Borrowing it
Nothing to install: this file belongs to paulbreuler/limps. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/paulbreuler/limps/main/.claude/skills/mcp-code-review/SKILL.mdgit clone --depth 1 https://github.com/paulbreuler/limpsWrote 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/paulbreuler/limps/mcp-code-review)<a href="https://agentmods.dev/skills/paulbreuler/limps/mcp-code-review"><img src="https://agentmods.dev/badge/skills/paulbreuler/limps/mcp-code-review/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/paulbreuler/limps/mcp-code-review"><img src="https://agentmods.dev/badge/skills/paulbreuler/limps/mcp-code-review.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 | $0.00040 | $0.00974 |
| Opus 5.5 | $0.00016 | $0.00390 |
| Sonnet 5.5 | $0.00008 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
mcp-code-review scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP + LLM Code Review (limps)
Purpose
Perform a security-focused, test-minded code review with emphasis on MCP servers, LLM safety, and performance risks in this repository.
Scope
Use $ARGUMENTS as the scope (paths, diff range, PR number, or component name). If no scope is provided, review the current git diff.
Workflow
- Establish context
- Read
CLAUDE.mdand relevant package docs. - Identify the target package (
packages/limpsorpackages/limps-headless).
- Read
- Threat intel + dependency hygiene
- Search authoritative sources for new MCP/LLM or supply-chain issues:
- OWASP LLM Top 10, OWASP API Top 10, npm advisories, GitHub Security Advisories.
- Audit npm dependencies (use repo scripts when available):
npm audit --workspaces --include=prodnpm audit --workspaces --omit=dev(if prod-only is needed)
- Check for outdated or abandoned packages:
npm outdated --workspaces
- Inspect dependency tree for suspicious packages or name lookalikes:
npm ls --all --workspaces
- Verify lockfile integrity expectations:
- Prefer
npm cifor clean installs (verifiespackage-lock.jsonintegrity).
- Prefer
- Search authoritative sources for new MCP/LLM or supply-chain issues:
- Enumerate change surface
- List changed files and inspect diffs before diving into code.
- Security-first review
- Validate input handling, path safety, and external command usage.
- Check for secret exposure (logs, errors, telemetry).
- MCP/LLM safety review
- Review tool schemas, argument validation, and permission boundaries.
- Identify prompt injection vectors and untrusted content handling.
- Correctness and reliability
- Look for logic errors, race conditions, and edge cases.
- Performance and cost
- Identify expensive operations, redundant work, or unbounded processing.
- Tests
- Confirm coverage for new behavior and regression risk areas.
Repo-Specific Risk Areas
Focus extra scrutiny on:
packages/limps/src/server.ts,src/tools/*,src/resources/*(MCP tool/resource behavior)packages/limps/src/rlm/*andprocess_doc(s)tools (untrusted code execution)packages/limps/src/indexer.tsandsrc/watcher.ts(filesystem and database safety)packages/limps-headless/src/tools/*(external fetchers, parsing, extraction)
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.
- 1mo ago First seen · 92 lines · 40 tokens per session scan A 40a37c70adb6
mcp-code-review is a skill published in the GitHub repository paulbreuler/limps (10 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 974 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hypotheses
Turns a research direction into testable hypotheses with predictions, competing explanations and the experiments that discriminate between them, including the design (controls, randomization, blocking), sample size or seed count, the pre-specified analysis, and the result that would falsify each hypothesis. Use when a…
crit-cli
Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…
crit
Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
crossreview
Run when the user invokes /crossreview (or /crossreview:setup to choose the reviewers) or asks for a cross-review, a quorum review or a second opinion from other agents or models: fan a code review (uncommitted work, a branch, a commit range, files, a plan or a document) out to several console code agents (Claude…
review-harness
Use when reviewing implementation work that ran through a /tmp Pi task harness. Checks contract drift, unsafe shortcuts, validation evidence, and status honesty.