A read-only process for independently reviewing one open GitHub pull request, which is a proposed code change awaiting review.

Use it to inspect a specified pull request, report concrete code problems, and mark the review status when the one-time review is complete.

It avoids repeated or duplicate reviews and keeps the reviewer from changing code or the pull request itself.

How Ailian0206/mcp-guardian configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Ailian0206/mcp-guardian. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Ailian0206/mcp-guardian/main/.claude/skills/pr-review/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Ailian0206/mcp-guardian

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ailian0206/mcp-guardian/pr-review/github.svg)](https://agentmods.dev/skills/ailian0206/mcp-guardian/pr-review)

Your own site

<a href="https://agentmods.dev/skills/ailian0206/mcp-guardian/pr-review"><img src="https://agentmods.dev/badge/skills/ailian0206/mcp-guardian/pr-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ailian0206/mcp-guardian/pr-review"><img src="https://agentmods.dev/badge/skills/ailian0206/mcp-guardian/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 901 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00046	$0.00901
Opus 5.5	$0.00018	$0.00360
Sonnet 5.5	$0.00009	$0.00180
Haiku 4.5	$0.00005	$0.00090

Measured 1mo ago against content hash abf3c6617c82, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-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.

.claude/skills/pr-review/SKILL.md · 82 lines

What it actually says

PR 独立只读审核（MCP Guardian）

替代 Cursor Bugbot。只发现和报告问题；修复由开发 agent 完成。

成本红线（最高优先级）

每个 PR 只审一次。评论里已有任意 CLAUDE_REVIEWED_SHA，或已有 claude-reviewed / claude-changes-requested → 立即退出，不发新评论、不改标签、不读 diff。
禁止因 head 前进、修复 push、pr-gate 重跑而复审。
禁止并行启动第二个 /pr-review（同一 PR）。
禁止扫描「所有缺 marker 的 PR」并批量审核；一次调用只处理用户指定的那一个开放 PR（普通模式若有多个开放 PR，只审编号最小的一个，且若它已审过则退出）。
优先 gh pr diff；高风险文件按需用 Contents API，禁止无目的整仓拉取。

调用模式

/pr-review
/pr-review --trusted-base <PR编号>

普通：当前工作区；未改审核协议 skill/规则时用这个。
可信基线：仅当 diff 命中 .claude/skills/pr-review/** 或 .cursor/rules/pr-review-gate.mdc 时使用。

代码只读硬边界

允许：gh pr list/view/diff、gh api、Read、Grep、只读验证。

禁止：改 tracked 文件、commit/push、开/关/合 PR、checkout 目标 head、在 trusted-base 执行目标分支代码、直接修 finding。

审核状态协议

Summary 结尾：

<!-- CLAUDE_REVIEWED_SHA: <head-sha> -->

claude-reviewed：本次（也是本 PR 唯一一次）审核完成。
claude-changes-requested：存在未解决 CRITICAL/HIGH。

幂等：本 PR 任意历史 marker / 上述标签已存在 → 跳过（不要求 marker 等于当前 head）。

只有本审核器可维护这两个标签。

审核协议路径（才强制 trusted-base）

.claude/skills/pr-review/**
.cursor/rules/pr-review-gate.mdc

普通模式若命中上述路径：零 GitHub 写入退出，提示开发 agent 用 trusted-base。
注意：改 AGENT.md / playbook 文案不再强制 trusted-base（避免无意义烧额度）。

普通模式

gh pr list --state open ...；取编号最小的一个开放 PR。
若已审过（marker 或标签）→ 退出。
命中协议路径 → 退出并要求 trusted-base。
否则进入共同审核过程（一次）。

可信基线模式

只审参数指定的一个 PR。校验 OPEN、baseRefOid、detached HEAD=baseRefOid。
已审过 → 立即退出。
读目标：只用 gh pr diff + 必要的 Contents API。

共同审核过程

读完整 gh pr diff。
策略/Gateway/审批等高风险点按需读全文。
等级：CRITICAL/HIGH 阻塞；MEDIUM/LOW 记录。
必查：密钥、路径穿越、fail-open、审批绕过、审计、ownership、吞错、无界查询、缺测。
inline + 一条 summary + marker；设标签；立即退出，不轮询、不复审。

项目约束

Draft 也审（仍只一次）。
忽略无关 .worktrees/。

Changes

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 · 82 lines · 46 tokens per session scan A abf3c6617c82

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository Ailian0206/mcp-guardian (1 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 901 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.

Code review

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

openclaw/clawhub · 17 tokens

omh-code-review

This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 48 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

explore-unknowns

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…

dzhng/skills · 162 tokens

asplos-writing-style

Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…

brycewang-stanford/Awesome-Journal-Skills · 65 tokens

mcp-guardian: Skill for Claude Code