gws-mcp: Instructions file for Claude Code

CLAUDE.md

gws-mcp CLAUDE.md is an instructions file for Claude Code from shigechika/gws-mcp. It costs 728 tokens per session, scanned A, original, from a forked repository, Apache-2.0.

Repository-specific instructions for contributing to a fork of Google's Workspace command-line tool that also supports MCP servers, a standard way for agents to call tools. They describe the project layout, upstream-merge checks, known Rust fixes, and verification commands.

In plain words
What is it for?
Use them when modifying, merging, or verifying the shigechika/gws-mcp repository, including its Rust workspace and GitHub Actions.
Why use it?
They explain the fork's differences and the checks needed after syncing changes from the original project. This reduces the chance of breaking the fork or losing its MCP changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md.

This is shigechika/gws-mcp's own configuration. It tells Claude Code how to work on gws-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gws-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shigechika/gws-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shigechika/gws-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shigechika/gws-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for gws-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shigechika/gws-mcp/claude-md.svg)](https://agentmods.dev/instructions/shigechika/gws-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shigechika/gws-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shigechika/gws-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 728 This file is loaded in full into every session.
When invoked 728 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin fork From a forked repository.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00728 $0.00728
Opus 5 $0.00364 $0.00364
Sonnet 5 $0.00146 $0.00146
Haiku 4.5 $0.00073 $0.00073

Measured 8d ago against content hash 15eedbe403e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 8d 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.

CLAUDE.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When contributing to this repository, you must strictly follow all guidelines outlined in the AGENTS.md file.

Fork-specific Notes

This is a fork of googleworkspace/cli that maintains MCP server support. See FORK.md for details.

Upstream Merge Checklist

After merging upstream/main, fix MCP compilation errors:

  1. crates/google-workspace-cli/src/mcp_server.rs — match new arguments in executor::execute_method() calls
  2. crates/google-workspace-cli/src/mcp_server.rs — match new fields in Gmail helper structs
  3. crates/google-workspace-cli/src/helpers/gmail/mod.rs — ensure pub(crate) visibility is not reverted to pub(super)
  4. pub(crate) targets: Mailbox, to_mb_address_list, apply_optional_headers, finalize_message, resolve_mail_method, Attachment
  5. Run cargo clippy -- -D warnings && cargo test to verify
  6. If conflicts exceed ~20 files, consider rebasing: checkout upstream/main as new branch, re-apply MCP changes, reset main

Project Structure

  • Cargo workspace: crates/google-workspace-cli/ (binary) + crates/google-workspace/ (library)
  • MCP server (stdio transport): crates/google-workspace-cli/src/mcp_server.rs. The fork-only HTTP transport — Streamable HTTP plus an embedded OAuth 2.1 authorization/resource server (per-user Google token isolation) — lives in crates/google-workspace-cli/src/mcp_http_server.rs and is arguably the fork's largest security surface; keep it in scope when reviewing auth/MCP changes.
  • Local install: cargo install --path crates/google-workspace-cli

GitHub Actions

  • Fork workflows (this list grows over time): ci.yml, policy.yml, sync-upstream.yml, audit.yml, auto-tag.yml, release-fork.yml
  • gh workflow list may show upstream workflows — use gh api repos/<owner>/<repo>/actions/workflows to check fork workflows, but confirm the file actually exists on the default branch: that API keeps reporting a workflow as "active" while its file only survives on stale side branches (this is how the deleted generate-skills.yml kept getting re-added to docs)
  • gh run list may show upstream runs — filter with --branch=main for fork-specific results
  • audit.yml runs cargo audit daily (06:00 UTC cron) plus on Cargo.toml/Cargo.lock pushes/PRs. When it fails on a new RUSTSEC advisory, cargo update -p <crate> (or a transitive dep swap, e.g. bumping serial_test dropped its vulnerable scc dependency) is usually enough — no source changes needed, just a Cargo.lock-only PR with a changeset.
  • ci.yml has a Verify Skills job that reruns cargo run -- generate-skills --output-dir skills and prints a warning if skills/ is out of date, plus a Lint Skills job that validates skills/ with agentskills. If you change MCP tool schemas or generate_skills.rs, regenerate skills/ locally and commit the result to avoid drift warnings (the generate-skills.yml hourly auto-sync workflow was deleted, even though the drift warning still mentions it).

Read the full file on GitHub · 30 lines

Changes

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.

  1. 8d ago First seen · 30 lines · 728 tokens per session scan A 15eedbe403e7

Subscribe to this mod's changes

gws-mcp CLAUDE.md is an instructions file published in the GitHub repository shigechika/gws-mcp (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 728 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.

mcp
Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens