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/pol-lopez/fastapi-template/agents-mdgit clone --depth 1 https://github.com/pol-lopez/fastapi-templateWhat 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 | $0.00921 | $0.00921 |
| Opus 5 | $0.00461 | $0.00461 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
fastapi-template AGENTS.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.
FastAPI Template - Project Guidelines
This file provides guidance to AI coding agents (Claude Code, Codex, Cursor, etc.) when working with code in this repository.
Overview
FastAPI + Python 3.14 + PostgreSQL + SQLAlchemy async + Alembic. Hexagonal DDD architecture with bounded contexts under src/contexts/. Dependency injection via dependency-injector. CLI via Typer.
Commands
make start # Start services (docker compose up)
make stop # Stop services
make build # Build Docker images
make fmt # Format code with ruff
make lint # Lint code with ruff --fix
make all # Install + format + lint
make test # Run all tests (Docker)
make test-unit # Run unit tests (Docker)
make test-unit-local # Run unit tests locally (fast, no Docker)
make test-integration # Run integration tests (Docker)
make test-e2e # Run e2e tests (Docker)
make test-cov # Run tests with coverage (Docker)
make migration-create # Create autogenerated Alembic migration
make migration-upgrade # Apply migrations (upgrade head)
make migration-downgrade # Revert last migration
make migration-history # Show migration history
make cli args="..." # Run CLI commands in container
Code Style
- Language: All code, variable names, class names, function names, and comments in English. Commit messages and PR descriptions in English.
- Comments: Never add comments unless explicitly requested or the code is genuinely non-obvious. Do not add explanatory comments when removing dead code — just remove it.
- Imports: Absolute, starting with
src/(e.g.,from src.contexts.auth.domain.aggregates import User) - Async: Always
async/awaitfor I/O operations. Useasyncpgdriver. - Python: Strict typing. Use
|union syntax, notOptional. Explicit return types on all functions. NoAny. - Errors: Throw custom Domain Errors (
src/contexts/*/domain/errors.py), never generic HTTPException in domain/application layers. The HTTP middleware translates domain errors to HTTP responses. - Formatting: Ruff enforces 88-char line length, double quotes, 4-space indent. Do NOT fight ruff — if it reformats something, that's the project standard.
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 · 921 tokens per session scan A 45107ed47f63
fastapi-template AGENTS.md is an instructions file published in the GitHub repository pol-lopez/fastapi-template (23 stars, last pushed 8d ago), licensed MIT. It adds 921 tokens to every session, about $0.0046 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 2026-08-30.
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.
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).
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
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
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.