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 skills add tmj-90/gaffer --skill python-conventionsgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/skills/tmj-90/gaffer/python-conventions)<a href="https://agentmods.dev/skills/tmj-90/gaffer/python-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/python-conventions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tmj-90/gaffer/python-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/python-conventions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00120 | $0.02146 |
| Opus 5.5 | $0.00048 | $0.00858 |
| Sonnet 5.5 | $0.00024 | $0.00429 |
| Haiku 4.5 | $0.00012 | $0.00215 |
Grade A, and why
python-conventions 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 16d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write idiomatic, typed Python
Python stays maintainable when every signature is typed, errors are narrow, resources
live in with blocks and shared state is guarded. For the builder and the reviewer of a Python diff; the repo's config and existing code win over it.
Procedure
- Discover the repo's conventions first. Call
search_lorefor Python conventions. Readpyproject.toml(requires-python,[tool.ruff],[tool.mypy]/[tool.pyright],[tool.pytest.ini_options]), the lockfile that names the env manager (uv.lock→ uv,poetry.lock→ Poetry,requirements*.txt→ pip/venv),tox.ini/noxfile.py,.pre-commit-config.yamland the CI workflow. Open the nearest sibling module and its test; copy its imports, data modelling (dataclass/Pydantic/attrs), logging and fixtures. Never install into the system interpreter; never edit tool config to make your change pass. - Pin the exact commands from CI,
Makefile, tox/nox or pre-commit (therun-testsandrun-lintskills). Use the defaults below only when the repo defines none. - Write the change with the idioms below, then walk the concurrency section for every task, thread, file, connection and shared object you touched.
- Test each acceptance criterion's own behaviour. One pytest test (or
parametrizecase) per AC that fails without your change, plus its error path. If the AC involves shared state or persistence, add a test that runs N concurrent callers (ThreadPoolExecutororasyncio.gather) and asserts the invariant. - Verify, then stop. Done when: lint and format check are clean, the type checker
reports no new errors, the test suite (with the repo's coverage gate) is green, and
every AC has a test. Record the output with the
record-evidenceskill; the runner submits the work.
Commands
- Env: use the existing environment —
uv run --no-sync …(plainuv runsyncs, i.e. installs),poetry run …, or.venv/bin/…. Never install: the hook blockspip install, anduv sync/poetry install/uv addare forbidden too though the hook does not catch them. A missing tool goes in the evidence. - Lint and format:
ruff check .andruff format --check .(orblack --check .andisort --checkwhere the repo still uses them). - Types:
mypy .(or the configured paths/--strict) orpyright, per the repo. - Tests:
pytest -q; one test:pytest path/test_x.py::test_name; coverage:pytest --cov=<pkg> --cov-report=term-missing. - Security when relevant:
pip-audit(if installed; it reads the environment, never fixes it);bandit -r <pkg>if configured.
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.
- 16d ago Changed · +48 lines · +36 tokens per session d71b5e76677e
- 1mo ago First seen · 77 lines · 84 tokens per session scan A cadc4c6206c9
python-conventions is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 120 tokens to every session and 2,146 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
test-generator
Generate pytest test cases for Python functions and classes.
python-pytest-ops
Modern pytest patterns for effective testing.
pytest-patterns
Pytest best practices including fixtures, parametrize, markers, and assertion patterns for Python test suites.
python-testing
Python testing patterns with pytest including unit tests, integration tests, fixtures, mocking, and coverage. Use when writing Python tests.
junit-testing
JUnit 5 testing patterns including annotations, Mockito mocking, Spring Boot test slices, MockMvc, Testcontainers integration, and parameterized tests. Use when the user is writing Java tests, setting up test infrastructure, mocking dependencies, testing Spring controllers, or running integration tests with real…