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/nabheet/google-services-mcp/agents-mdgit clone --depth 1 https://github.com/nabheet/google-services-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/nabheet/google-services-mcp/agents-md)<a href="https://agentmods.dev/instructions/nabheet/google-services-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nabheet/google-services-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 | $0.01393 | $0.01393 |
| Opus 5 | $0.00696 | $0.00696 |
| Sonnet 5 | $0.00279 | $0.00279 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
google-services-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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guide for AI agents working in this repository.
Project
TypeScript MCP server connecting to Google consumer services (Gmail, Calendar, Meet, Drive, Contacts, Tasks) with multi-account OAuth. Package name google-services-mcp, executable google-services-mcp. ESM ("type": "module"), Node16 module resolution, target ES2022.
Architecture
src/
main.ts # bin entry: stdio serve OR cli dispatch
server.ts # createServer(): McpServer + registerTools
cli.ts # dispatchCommand() pure command dispatch (testable)
auth/
config.ts # env/file config resolution
store.ts # token/config persistence in data dir
oauth.ts # OAuth loopback flow, browser launch, CSRF state
manager.ts # AuthManager facade: accounts, clients, status
services/
gmail.ts # send/list/get/modify/reply
calendar.ts # events CRUD + Meet links
drive.ts # files list/get/upload/update/delete/share
contacts-tasks.ts # contacts + tasks
sheets.ts # spreadsheets: get/read/write/append/create/batch
docs.ts # documents: get/read/create/insert/replace/batch
slides.ts # presentations: get/create/replace/add/delete/batch
youtube.ts # search/videos/playlists/playlistItems/subscriptions
forms.ts # forms: get/responses/create/add-question/batch
tools/
index.ts # registerTools(server): 60 tools, google_ prefix
util/
result.ts # ok/text/err/noAccountsHint
test/ # vitest suites, mirrored layout
Data flow: MCP tool → withClient(account, fn) resolves a client via authManager.getClient() → service module calls googleapis → ok/err result → tool returns { content: [{ type: "text", text: JSON.stringify(result) }] }.
Conventions
- TDD: write the test first, run it (see it fail), implement, run again until green. Keep suites fast.
- Import style: always
.jsextensions in relative imports (Node16). The vitest resolution maps.js→.ts. - Import depth: top-level
test/*.test.tsuses../src/...; nestedtest/auth/*.test.tsuses../../src/.... Wrong depth yields a confusing "Cannot find module". - Tools: register with
registerTool(name, { title, description, inputSchema }, cb)from@modelcontextprotocol/sdk/server/mcp.js. Zod 3.25 for schemas.server.tool()is deprecated. - Tool naming:
google_<domain>_<action>, snake_case — avoids collision with client-native tools. - Errors: return
{ isError: true, content: [{ type: "text", text: "Error: <message>" }] }viaerr(). - Vitest: import
{ describe, expect, it, vi, beforeEach }explicitly. Mockgoogleapisat module level withvi.mockfactory andvi.hoisted()mocks. - Unhandled rejections in tests: attach the
expect(promise).rejects...assertion BEFORE the triggeringawait fetch(...)call, thenawaitthe assertion.
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.
- 4d ago First seen · 94 lines · 1,393 tokens per session scan A 3fbe93fae2ed
google-services-mcp AGENTS.md is an instructions file published in the GitHub repository nabheet/google-services-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 1,393 tokens to every session, about $0.0070 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.