github-mcp-gateway: Instructions file for Claude Code

CLAUDE.md

github-mcp-gateway CLAUDE.md is an instructions file for Claude Code from mazze93/github-mcp-gateway. It costs 3,037 tokens per session, scanned A, original, Apache-2.0.

A project-specific instruction guide for Claude Code covering a remote MCP server that gives approved AI clients authenticated access to GitHub.

In plain words
What is it for?
Working on the Cloudflare Workers gateway, running its TypeScript checks and tests, and understanding GitHub access and permission fallbacks.
Why use it?
It records deployment details, permissions, commands, tests, and known limits so code changes and releases follow the actual setup.

Instructions file for Claude Code

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

This is mazze93/github-mcp-gateway's own configuration. It tells Claude Code how to work on github-mcp-gateway 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 github-mcp-gateway configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mazze93/github-mcp-gateway. 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/mazze93/github-mcp-gateway/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mazze93/github-mcp-gateway

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 github-mcp-gateway CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mazze93/github-mcp-gateway/claude-md/github.svg)](https://agentmods.dev/instructions/mazze93/github-mcp-gateway/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mazze93/github-mcp-gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/mazze93/github-mcp-gateway/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 github-mcp-gateway CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mazze93/github-mcp-gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/mazze93/github-mcp-gateway/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,037 This file is loaded in full into every session.
When invoked 3,037 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 $0.03037 $0.03037
Opus 5.5 $0.01215 $0.01215
Sonnet 5.5 $0.00607 $0.00607
Haiku 4.5 $0.00304 $0.00304

Measured 2d ago against content hash 8562f3573496, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-mcp-gateway 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 2d 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 · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

github-mcp-gateway

Remote MCP server on Cloudflare Workers giving MCP clients (Claude Code, Claude.ai/Cowork, and any spec-compliant client) authenticated GitHub access via a GitHub App user-to-server OAuth flow.

Deployment facts (live)

  • Worker: github-mcp-gateway — https://github-mcp-gateway.mazzewhiteley93.workers.dev
  • MCP endpoint: /mcp (streamable HTTP) and /sse (legacy SSE)
  • KV namespace: OAUTH_KV = 0773ec3dd785418c984559f47d1623e9
  • Secrets set on the worker: GITHUB_APP_CLIENT_ID, GITHUB_APP_CLIENT_SECRET, COOKIE_ENCRYPTION_KEY
  • Allowlist var: ALLOWED_GITHUB_LOGINS="mazze93" (in wrangler.jsonc)
  • GitHub App permissions: Contents RW, Issues RW, Pull requests RW, Metadata R, Administration RW. github_update_repo works directly (verified 2026-10-21 with a no-op description update).

Commands

npm run typecheck   # tsc --noEmit
npm test            # vitest run, via @cloudflare/vitest-pool-workers (real workerd, not a Node polyfill)
npm test test/oauth-boundaries.test.ts   # one file
npm test -- -t "localhost"       # one test by name
npm run dev         # wrangler dev at http://localhost:8788 (needs .dev.vars)
npm run tail        # live worker logs
bash scripts/test-toolchain.sh  # Apple container preferred; Docker fallback; dry-run only

npx wrangler deploy --dry-run --outdir dist   # local build check; catches
                    # bundling/binding errors tsc cannot see. Never publishes.

Deployment is automatic. .github/workflows/deploy.yml typechecks, tests, and deploys on every push to main — it is the only place a Cloudflare token is exposed to a deploy step (ci.yml runs on PRs including forks and is deliberately credential-free). npm run deploy is a manual fallback, not the normal path; production drifting behind main because someone forgot to run it by hand is the exact failure that workflow was added to close.

test/*.test.ts covers the OAuth allowlist gate, CSRF/state/signed-cookie handling, loopback redirect validation, token refresh, and tool error-wrapping — see vitest.config.ts for how bindings are sourced from wrangler.jsonc. CI runs the suite as a verification gate. The authorize routes are covered in test/authorize-routes.test.ts; test/oauth-boundaries.test.ts also covers token audience isolation and legacy path-bound grant rejection. Cross-location KV refresh races remain a known limitation. typecheck + test + a live tool call against the deployed worker is the verification bar.

Read the full file on GitHub · 215 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. 2d ago Changed · +18 lines · +273 tokens per session 8562f3573496
  2. 7d ago Changed · +4 lines · +66 tokens per session c1eeeaffe485
  3. 14d ago Changed · +5 lines · +84 tokens per session 363250175579
  4. 2mo ago First seen · 188 lines · 2,614 tokens per session scan A 155ddb07f7c0

Subscribe to this mod's changes

github-mcp-gateway CLAUDE.md is an instructions file published in the GitHub repository mazze93/github-mcp-gateway (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 3,037 tokens to every session, about $0.0121 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.

Related

Other instructions, from other repositories

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 · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens