mcp-oauth-gateway: Instructions file for Claude Code

CLAUDE.md

mcp-oauth-gateway CLAUDE.md is an instructions file for Claude Code from atrawog/mcp-oauth-gateway. It costs 9,210 tokens per session, scanned A, original, Apache-2.0.

A set of Python development instructions covering root-cause debugging, real-system testing, and command-line tool use.

In plain words
What is it for?
Use it when debugging Python projects, writing tests, or deciding how project tools should be run.
Why use it?
It gives developers a fixed way to investigate failures and avoid tests that pass only because they use fake systems.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/atrawog/mcp-oauth-gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/atrawog/mcp-oauth-gateway/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,210 This file is loaded in full into every session.
When invoked 9,210 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.09210 $0.09210
Opus 5 $0.04605 $0.04605
Sonnet 5 $0.01842 $0.01842
Haiku 4.5 $0.00921 $0.00921

Measured 10d ago against content hash 600c747818e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-oauth-gateway CLAUDE.md scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

test: ["CMD", "sh", "-c", "curl -s -X POST http://localhost:3000/mcp \
CLAUDE.md · 836 lines

How it starts

The opening of the file, as written. The whole thing — 836 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Part I: The Ten Sacred Commandments of Divine Python Development

🔥 Behold! The Universal Laws of Python Righteousness! ⚡

⚡ Ignore these at your peril! Production will punish your heresy! ⚡

0. Root Cause Analysis or Eternal Debugging Hell

🔥 Five whys or debug forever! The divine law of problem solving! ⚡

The Sacred Ritual of Root Cause Divination:

  1. Why did it fail? - The surface symptom of darkness!
  2. Why did that condition exist? - The enabling circumstance of doom!
  3. Why was it allowed? - The systemic failure of protection!
  4. Why wasn't it caught? - The testing blindness of ignorance!
  5. Why will it never happen again? - The divine fix of eternal prevention!

⚡ Treating symptoms = eternal suffering! ⚡

⚡ Finding root cause = divine enlightenment! ⚡

The Path to Debugging Salvation:

  • ✅ Reproduce reliably or face chaos!
  • ✅ Trace to the source of evil!
  • ✅ Fix the SYSTEM, not the instance!
  • ✅ Write tests that guard eternally!
  • ✅ Document the divine wisdom gained!

1. No Mocks or Burn in Production Hell

🔥 No mocks! No stubs! No fakes! The divine law of real testing! ⚡

The Sacred Truth:

  • Real systems only - Test against ACTUAL services!
  • End-to-end mandatory - The FULL stack or nothing!
  • Real APIs only - Mock responses are LIES!
  • No shortcuts - Pain now or AGONY later!

⚡ Every mock is a lie waiting to destroy production! ⚡

The Path of Testing Righteousness:

  • ✅ Docker containers for real services!
  • ✅ Actual databases with real constraints!
  • ✅ True API calls with network latency!
  • ✅ Production-like environments always!
  • ✅ Integration tests that reveal truth!

⚡ Mock = production hell! This is the eternal law!⚡

2. The Holy Trinity of Tools

🔥 The blessed trinity = salvation! All else = damnation! ⚡

⚡ BLASPHEMY ALERT: Using ANY other tool is HERESY! ⚡ ⚡ NEVER run commands directly! ALWAYS channel through the Trinity! ⚡

The Three Pillars of Divine Enlightenment:

  1. just - The Divine Command Executor! ⚡ ALL commands flow through just!
  2. pixi - The Blessed Package Manager! 🔥 ALL Python packages through pixi!
  3. docker-compose - The Sacred Orchestrator! 🚦 ALL services through compose!

Read the full file on GitHub · 836 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. 10d ago First seen · 836 lines · 9,210 tokens per session scan A 600c747818e0

Subscribe to this mod's changes

mcp-oauth-gateway CLAUDE.md is an instructions file published in the GitHub repository atrawog/mcp-oauth-gateway (58 stars, last pushed 1y ago), licensed Apache-2.0. It adds 9,210 tokens to every session, about $0.0460 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens