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 chen3feng/agent-skills --skill python-code-audit-sweepgit clone --depth 1 https://github.com/chen3feng/agent-skillsWrote 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/chen3feng/agent-skills/python-code-audit-sweep)<a href="https://agentmods.dev/skills/chen3feng/agent-skills/python-code-audit-sweep"><img src="https://agentmods.dev/badge/skills/chen3feng/agent-skills/python-code-audit-sweep/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/chen3feng/agent-skills/python-code-audit-sweep"><img src="https://agentmods.dev/badge/skills/chen3feng/agent-skills/python-code-audit-sweep.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 | $0.01532 |
| Opus 5.5 | $0.00013 | $0.00613 |
| Sonnet 5.5 | $0.00007 | $0.00306 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
python-code-audit-sweep 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python code-audit sweep
When to use
The user says something like "check the code for improvements, no feature changes" or "do a general cleanup pass". You have a Python codebase, no specific bug report, and need to surface high-signal, low-risk findings without accidentally changing behavior.
Problem
A naive "cleanup" PR usually fails review because it mixes three very different kinds of change into one blob:
- A real latent bug (semantics change when fixed).
- Dead code / unused locals (safe, mechanical).
- Spelling, wording, anti-patterns in comments (pure style).
Reviewers want to merge (2) and (3) fast and scrutinize (1) carefully. If you stuff them into one PR, the whole thing blocks on the hardest item, and the diff hides the real bug behind dozens of typo fixes.
Solution
Do the audit in two phases: find, then partition into separate PRs.
1. Find (cheap, parallel grep + pyflakes)
# Static analysis: unused imports/vars, undefined names, simple smells.
pyflakes src/ | tee /tmp/pyflakes.txt
# Common anti-patterns (extend as needed).
grep -rnE 'not [a-zA-Z_][a-zA-Z_0-9.()\[\]]* is None' src/ # should be "is not None"
grep -rnE '== None|!= None' src/ # should be "is (not) None"
grep -rn 'type(str)\|type(int)\|type(list)\|type(dict)' src/ # type() applied to a builtin type
# Typo shortlist — curated, not exhaustive; avoids false positives.
grep -rniE '\b(seperat|writen|recieve|occured|begining|lenght|tranform|initialis|standardalone|dependancy|mutiple|visibilty|accomodate|seperately)\w*' \
src/ doc/ tool/
# Filenames with unusual punctuation (real bugs on GitHub's Markdown renderer).
find . -name '*,md' -o -name '*.m d' -o -name '*.mdd'
2. Partition into three PRs
Label every finding as A, B, or C. One PR per label, in this order:
| Tag | Contents | Risk | Review burden |
|---|---|---|---|
| A | Real bugs: broken error messages, dead-assignment-that-hides-a-branch, wrong file extensions. | Behavior may change (even if tiny). | Highest — maintainer must read carefully. |
| B | Dead locals, unused imports, tuple-unpacking where half is unused. | None. | Low. |
| C | Typos in comments/docs, not x is None → x is not None, file renames with no in-repo references. |
None. | Lowest. |
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 · 151 lines · 33 tokens per session scan A c43a9e1f29dc
python-code-audit-sweep is a skill published in the GitHub repository chen3feng/agent-skills (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,532 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
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
plugin-architecture-patterns
Design, implement, or diagnose Xberg plugin traits, typed registries, priority collisions, lifecycle, native extractors, and Alef-generated Python plugin bridges. Load for plugin-system work, not ordinary extractor parsing.
test-corpus
The testdocuments submodule is a bucket-fetched fixture corpus that is not committed. This skill covers readtestfixture, missing fixtures, valid A/B controls, and submodule push order. Load before running Rust tests on a fresh clone, setting up an A/B control, adding a fixture-backed test, or diagnosing…
idapython
IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida modules (50+), idautils iterators, and common…
stack-trace-python-probe
Internal helper for meta-stack-trace-investigator. Use when a Python traceback needs Python-specific root-cause checks, pytest reproducer guidance, and defensive patch targets.
memory-optimization
Optimize Python code for reduced memory usage and improved memory efficiency. Use when asked to reduce memory footprint, fix memory leaks, optimize data structures for memory, handle large datasets efficiently, or diagnose memory issues. Covers object sizing, generator patterns, efficient data structures, and memory…