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/rnegron/django-project-template/agents-mdgit clone --depth 1 https://github.com/rnegron/django-project-templateWrote 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.
[](https://agentmods.dev/instructions/rnegron/django-project-template/agents-md)<a href="https://agentmods.dev/instructions/rnegron/django-project-template/agents-md"><img src="https://agentmods.dev/badge/instructions/rnegron/django-project-template/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02252 | $0.02252 |
| Opus 5 | $0.01126 | $0.01126 |
| Sonnet 5 | $0.00450 | $0.00450 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
django-project-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 4d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repository. Tool-specific entrypoints such as CLAUDE.md point here so every agent shares one source of truth.
Project Overview
A Django backend project bootstrapped from a Django project template, set up for rapid development.
Key characteristics:
- Python 3.13 with Django 5.2 (LTS)
- Custom settings layout in
config/(not within the app directory) - Custom User model with email-only authentication (no username)
- Full-stack setup including frontend tooling (Tailwind, htmx, Alpine.js)
- Celery + Redis for async tasks
- Docker-first development approach
Essential Commands
Development Setup
# Local development (without Docker)
uv sync
cp .env.example .env
uv run pre-commit install
uv run python manage.py check
# Docker development (recommended)
cp .env.example .env
docker-compose up --detach --build
# Default admin: [email protected] / password123
Running Tests
# Run all tests
uv run pytest
# Run with coverage (CI standard: 85% minimum)
uv run pytest --cov={{ project_name }} --cov-fail-under=85 --cov-report term-missing:skip-covered
# Run specific test file
uv run pytest tests/test_something.py
# Run specific test
uv run pytest tests/test_something.py::test_function_name
Code Quality
# Run all pre-commit hooks manually
uv run pre-commit run --all-files
# Individual tools
uv run ruff check . # Run linting
uv run ruff check . --fix # Run linting with auto-fix
uv run ruff format . # Run formatting
uv run mypy . # Run type checking
Commit Messages
This project enforces Conventional Commits format:
# Interactive commit (recommended for beginners)
uv run cz commit
# Manual commit (must follow conventional format)
git commit -m "feat: add user profile page"
git commit -m "fix(auth): resolve token expiration"
git commit -m "docs: update README with new features"
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.
- 4d ago First seen · 268 lines · 2,252 tokens per session scan A 0423f0d5e732
django-project-template AGENTS.md is an instructions file published in the GitHub repository rnegron/django-project-template (11 stars, last pushed 2mo ago), licensed MIT. It adds 2,252 tokens to every session, about $0.0113 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
speedpy AGENTS.md
Instructions for speedpy/speedpy, covering agents.md, additional case-specific instructions, project overview, development commands and architecture.
django-starter-template AGENTS.md
Instructions for wilfredinni/django-starter-template, covering agents.md, commands, lint & typecheck, architecture and testing.
speedpy CLAUDE.md
Instructions for speedpy/speedpy: See AGENTS.md for project guidance. All conventions, architecture notes, and development commands for this project live there — use it as the source of truth.
CoachSync AGENTS.md
Instructions for rakibul-islam-raju/CoachSync, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
dare-backend AGENTS.md
AGENTS.md instructions for cmudco/dare-backend, covering agents.md, project architecture, development commands, environment setup and development server.
dare-backend CLAUDE.md
Claude Code instructions for cmudco/dare-backend, a project described as: Open-source Django REST backend for the DARE Platform, with multi-LLM chat, RAG, MCP tools, AI workflows, and usage tracking.