gmail-mcp-server: Skill for Claude Code

.claude/skills/pr-review-sop/SKILL.md

pr-review-sop is a skill for Claude Code from cgutiguti/gmail-mcp-server. It costs 65 tokens per session (1,638 once invoked), scanned A, original, MIT.

A standard procedure for reviewing pull requests and issues in a code repository. A pull request is a proposed set of code changes, and the procedure includes checking discussions, labels, branches, security, and continuous-integration results.

In plain words
What is it for?
Use it when reviewing or triaging pull requests and issues, merging approved work, and verifying that CI passes after pushes.
Why use it?
It reduces the chance of missing requested fixes, security concerns, unresolved comments, or broken automated checks. It also enforces a staging branch before changes reach the stable branch.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

This is cgutiguti/gmail-mcp-server's own configuration. It tells Claude Code how to work on gmail-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gmail-mcp-server configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/cgutiguti/gmail-mcp-server/main/.claude/skills/pr-review-sop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cgutiguti/gmail-mcp-server

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.

agentmods badge for pr-review-sop

README.md
[![agentmods](https://agentmods.dev/badge/skills/cgutiguti/gmail-mcp-server/pr-review-sop/github.svg)](https://agentmods.dev/skills/cgutiguti/gmail-mcp-server/pr-review-sop)
Your own site
<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.

agentmods 80×15 button for pr-review-sop

Your own site · 80×15
<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>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,638 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.01638
Opus 5 $0.00032 $0.00819
Sonnet 5 $0.00013 $0.00328
Haiku 4.5 $0.00006 $0.00164

Measured 10d ago against content hash ea9b19ebf00f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 10d 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-sop/SKILL.md · 107 lines

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).

  1. Before starting a new batch of PR reviews/changes: merge experimentalmain IF the experiment is confirmed successful. If no evidence, ask the user.
  2. PR merges and own changes go into experimental first. Never merge PRs directly into main.
  3. After a batch is complete on experimental: wait for user confirmation, then merge experimentalmain.
  4. After every push to any branch: run gh run list --branch {branch} --limit 1 and verify CI passes. If CI fails, fix immediately — do NOT leave broken CI for the user to discover. This applies to every git push in 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-auditor subagent.
  • 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.

Read the full file on GitHub · 107 lines

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.

  1. 10d ago First seen · 107 lines · 65 tokens per session scan A ea9b19ebf00f

Subscribe to this mod's changes

pr-review-sop is a skill published in the GitHub repository cgutiguti/gmail-mcp-server (0 stars, last pushed 9d ago), licensed MIT. It adds 65 tokens to every session and 1,638 once invoked, about $0.0003 per session on Opus 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.