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 skills/mickeyyaya/refactoring-skills/python-review-patternsnpx skills add mickeyyaya/refactoring-skills --skill python-review-patternsgit clone --depth 1 https://github.com/mickeyyaya/refactoring-skillsWhat 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 | $0.00057 | $0.02731 |
| Opus 5 | $0.00028 | $0.01366 |
| Sonnet 5 | $0.00011 | $0.00546 |
| Haiku 4.5 | $0.00006 | $0.00273 |
Grade A, and why
python-review-patterns 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 2d 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Code Review Patterns
Overview
Python's design — dynamic typing, duck typing, mutable defaults, and the GIL — creates a class of bugs invisible to reviewers unfamiliar with the language. A reviewer applying general rules without Python context will generate false positives (flagging correct duck typing as a type error) and false negatives (missing the mutable default argument trap, which looks syntactically valid but is always wrong).
Load this skill when reviewing a Python PR, assigning severity to a Python-specific finding, or checking whether a flagged pattern is a real bug or a duck-typing false positive.
Quick Reference
| Review Dimension | Severity | Primary Red Flag |
|---|---|---|
| Mutable default argument | HIGH | def f(x=[]) or def f(x={}) |
| Mutable class attribute | HIGH | class C: items = [] shared across instances |
| Missing type hints on public API | LOW | No annotations on public function signatures |
| Incomplete type hints (partial) | MEDIUM | Some args annotated, others not |
Optional vs X | None |
NIT | Use X | None in Python 3.10+; Optional[X] in 3.9- |
| GIL: CPU-bound in threads | HIGH | threading.Thread doing heavy computation |
| asyncio blocking call | HIGH | time.sleep() or sync I/O inside async def |
Bare except: |
MEDIUM | Catches KeyboardInterrupt, SystemExit |
| Exception swallowed silently | HIGH | except Exception: pass with no log |
| Star import | MEDIUM | from module import * in non-__init__ context |
| Circular import | HIGH | Mutually importing modules at top level |
global keyword |
MEDIUM | Mutable shared state; HIGH under threading |
eval()/exec() on user input |
CRITICAL | Arbitrary code execution |
assert in production logic |
HIGH | Stripped by -O; never use for validation |
| Non-context-manager resource | MEDIUM | f = open(...) without with |
Mutable Default Arguments
Python evaluates default argument values once at function definition time, not at call time. A mutable default (list, dict, set) is shared across all calls that omit the argument — always a bug.
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.
- 2d ago First seen · 358 lines · 57 tokens per session scan A e61755ccd0e6
python-review-patterns is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 57 tokens to every session and 2,731 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
bump-dependency
Bumps a Python package dependency across Home Assistant Core integrations, regenerates core requirement files, runs verification tests and prek lint, and prepares a pull request with proper release/compare links.
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
adk-style
Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or…
coding
编写并运行 Python 代码，验证脚本逻辑和输出。.
ax-python-agent
Use when writing Python code with axllm for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.