Borrowing it
Nothing to install: this file belongs to ArtyMcLabin/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/ArtyMcLabin/Gmail-MCP-Server/main/.claude/skills/pr-review-sop/SKILL.mdgit clone --depth 1 https://github.com/ArtyMcLabin/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/artymclabin/gmail-mcp-server/pr-review-sop)<a href="https://agentmods.dev/skills/artymclabin/gmail-mcp-server/pr-review-sop"><img src="https://agentmods.dev/badge/skills/artymclabin/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/artymclabin/gmail-mcp-server/pr-review-sop"><img src="https://agentmods.dev/badge/skills/artymclabin/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 | $0.02739 |
| Opus 5 | $0.00032 | $0.01370 |
| Sonnet 5 | $0.00013 | $0.00548 |
| Haiku 4.5 | $0.00006 | $0.00274 |
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 11d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR & Issue Review SOP
Project Philosophy (Read First - Governs Every Review)
SSoT: README.md § Philosophy. This fork is lean and pragmatic. Local stdio MCP server, minimal dependencies, maintainer dogfoods it daily - "if I wouldn't run it or maintain it myself, it doesn't go in." The maximalist direction lives in the downstream fork klodr/gmail-mcp (unaffiliated); feature-hungry users get redirected there, politely, with the standard caveat that we don't track its security.
Every PR and issue assessment MUST include a philosophy verdict: MATCH / MISMATCH / NEUTRAL.
Heuristics:
- MATCH: bugfixes, correctness/reliability of the existing surface, docs accuracy, test coverage for existing behavior, zero-dependency improvements, credential-safety per the local threat model.
- MISMATCH (default decline + redirect to klodr fork): new feature surface the maintainer wouldn't use daily, new dependencies, infra/deployment expansion (Docker images, hosting), hardening classes the local threat model explicitly excludes (see Security Standards below), capabilities with an existing simple workaround (e.g. registering the server twice ≈ multi-account).
- NEUTRAL: repo hygiene, triage, support/environmental issues, distribution of the existing lean server.
MISMATCH handling: don't build it, don't merge it. Pitch the item to the maintainer FIRST (angry-king style) and close only after his explicit call - never auto-close a contributor's PR/issue on philosophy grounds alone (Arty directive 2026-07-10: outward-facing closures are his judgment, MISMATCH verdict or not). Once he says close: comment kindly, point to klodr/gmail-mcp, close.
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. - End of each dev round (batch merged to
experimental, awaiting soak): create a task in the user's Personal CRM (mcp__claude_ai_Personal_CRM__crm_create_task, load via ToolSearch) titled "Promote Gmail-MCP experimental→main if soak clean", due ~1 week out (or whatever fits the round's size). The user tracks promotions there, not in GitHub. (Arty directive 2026-07-11.)
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.
- 11d ago First seen · 137 lines · 65 tokens per session scan A 43a626f9fc71
pr-review-sop is a skill published in the GitHub repository ArtyMcLabin/Gmail-MCP-Server (236 stars, last pushed 29d ago), licensed MIT. It adds 65 tokens to every session and 2,739 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other skills, from other repositories
gmail-tool
Gmail integration tool for unread checks, reading bodies, and drafts via OAuth2 Gmail API access. Use when: reading inbox mail, fetching message bodies, writing drafts, or searching labeled mail.
gmail
Send, read, and manage Gmail messages and email attachments automatically.
mail-operations
Use this skill whenever the user wants to interact with email. This includes reading inbox, sending emails, replying, searching messages, managing labels and categories, downloading attachments, setting up auto-reply rules, or triggering agents to handle incoming emails. Supports Gmail, Outlook, and IMAP/SMTP (QQ…
c-email
Read, send, search, and label email via gog (Gmail CLI) or himalaya (IMAP). Supports inbox management, drafting replies, thread viewing, and label/folder operations across Gmail and standard IMAP accounts.
Search and read the user's mail through the your-mail MCP server, a read-only mirror of their IMAP accounts indexed by notmuch. Use it to find messages, read threads, summarise and triage mail, and pull details (booking references, invoices, what someone promised) into other work. It cannot send, delete, move or…
imap-smtp-email
Read, search, and manage email via IMAP protocol. Send email via SMTP. Supports Gmail, Outlook, 163.com, 126.com, QQ Mail, and any standard IMAP/SMTP server with multi-account support.