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/klodr/gmail-mcp/agents-mdgit clone --depth 1 https://github.com/klodr/gmail-mcpWrote 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/klodr/gmail-mcp/agents-md)<a href="https://agentmods.dev/instructions/klodr/gmail-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/klodr/gmail-mcp/agents-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 | $0.02688 | $0.02688 |
| Opus 5 | $0.01344 | $0.01344 |
| Sonnet 5 | $0.00538 | $0.00538 |
| Haiku 4.5 | $0.00269 | $0.00269 |
Grade A, and why
gmail-mcp AGENTS.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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is gmail-mcp — a Model Context Protocol server that exposes the Gmail v1 API to AI assistants behind scope-gated tools (~33 tools across messages, threads, labels, filters, drafts, downloads, batch ops). It is a hardened + enhanced fork of GongRzhe/Gmail-MCP-Server (archived) via ArtyMcLabin/Gmail-MCP-Server, with 130+ commits of divergence — prompt-injection guards, OAuth scope-gating, batch retry, supply-chain hygiene, and CI gating.
This file is the canonical source of truth for any AI agent that edits the code in this repository. Read it before making changes. It encodes the conventions the maintainers actually enforce — not aspirations.
If you are an installation agent (i.e. helping a user install the MCP server in their client config rather than edit the server code), stop reading this file and read
llms-install.mdinstead. That file is for the install audience; this one is for code-editing agents.
Audience boundary
| Audience | Source of truth |
|---|---|
| Edits this repo's code | AGENTS.md (you are here) |
| Installs this MCP into a client config | llms-install.md |
| Threat model / security argument | docs/ASSURANCE_CASE.md |
| Disaster recovery / continuity | docs/CONTINUITY.md |
| Forward-looking work | docs/ROADMAP.md |
| Comparison vs upstream forks | docs/COMPETITORS.md |
| End-user features and install commands | README.md |
| Vulnerability reporting | .github/SECURITY.md |
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 · 236 lines · 2,688 tokens per session scan A e938b7e4eb7e
gmail-mcp AGENTS.md is an instructions file published in the GitHub repository klodr/gmail-mcp (11 stars, last pushed 10d ago), licensed MIT. It adds 2,688 tokens to every session, about $0.0134 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other instructions, from other repositories
google-mcp CLAUDE.md
Instructions for quinnjr/google-mcp, covering claude.md, commands, architecture, entry & server and auth.
gmail-mcp-server AGENTS.md
AGENTS.md instructions for neutral-Stage/gmail-mcp-server, covering agents.md, project overview, build/lint/test commands, install dependencies and build typescript to dist/.
mcp-server-gmail CLAUDE.md
Claude Code instructions for franciscpd/mcp-server-gmail, covering claude.md, .planning/ — single source of truth, workflow — follow this order exactly, phase 1 — discuss and phase 2 — brainstorm.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).