Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/jnpacker/gmail-mcp-server/gemini-mdgit clone --depth 1 https://github.com/jnpacker/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/instructions/jnpacker/gmail-mcp-server/gemini-md)<a href="https://agentmods.dev/instructions/jnpacker/gmail-mcp-server/gemini-md"><img src="https://agentmods.dev/badge/instructions/jnpacker/gmail-mcp-server/gemini-md.svg" alt="Measured on agentmods" 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 | $0.01299 | $0.01299 |
| Opus 5 | $0.00649 | $0.00649 |
| Sonnet 5 | $0.00260 | $0.00260 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
gmail-mcp-server GEMINI.md 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 3d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Repo Is
Two loosely coupled systems that share the Gmail API client:
- MCP Server (
gmail_mcp_server/) — a stdio MCP server exposing Gmail tools to AI assistants (Claude, Gemini). Runs headlessly via.mcp.json. - Web Dashboard (
app.py) — a Flask app that invokes triage by spawninggemini -p /triageas a subprocess, parses the structured output, and caches results for the browser UI.
The triage command itself lives in commands/triage.md (symlinked into .claude/commands/ and converted to .gemini/commands/ TOML). The command instructs the AI to call Gmail MCP tools directly.
Commands
# Auth setup (requires credentials.json from Google Cloud Console)
make auth
# Run tests
python -m pytest # all tests
python -m pytest tests/test_server.py # single file
python -m pytest -k "test_format" # single test pattern
# Start web dashboard (auto-restarts on crash)
make dashboard
# Run triage manually
make triage MODEL=haiku # default; also: sonnet, opus
make watch MODEL=haiku # run every 5 min
# Dashboard PIN management
make set-pin
# Re-link slash commands after editing commands/*.md
make link-commands
# Container
make podman-build
make podman-push
Architecture
MCP Server (gmail_mcp_server/)
server.py—GmailMCPServerwrapsmcp.server.Server. Maintains an in-memory position map (email_position_map) that maps 1-based integer positions (shown inlist_unread_emailsoutput) to Gmail message IDs. This map is rebuilt on everylist_unread_emailscall, so tools likedelete_emailsandarchive_emailsacceptpositions[]referencing the last fetch. Also holds an in-memory action log (capped at 100).gmail_client.py—GmailClientwrapsgoogle-api-python-client. Auth is lazy:_ensure_authenticated()is called before every API call. Token is read fromtoken.json; interactive OAuth only runs whenGMAIL_INTERACTIVE_AUTH=1.modify_labelsautomatically removes all otherTriage/*labels when a new one is added — this enforces the one-label-per-email invariant.auth.py— standalone auth helper invoked bymake auth.
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.
- 3d ago First seen · 95 lines · 1,299 tokens per session scan A 9cfb08231ad5
gmail-mcp-server GEMINI.md is an instructions file published in the GitHub repository jnpacker/gmail-mcp-server (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,299 tokens to every session, about $0.0065 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.