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/wilfredinni/django-starter-template/agents-mdgit clone --depth 1 https://github.com/wilfredinni/django-starter-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/wilfredinni/django-starter-template/agents-md)<a href="https://agentmods.dev/instructions/wilfredinni/django-starter-template/agents-md"><img src="https://agentmods.dev/badge/instructions/wilfredinni/django-starter-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 5.1 | $0.00772 | $0.00772 |
| Opus 5 | $0.00386 | $0.00386 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
django-starter-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 6d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Commands
All Django commands run inside Docker (docker compose exec backend). Use the make shortcuts:
make up # docker compose up
make test # docker compose exec backend pytest
make test-cov # pytest --cov
make test-html # pytest --cov --cov-report=html
make migrate # docker compose exec backend python manage.py migrate
make seed # seed DB (creates [email protected] / admin)
make superuser # createsuperuser
make shell # shell_plus (django-extensions, only in DEBUG)
make logs # logs -f backend
make logs-worker # logs -f worker
make logs-beat # logs -f beat
make rebuild # docker compose up --build
Single test file or function:
docker compose exec backend pytest apps/users/tests/test_user_model.py
docker compose exec backend pytest apps/users/tests/test_user_model.py::test_create_user
Important: The backend entrypoint auto-runs migrate on every start. No manual migrate step needed in Docker.
Lint & Typecheck
No CI enforces lint/typecheck. Run manually before committing:
uv run ruff check .
uv run ruff format --check .
uv run mypy .
Ruff selects E/F/I/B, line-length 90, double quotes, target py314. Mypy targets python_version = "3.14" with django-stubs + mypy-drf-plugin.
Architecture
- Django settings:
conf/settings.py(DJANGO_SETTINGS_MODULE=conf.settings) - Test settings:
conf/test_settings.py— swaps RequestIDMiddleware/RequestIDFilter for mocks, usesLocMemCache(throttle state resets per run), relaxes all throttle rates to 1000/min - Apps:
apps/users/(CustomUser, auth),apps/core/(ping, middleware, tasks, seed — no models) - AUTH_USER_MODEL:
users.CustomUser— email-based,username=None,USERNAME_FIELD='email' - Auth: Knox tokens (sha512, 64 chars, 10hr TTL,
Bearerprefix). Admin creates users via/api/v1/auth/create/ - Admin URL:
/admin-panel/(not/admin/) - Celery: app name
"worker"inconf/celery.py,celery -A conffor CLI. DjangoDatabaseSchedulerfor beat. Worker/beat wait for migrations viascripts/wait-for-migrations.sh - Package layout:
pyproject.tomlsetspackages = ["apps", "conf"]— internal imports useapps.core.,apps.users.,conf.settings
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.
- 6d ago First seen · 73 lines · 772 tokens per session scan A ad1d32c413ff
django-starter-template AGENTS.md is an instructions file published in the GitHub repository wilfredinni/django-starter-template (53 stars, last pushed 11d ago), licensed MIT. It adds 772 tokens to every session, about $0.0039 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
AGENTS.md instructions for speedpy/speedpy, covering agents.md, additional case-specific instructions, project overview, development commands and architecture.
python-template AGENTS.md
AGENTS.md instructions for gpauloski/python-template, covering agent instructions, repository layout, environment & commands, conventions and skills.
klaussy-agents fastapi.instructions.md
Instructions for steph-dove/klaussy-agents: Example context from fastapi/applications.py (lines 214-220).
klaussy-agents httpx.instructions.md
Instructions for steph-dove/klaussy-agents: Example context from httpx/urlparse.py (lines 153-163).
python-template CLAUDE.md
Claude Code instructions for gpauloski/python-template: The agent instructions for this repository live in AGENTS.md to avoid duplication. They are imported below.
robs_awesome_python_template AGENTS.md
Instructions for tedivm/robs_awesome_python_template, covering agent instructions and key technologies.