agentmods.dev

gws-mcp: Instructions file for Claude Code

CLAUDE.md

gws-mcp CLAUDE.md is an instructions file for Claude Code from purplespacecat/gws-mcp. It costs 461 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for gws-mcp, a local connector for Google Tasks, Calendar, and Drive. The instructions define how the connector must handle reads, changes, approvals, permissions, and secrets.

In plain words
What is it for?
Developing or changing gws-mcp while following its tool naming, approval, scope, keyring, and trash-instead-of-delete rules.
Why use it?
It prevents unsafe or inconsistent changes, such as running a write without human approval or permanently deleting a Drive file.

Instructions file for Claude Code

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

This is purplespacecat/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 →

not rated 0repo today A scan 461 tokens original MIT
View source ↗ purplespacecat/gws-mcp
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/purplespacecat/gws-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/purplespacecat/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/purplespacecat/gws-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/purplespacecat/gws-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/purplespacecat/gws-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/purplespacecat/gws-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gws-mcp CLAUDE.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 461 This file is loaded in full into every session.
When invoked 461 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 original No closer match found in the catalogue.
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 $0.00461 $0.00461
Opus 5.5 $0.00184 $0.00184
Sonnet 5.5 $0.00092 $0.00092
Haiku 4.5 $0.00046 $0.00046

Measured 2mo ago against content hash c41a0c3172f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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 · 40 lines

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

  1. 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.
  2. Tool naming is the contract: reads are list_*/get_*/search_*/read_* (+ readOnlyHint); writes are create_*/update_*/complete_*/move_*/ respond_*/trash_*/delete_* (+ destructiveHint where irreversible). Drive delete is trash, never hard delete. The contract is enforced mechanically by test_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.
  3. Scopes are a ceiling (tasks, calendar.events, drive — in config.py): adding one needs a discussion issue, not a commit.
  4. 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 — keep test_state_never_leaks_secret_material honest).
  5. 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.

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. 2mo ago First seen · 40 lines · 461 tokens per session scan A c41a0c3172f8

Subscribe to this mod's changes

gws-mcp CLAUDE.md is an instructions file published in the GitHub repository purplespacecat/gws-mcp (0 stars, last pushed today), licensed MIT. It adds 461 tokens to every session, about $0.0018 per session on Opus 5.5. 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.

Productivity
Related

gws-mcp CLAUDE.md compared with instructions from other repositories

gws-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gws-mcp CLAUDE.mdpurplespacecat/gws-mcpInstructions file0todayMITA461Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode