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 andr-ca/agentharness --skill python-conventionsgit clone --depth 1 https://github.com/andr-ca/agentharnessWrote 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/andr-ca/agentharness/python-conventions)<a href="https://agentmods.dev/skills/andr-ca/agentharness/python-conventions"><img src="https://agentmods.dev/badge/skills/andr-ca/agentharness/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/andr-ca/agentharness/python-conventions"><img src="https://agentmods.dev/badge/skills/andr-ca/agentharness/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 | $0.00037 | $0.00637 |
| Opus 5.5 | $0.00015 | $0.00255 |
| Sonnet 5.5 | $0.00007 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00064 |
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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Conventions
This file is self-contained for day-to-day use. Deeper reference (needs
the full harness checkout, not just this skill — these aren't bundled
here since they're documentation, not something this skill runs):
languages/python/CONVENTIONS.md (complete examples) and
languages/python/COPILOT_INSTRUCTIONS.md (general agent operating
principles for Python repos — inspect before changing, scope discipline,
never claim a command passed without running it).
Naming
snake_case— functions, variables.PascalCase— classes.UPPER_SNAKE_CASE— module-level constants.- Single underscore prefix for private (
_internal); avoid double underscore except for genuine name-mangling needs. - Exceptions:
PascalCase+Error/Exceptionsuffix, specific not generic (ValidationError, notBadThing).
Imports & structure
Standard library → third-party → local, each group separated by a blank
line. Absolute imports over relative. No from module import *.
Type hints
Use them on function parameters and returns. Match syntax to the
project's minimum Python version — check requires-python in
pyproject.toml before using list[str] (3.9+), X | None (3.10+), or
match/case (3.10+). Don't silently raise the minimum version.
Pitfalls to catch in review
# Mutable default argument — persists across calls, shared state bug
def f(item, container=[]): # WRONG
def f(item, container=None): # RIGHT — default to None, create inside
# Bare/broad except — swallows KeyboardInterrupt, hides real errors
except: # WRONG
except Exception: # still too broad, usually
except ValueError as e: # RIGHT — catch what you expect
# `is` for value comparison — checks identity, not equality
if user_id is 5: # WRONG
if user_id == 5: # RIGHT (== for values, `is` only for None/True/False)
Testing
tests/ directory, test_*.py files, test_* functions, pytest
fixtures for setup. See patterns/testing/TDD.md for the broader
methodology — this skill covers Python-specific structure only.
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.
- 1mo ago First seen · 70 lines · 37 tokens per session scan A 9bd812f5ec1e
python-conventions is a skill published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 5d ago), licensed MIT. It adds 37 tokens to every session and 637 once invoked, about $0.0001 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
mcore-linting-and-formatting
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
cuopt-routing-api-python
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
splitting-oversized-modules
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…
splitting-oversized-modules
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…