Borrowing it
Nothing to install: this file belongs to purplespacecat/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.
curl -O https://raw.githubusercontent.com/purplespacecat/gws-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/purplespacecat/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/purplespacecat/gws-mcp/claude-md)<a href="https://agentmods.dev/instructions/purplespacecat/gws-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/purplespacecat/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 5.1 | $0.00461 | $0.00461 |
| Opus 5 | $0.00230 | $0.00230 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
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 6d 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.
What it actually says
CLAUDE.md — gws-mcp
Scoped MCP server (local stdio) for Google Tasks/Calendar/Drive. The full
design + phased plan live in the owner's private vault
(~/Documents/obsidian/docs/meta/gws-mcp-design.md) — read it before
structural changes.
Non-negotiable invariants
- Every mutating tool requires explicit human approval before executing — MCP elicitation primary, two-step confirm-token fallback for clients without it. Never weaken either path, never let a write execute on the first call in fallback mode.
- Tool naming is the contract: reads are
list_*/get_*/search_*/read_*(+readOnlyHint); writes arecreate_*/update_*/complete_*/move_*/ respond_*/trash_*/delete_*(+destructiveHintwhere irreversible). Drive delete is trash, never hard delete. The contract is enforced mechanically bytest_server.py::test_naming_convention_matches_annotations— extending the prefix set means updating it here, in CONTRIBUTING.md, and in that test, in the same PR. - Scopes are a ceiling (
tasks,calendar.events,drive— inconfig.py): adding one needs a discussion issue, not a commit. - No secret material on disk or in output: tokens live in the OS keyring;
auth_state()and every error message must stay leak-free (tests enforce this — keeptest_state_never_leaks_secret_materialhonest). - stdout is the MCP protocol channel — server-side code never prints; diagnostics go to stderr.
Dev
uv sync # env + lockfile
uv run pytest # tests mock the keyring; must pass headless
uv run ruff check src tests
uv run gws-mcp auth # interactive OAuth (browser) — CLI only, never in-session
uv run gws-mcp # serve on stdio
Main is ruleset-protected: all changes via PR. Keep PRs single-purpose.
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.
- 6d ago First seen · 40 lines · 461 tokens per session scan A c41a0c3172f8
gws-mcp CLAUDE.md is an instructions file published in the GitHub repository purplespacecat/gws-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 461 tokens to every session, about $0.0023 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).
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).
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.