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/datatorag/gws-mcp/claude-mdgit clone --depth 1 https://github.com/datatorag/gws-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/datatorag/gws-mcp/claude-md)<a href="https://agentmods.dev/instructions/datatorag/gws-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/datatorag/gws-mcp/claude-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 | $0.00918 | $0.00918 |
| Opus 5 | $0.00459 | $0.00459 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
gws-mcp CLAUDE.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 5d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project
Google Workspace MCP extension for Claude. Wraps the gws CLI binary to expose 67 tools (Gmail, Calendar, Drive, Contacts, Sheets, Docs, Slides, Tasks, generic API access) via MCP.
Commands
pnpm run build— compile TypeScript (src/ → server/)pnpm run dev— watch modepnpm run build:extension— compile + pack intogoogle-workspace-mcp.mcpbpnpm run download-binaries— fetch gws binaries into bin/
Architecture
Two entry points sharing createMcpServer() from create-server.ts:
extension.ts— stdio transport for.mcpb(Claude Desktop). Auto-triggers browser OAuth login on first run.index.ts— HTTP transport on port 39147 for Claude Code / standalone use.
gws-client.ts wraps the gws CLI binary (Rust, in bin/). OAuth client ID and secret are read from GWS_OAUTH_CLIENT_ID / GWS_OAUTH_CLIENT_SECRET env vars and passed to the binary.
Key conventions
- ESM (
"type": "module"), all imports use.jsextensions - TypeScript strict mode, target ES2024, NodeNext module resolution
- Output dir is
server/(notdist/) - Use
pnpm, notnpm - Tests:
pnpm test(vitest — typechecks the test files, then runs them). Unit tests live beside the module and drive handlers through a fake{ api }client, so they need no network. They cannot catch a changed upstream response shape: a live smoke test against the real API is still the verification for anything touching a Google endpoint.
Tool annotations
Every tool declares annotations via a preset from src/tools/annotations.ts,
never hand-written booleans — the three shapes were copied out 55 times and
eight had drifted to wrong values:
READ(title)— cannot modify anything. Reads, searches, lists, gets.CREATE(title)— adds something new; cannot overwrite or destroy.MUTATE(title)— overwrites or removes existing state, or has an irreversible effect outside our system (sending mail, sharing a file).
MUTATE is the safe default when unsure: over-prompting costs a click,
under-prompting costs the user something they cannot get back. ToolDef
makes annotations and both hints required, so an unannotated tool is a
compile error rather than a silent one (under MCP defaults an absent
destructiveHint reads as TRUE and an absent readOnlyHint as FALSE).
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.
- 5d ago First seen · 76 lines · 918 tokens per session scan A 604854cea8bc
gws-mcp CLAUDE.md is an instructions file published in the GitHub repository datatorag/gws-mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 918 tokens to every session, about $0.0046 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
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.
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).