metis: Instructions file for Claude Code

CLAUDE.md

metis CLAUDE.md is an instructions file for Claude Code from KacemMathlouthi/metis. It costs 10,476 tokens per session, scanned A, original, MIT.

A repository instruction file for Claude Code, an AI coding assistant. It records the project’s standards, structure, commands, and Python/FastAPI backend guidance so the assistant can follow the project’s existing rules.

In plain words
What is it for?
Use it to guide changes in the metis repository, especially backend work, validation, error handling, database access, and tests.
Why use it?
It reduces repeated explanations about code quality, security, testing, types, and project conventions. It gives coding work a shared set of expectations.

Instructions file for Claude Code

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

This is KacemMathlouthi/metis's own configuration. It tells Claude Code how to work on metis 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 metis configures →

Reuse

Borrowing it

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

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 metis CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kacemmathlouthi/metis/claude-md"><img src="https://agentmods.dev/badge/instructions/kacemmathlouthi/metis/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,476 This file is loaded in full into every session.
When invoked 10,476 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 $0.10476 $0.10476
Opus 5.5 $0.04190 $0.04190
Sonnet 5.5 $0.02095 $0.02095
Haiku 4.5 $0.01048 $0.01048

Measured 19d ago against content hash 91b806251992, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

metis 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 19d 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 · 728 lines

How it starts

The opening of the file, as written. The whole thing — 728 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to any coding agent working on this repository.

Standards

This is a production-grade codebase. All contributions must meet the following bar:

  • Code quality: Clean, readable, well-structured code. No shortcuts, no hacks, no "good enough" solutions. Every function should be purposeful and every abstraction justified.
  • Performance: Optimized by default. Async where it matters, efficient data structures, minimal allocations, no N+1 queries, no unnecessary re-renders.
  • Security: Zero tolerance for vulnerabilities. Input validation at boundaries, parameterized queries, proper auth checks, no secrets in code, OWASP top 10 awareness at all times.
  • Error handling: Graceful degradation, meaningful error messages, proper logging. No silent failures, no bare excepts, no swallowed errors.
  • Type safety: Full type hints (Python) and strict TypeScript. No Any unless absolutely unavoidable. Types are documentation.
  • Testing mindset: Write code that is testable. Dependency injection, clear interfaces, no hidden side effects.
  • Consistency: Follow existing patterns in the codebase. Match naming conventions, file organization, and architectural patterns already established.

Project Overview

Metis is an AI-powered GitHub code reviewer that provides intelligent, context-aware feedback on pull requests. The system uses a GitHub App to receive webhook events, analyze code changes, and post automated reviews.

Architecture: Monorepo with separate backend (Python/FastAPI) and frontend (React/TypeScript/Vite).

Commands

Backend (Python/FastAPI)

Navigate to backend/ for all backend commands:

cd backend

# Development
uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

# Celery worker (async task processing)
celery -A app.core.celery_app worker --loglevel=info
celery -A app.core.celery_app flower --port=5555  # Monitoring UI

# Install dependencies (using uv)
uv sync

# Database
docker-compose -f docker-compose.dev.yml up -d  # Start PostgreSQL + Redis + pgAdmin + Redis Insight
alembic upgrade head                             # Run migrations
alembic revision --autogenerate -m "description" # Create migration
alembic downgrade -1                             # Rollback one migration
alembic history                                  # View migration history

# Code quality
ruff check .              # Lint
ruff format .             # Format
mypy app/                 # Type check
pytest                    # Run all tests
pytest tests/unit         # Run unit tests only
pytest tests/integration  # Run integration tests only
pytest -v -k test_name    # Run specific test

# Pre-commit hooks
pre-commit install
pre-commit run --all-files

# Services
docker-compose -f docker-compose.dev.yml up -d     # Start all services
docker-compose -f docker-compose.dev.yml logs -f   # View logs
docker-compose -f docker-compose.dev.yml down      # Stop all services

Read the full file on GitHub · 728 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. 19d ago First seen · 728 lines · 10,476 tokens per session scan A 91b806251992

Subscribe to this mod's changes

metis CLAUDE.md is an instructions file published in the GitHub repository KacemMathlouthi/metis (20 stars, last pushed 19d ago), licensed MIT. It adds 10,476 tokens to every session, about $0.0419 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 2026-10-19.

Related

metis CLAUDE.md compared with instructions from other repositories

metis CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
metis CLAUDE.mdKacemMathlouthi/metisInstructions file2019d agoMITA10,476Claude 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