Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add louisbrulenaudet/monorepo-template --skill review-claude-codegit clone --depth 1 https://github.com/louisbrulenaudet/monorepo-templateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/louisbrulenaudet/monorepo-template/review-claude-code)<a href="https://agentmods.dev/skills/louisbrulenaudet/monorepo-template/review-claude-code"><img src="https://agentmods.dev/badge/skills/louisbrulenaudet/monorepo-template/review-claude-code/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/louisbrulenaudet/monorepo-template/review-claude-code"><img src="https://agentmods.dev/badge/skills/louisbrulenaudet/monorepo-template/review-claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.01070 |
| Opus 5 | $0.00034 | $0.00535 |
| Sonnet 5 | $0.00014 | $0.00214 |
| Haiku 4.5 | $0.00007 | $0.00107 |
Grade B, and why
review-claude-code scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- [.claude/settings.json](../../../.claude/settings.json) - permissions, hooks wiring, model/env How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Claude Code
Review the Claude Code setup for alignment with current official best practices, optimal developer experience (DX), and AI collaboration quality on this large pnpm/Turborepo monorepo. Your reply must be a plan of suggested changes: concise, actionable, structured - not only prose.
Invocation
Text after the slash command is additional scope/focus (e.g. "permissions only", "hooks") - narrow the review accordingly.
Ground truth (mandatory)
Your pre-trained knowledge of Claude Code may be outdated. Do not draft suggestions from memory alone.
- Resolve "Claude Code" via the Context7 MCP (
resolve-library-id→query-docs) for settings keys, permission rule syntax, hooks events, subagent frontmatter, and worktree behavior. - For anything Context7 lacks, use Firecrawl search/scrape restricted to the official docs domain(s) (
code.claude.com,docs.anthropic.com) - settings reference, permissions, IAM, hooks, sandboxing, worktrees, output styles, best-practices guidance for large codebases. - Check version currency: compare installed CLI (
claude --version) against the latest stable release notes (official changelog). Flag deprecated settings keys or hook events still present in config. - Cite the retrieved source next to every finding; label anything you could not verify as Unverified.
Scope artifacts
- .claude/settings.json - permissions, hooks wiring, model/env
- .claude/rules/ - path-scoped rules,
core/guardrailsalways-on surface - .claude/agents/ -
verifier,bundle-analyzer,docs-researcher(toolsleast privilege) - .claude/skills/ - symlinks into
.agents/skills/; broken or stale links - CLAUDE.md + nested per-app/package guides - duplication vs pointer discipline
.claude/worktrees/,.claude/status-line.sh,.mcp.jsonserver list- Sync parity with the Cursor tree (see
/review-cursorfor that side's depth)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 65 lines · 68 tokens per session scan B e37377a93412
review-claude-code is a skill published in the GitHub repository louisbrulenaudet/monorepo-template (19 stars, last pushed 11d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,070 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
a2wave-memory
Progressively recall and maintain a2wave cross-session memory through a compact startup catalog, bounded topics, and searchable history.
memorize
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering.
cloudflare-router
Use when manage Cloudflare DNS, CDN, and security rules via API. Use when configuring domains, SSL, WAF, or edge caching.
memoryguard
Local-first MCP memory backend and governance console for coding agents. Auto-organize, quarantine, supersede, and rollback shared memories across multiple agents.
mcp-memory-query
Query the mcp-memory-service to retrieve stored facts, decisions, notes, and session learnings. Use this skill whenever the user asks what you remember, wants to recall past decisions or conventions, asks "do you know anything about X", references "last time we discussed", says "check your memory", "look in memory"…
mcp-memory-multiuser
Query and store memory when ONE agent account is shared by several people (a company team or a family) and each person has a PRIVATE memory store plus a SHARED team/family store. Use whenever the user asks what you remember, wants to recall past decisions or conventions, says "check your memory", "search memory for"…