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.
git 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/rules/andr-ca/agentharness/python-conventions)<a href="https://agentmods.dev/rules/andr-ca/agentharness/python-conventions"><img src="https://agentmods.dev/badge/rules/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/rules/andr-ca/agentharness/python-conventions"><img src="https://agentmods.dev/badge/rules/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 | $0.00033 | $0.00614 |
| Opus 5.5 | $0.00013 | $0.00246 |
| Sonnet 5.5 | $0.00007 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
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 — 65 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 · 65 lines · 33 tokens per session scan A 81ff292a4f60
python-conventions is a cursor rule published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 5d ago), licensed MIT. It adds 33 tokens to every session and 614 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 2026-09-03.
Other cursor rules, from other repositories
python_tests
We use the unit tests to cover internal behavior that can work without the web / backend counterpart. We aim for 95%+ unit test coverage of our Python code in lib/streamlit.
python-llm-ml-workflow-cursorrules-prompt-file
Cursor rules for Python LLM & ML development with workflow integration.
python
Python best practices and patterns for modern software development with Flask and SQLite.
python-containerization-cursorrules-prompt-file
Cursor rules for Python development with containerization integration.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
rich
Definitive guidelines for building robust, maintainable, and visually appealing Python CLI applications using the rich library.