Borrowing it
Nothing to install: this file belongs to cgutiguti/gmail-mcp-server. 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/cgutiguti/gmail-mcp-server/main/.claude/skills/pr-review-sop/SKILL.mdgit clone --depth 1 https://github.com/cgutiguti/gmail-mcp-serverWrote 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/cgutiguti/gmail-mcp-server/pr-review-sop)<a href="https://agentmods.dev/skills/cgutiguti/gmail-mcp-server/pr-review-sop"><img src="https://agentmods.dev/badge/skills/cgutiguti/gmail-mcp-server/pr-review-sop/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/cgutiguti/gmail-mcp-server/pr-review-sop"><img src="https://agentmods.dev/badge/skills/cgutiguti/gmail-mcp-server/pr-review-sop.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 | $0.00065 | $0.01638 |
| Opus 5.5 | $0.00026 | $0.00655 |
| Sonnet 5.5 | $0.00013 | $0.00328 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
pr-review-sop 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR & Issue Review SOP
Branch Workflow
Two-branch model: main (stable) and experimental (staging).
- Before starting a new batch of PR reviews/changes: merge
experimental→mainIF the experiment is confirmed successful. If no evidence, ask the user. - PR merges and own changes go into
experimentalfirst. Never merge PRs directly intomain. - After a batch is complete on
experimental: wait for user confirmation, then mergeexperimental→main. - After every push to any branch: run
gh run list --branch {branch} --limit 1and verify CI passes. If CI fails, fix immediately — do NOT leave broken CI for the user to discover. This applies to everygit pushin the session, not just merges.
PR Review Checklist (All Steps Mandatory)
Step 1: Read All Comments and Reviews
- Fetch PR comments:
gh api repos/{owner}/{repo}/pulls/{N}/comments - Fetch review comments:
gh api repos/{owner}/{repo}/pulls/{N}/reviews - Fetch issue-level comments: included in
gh pr view --json comments - Summarize unresolved discussions or requests from repo owner.
Step 2: Check Labels
- Check for labels: "help wanted", "needs help", "good first issue", etc.
- If "help wanted" / "needs help": assess if anyone volunteered, if PR is stale, if requested help was provided.
Step 3: Security Audit (Conditional)
- Skip security audit for PRs with "help wanted" label that are still waiting for community testing/volunteers. These PRs are parked — auditing them wastes resources. Report a one-liner instead: "PR #N: still waiting for community help, no action needed."
- For all other PRs: run comprehensive security audit using
security-auditorsubagent. - Explicitly report verdict: "Security audit: PASS" or "Security audit: FAIL — [findings]"
- Never present a PR review to user without a completed security audit (unless skipped per above).
- For FAIL verdicts: list all findings with severity (CRITICAL/HIGH/MEDIUM/LOW/INFO).
- Local MCP threat model: This is a local stdio MCP server (user self-hosts on own PC, not remote/hosted). The LLM client already has full filesystem/shell access. Path traversal, filename injection, and local XSS are NOT security issues in this context — the "attacker" (LLM) already has more powerful tools (Bash, Write). Only flag issues that represent actual risk in the local threat model (e.g., credential leaks to third parties, network-exposed endpoints, dependency supply chain). Do NOT flag local filesystem operations as security vulnerabilities.
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 · 107 lines · 65 tokens per session scan A ea9b19ebf00f
pr-review-sop is a skill published in the GitHub repository cgutiguti/gmail-mcp-server (0 stars, last pushed 27d ago), licensed MIT. It adds 65 tokens to every session and 1,638 once invoked, about $0.0003 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
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…
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…
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…