestrator.md |
research | MEDIUM |
web-docs-researcher.md |
research | MEDIUM |
bug-issue-creator.md |
testing | MEDIUM |
**Impact:** Without `tools:` restrictions, these agents can access all tools including potentially dangerous ones like `Bash` without constraints.
**Fix:** Add explicit `tools:` frontmatter with YAML list format:
tools:
- Read
- Write
- Grep
- Glob
2. `core` Plugin Missing Agents Array in plugin.json
The `core` plugin has 9 agents but doesn't declare them in `plugin.json`:
code-quality-analyzer.mddocumentation-alignment-verifier.mdgit-diff-documentation-agent.mdperformance-optimizer.mdproject-scaffolder.mdprompt-engineer.mdtdd-orchestrator.mdtdd-python.mdtdd-typescript.md
**Fix:** Add agents array to `grey-haven-plugins/core/.claude-plugin/plugin.json`:
"agents": [
"./agents/code-quality-analyzer.md",
"./agents/documentation-alignment-verifier.md",
"./agents/git-diff-documentation-agent.md",
"./agents/performance-optimizer.md",
"./agents/project-scaffolder.md",
"./agents/prompt-engineer.md",
"./agents/tdd-orchestrator.md",
"./agents/tdd-python.md",
"./agents/tdd-typescript.md"
]
3. `deployment` and `linear` Plugins Missing Agents Array
While these plugins may not have agents directories, the `plugin.json` should either:
- Declare an empty
"agents": []array - Or add agents if they exist but aren't declared
Deprecated Patterns (Medium Priority)
1. Comma-Separated Tool Lists (34 agents)
**Status:** DEPRECATED - Use YAML lists instead
The following agents use comma-separated tool lists instead of YAML-style arrays:
| Plugin | Agent |
|---|---|
| agent-orchestration | context-manager.md |
| cc-trace | cc-trace.md |
| cor |
Related Skills
Fastapi Review
Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu
Security Defense in Depth
Implement multi-layered testing and security best practices.
Security SecLists Official Repository
[OWASP Testing Guide](https://owasp.org/www-project-web-security-testing-guide/)
Security Threat Hunting with Sigma Rules
Use Sigma detection rules to hunt for threats and analyze security events
Security Maintenance Walkthrough - 2026-03-29
- Re-triaged the full 2026-03-15 security finding set against current `main` and wrote a fresh current-head re
Security Google Workspace Model Armor
Filter user-generated content for safety
Security Related Agents
Django Reviewer
Expert Django code reviewer specializing in ORM correctness, DRF patterns, migration safety, security misconfi
Token Auditor
Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d
Gitnexus Security Boundary Reviewer
GitNexus security and trust-boundary reviewer. Use for auth, permissions, secrets, injection, unsafe parsing,