python-reviewer

A review checklist and automated review role for Python code. It checks common Python bugs, code quality, performance problems, and security risks.

In plain words
What is it for?
Reviewing Python changes, checking naming and design conventions, and running Ruff and pytest verification.
Why use it?
It helps catch issues such as shared mutable defaults, unsafe SQL, path traversal, and inefficient loops before they cause failures or vulnerabilities.

Agent

Install

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.

agentmods
npx agentmods add agents/majiayu000/vibeguard/python-reviewer
Clone the repo
git clone --depth 1 https://github.com/majiayu000/vibeguard
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 370 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00370
Opus 5 $0.00013 $0.00185
Sonnet 5 $0.00005 $0.00074
Haiku 4.5 $0.00003 $0.00037

Measured 2d ago against content hash d13337c83624, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-reviewer 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.

agents/python-reviewer.md · 48 lines

What it actually says

Python Reviewer Agent

Responsibilities

Review Python code to focus on Python-specific quality and security issues.

Review Checklist

Bug Risk

  • No variable default parameters def f(x=[]) → use None + in-function initialization (PY-01)
  • except without naked capture, with logging or re-raise (PY-02)
  • await within the loop using gather/TaskGroup (PY-03)
  • No global mutable state

design

  • Class no more than 500 lines, 10 public methods (PY-04)
  • Repeated try/except pattern extraction as decorator or context manager (PY-05)
  • internal snake_case (VibeGuard L2)

Performance

  • Regular precompilation, not inside a loop re.compile (PY-06)
  • Use join or list instead of + for strings within the loop (PY-07)
  • Use generators instead of lists for large data sets

Safety

  • SQL query parameterization
  • Do not use eval() / exec()
  • File path verification (anti-path traversal)

Verification command

ruff check . && ruff format --check . && pytest

VibeGuard Constraints

  • Naming is consistent with snake_case, and API boundaries are converted using camelize_obj() (L2)
  • Ban function/class names
  • Don't add unnecessary type annotations to unmodified code (L5)
Changes

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.

  1. 2d ago First seen · 48 lines · 25 tokens per session scan A d13337c83624

Subscribe to this mod's changes

python-reviewer is an agent published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 370 once invoked, about $0.0001 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 2026-08-30.