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/whichguy/gas_mcp/claude-mdgit clone --depth 1 https://github.com/whichguy/gas_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/whichguy/gas_mcp/claude-md)<a href="https://agentmods.dev/instructions/whichguy/gas_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/whichguy/gas_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 | $0.03387 | $0.03387 |
| Opus 5 | $0.01693 | $0.01693 |
| Sonnet 5 | $0.00677 | $0.00677 |
| Haiku 4.5 | $0.00339 | $0.00339 |
Grade A, and why
gas_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 3d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build & Run Commands
Core Development
npm install # Install dependencies
npm run build # Production build (TypeScript → JavaScript)
npm run build:dev # Development build with source maps
npm run dev # Watch mode with auto-rebuild
npm start # Build and start MCP server
npm run clean # Clean dist/ directory
Testing
| Category | Command | Purpose |
|---|---|---|
| Core | npm test |
System tests (30s timeout) |
npm run test:unit |
Unit tests (mocked) | |
npm run test:integration |
Real GAS API (auth required, 5min) | |
npm run test:system |
MCP protocol tests | |
npm run test:all |
Unit + system combined | |
| Quality | npm run test:security |
Security & validation |
npm run test:performance |
Performance benchmarks (60s) | |
npm run test:verification |
API schema compliance | |
| Verify | npm run test:git/auth/files/project/execution/server |
Domain-specific verification |
| Debug | DEBUG=mcp:* npm test |
Enable debug logging |
npx mocha test/path/file.test.ts --timeout 30000 |
Single test file |
Code Quality
npm run lint # ESLint with auto-fix
npm run bundle:analyze # Analyze bundle size
npm run test:production # Production readiness report
npm run test:all-verify # Run all verification tests
Development Workflow
Critical: After making changes to MCP server code or CommonJS modules:
- Build:
npm run build - Restart Claude Code - Required to pick up changes
- Test the changes
Test Project: Use scriptId 1Y72rigcMUAwRd7bwl3CR57O6ENo5sKTn0xAl2C4HoZys75N5utGfkCUG for testing
Architecture Overview
MCP server: AI ↔ GAS → 52 tools for create/manage/execute GAS projects
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.
- 3d ago First seen · 248 lines · 3,387 tokens per session scan A ca51932a50bf
gas_mcp CLAUDE.md is an instructions file published in the GitHub repository whichguy/gas_mcp (5 stars, last pushed 2mo ago), licensed MIT. It adds 3,387 tokens to every session, about $0.0169 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 tree-widgets.instructions.md
Use when asked to consume workbench tree widgets in VS Code.
vscode accessibility.instructions.md
Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
ui-components AGENTS.md
AGENTS.md instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).
windmill AGENTS.md
AGENTS.md instructions for windmill-labs/windmill, covering windmill, workflow, documentation, dev environment and per-worktree ports and database.