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/gpauloski/python-template/agents-mdgit clone --depth 1 https://github.com/gpauloski/python-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 | $0.00738 | $0.00738 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
python-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 yesterday.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Baseline guidance for AI coding agents working in this repository. Humans should
read the docs under docs/contributing/; this file is the concise, agent-facing
summary. CLAUDE.md imports this file so there is a single source of truth.
Repository Layout
pypkg/— the package source (flat layout, nosrc/). Avoid writing logic in__init__.py.tests/— pytest tests. Mirror the package layout; test files end in_test.py(e.g.pypkg/x/y.py→tests/x/y_test.py).testing/— shared helpers/fixtures for tests (not tests themselves).docs/— MkDocs sources.docs/generate_api.pyauto-generates API pages, so do not hand-writedocs/api/..github/workflows/— CI (tests, prek, docs, publish).
pypkg, pypkg-author, and gpauloski/python-template are template
placeholders; in a real project they will be replaced with the actual names.
Environment & Commands
This project uses uv. Create the environment and activate it once, then invoke tools directly.
uv sync # install project + dev group
source .venv/bin/activate # Windows: .venv\Scripts\activate
uv sync --group docs # add docs dependencies
pytest # run tests
pytest tests/x/y_test.py::test_z # run one test
prek run --all-files # run all hooks (lint/format/type/spell)
mypy . # type check
tox # full matrix (py3.10-3.13, prek, docs)
tox -e py313 # a single environment
uv build # build sdist + wheel
If the environment is not activated, prefix a command with uv run (e.g.
uv run pytest) to run it inside the managed environment.
Before finishing a change, ensure prek run --all-files and pytest both pass.
Conventions
- Every module starts with
from __future__ import annotations(enforced by Ruff isort). Fully type-annotate package code — mypy runs in strict mode. - Formatting/linting is Ruff with
ALLrules enabled (seepyproject.tomlfor the commented ignores). Style: single quotes, 79-char lines, Google-style docstrings. Do not fight the formatter. - Spell checking is typos; complexity is gated by complexipy.
- Tests use
assertand may omit docstrings/annotations (relaxed via per-file ignores). Put reusable test code intesting/, nottests/. - Prefer pure functions; document all raised exceptions in docstrings. See
docs/contributing/style-guide.mdfor the full style guide.
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.
- yesterday First seen · 66 lines · 738 tokens per session scan A 80cd6933cdec
python-template AGENTS.md is an instructions file published in the GitHub repository gpauloski/python-template (19 stars, last pushed 7d ago), licensed MIT. It adds 738 tokens to every session, about $0.0037 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
cookiecutter-mlops-package AGENTS.md
Instructions for fmind/cookiecutter-mlops-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.
django-starter-template AGENTS.md
Instructions for wilfredinni/django-starter-template, covering agents.md, commands, lint & typecheck, architecture and testing.
mayak AGENTS.md
Instructions for LamantinAI/mayak, covering agents.md, quick start, common commands, validation and testing.
Blueprint AGENTS.md
Instructions for Magolor/Blueprint, covering blueprint agent guide, purpose and authority, work loop, typescript architecture and commands.
template-advisor-aget AGENTS.md
Instructions for aget-framework/template-advisor-aget, covering agent configuration - advisor aget template, agent compatibility, project context, purpose and key characteristics.
Ignite AGENTS.md
AGENTS.md instructions for Sumukh/Ignite, covering agents.md, what this repo is, fast start (local development), seed local sqlite db with starter users and run app.