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/jmcmeen/python-backend/claude-mdgit clone --depth 1 https://github.com/jmcmeen/python-backendWhat 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 | $0.01197 | $0.01197 |
| Opus 5 | $0.00598 | $0.00598 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
python-backend 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
This is a Python backend template using a layered architecture with FastAPI, SQLAlchemy, Pydantic, and Alembic.
Architecture Rules
- Endpoints are thin wrappers.
app/api/handlers must only validate input (via schemas), call a service, and return a response. No business logic in route handlers. - Business logic lives in services.
app/services/contains all domain logic. Services must be framework-independent and testable in isolation -- no FastAPI or SQLAlchemy imports. - Repositories abstract data access.
app/repositories/wraps all ORM/database calls behind clean method signatures. Never use raw ORM queries outside of repositories. - Schemas are not models.
app/schemas/(Pydantic) defines API contracts.app/models/(SQLAlchemy) defines database tables. They evolve independently. - Utils stay small. If a utility in
app/utils/grows complex, promote it to a service. main.pyis wiring only. Mount routers, set up middleware, run startup hooks. Nothing else.
Directory Conventions
- API versioning:
app/api/v1/,app/api/v2/, etc. - One file per domain entity in models, schemas, services, and repositories (e.g.,
user.py,user_service.py,user_repo.py). - Tests mirror the source structure:
tests/unit/for services/utils,tests/integration/for API and DB tests. - Database migrations go in
migrations/(Alembic).
Tech Stack
- FastAPI + Uvicorn
- SQLAlchemy (ORM) + Alembic (migrations)
- Pydantic (validation and settings via BaseSettings)
- pytest + httpx + pytest-asyncio (testing)
Commands
Use uv and the Makefile. Don't suggest pip or invoke pytest directly.
make dev-setup # first-time onboarding (install + pre-commit + .env)
make dev # uvicorn --reload
make test # pytest + coverage (80% floor)
make test-unit # services/utils only
make test-integration # API/DB only
make lint # ruff check + format check
make fmt # ruff format + safe fixes
make typecheck # mypy --strict against app/
make migrate # alembic upgrade head
make migration m="..." # generate an autogenerated revision
make up # docker compose up -d --build
make down # docker compose down (preserves volumes)
make nuke # docker compose down -v --rmi all --remove-orphans
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.
- 2d ago First seen · 79 lines · 1,197 tokens per session scan A a868ac06df62
python-backend CLAUDE.md is an instructions file published in the GitHub repository jmcmeen/python-backend (5 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 1,197 tokens to every session, about $0.0060 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
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.