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 Jamie-BitFlight/claude_skills --skill code-review-pythongit clone --depth 1 https://github.com/Jamie-BitFlight/claude_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/jamie-bitflight/claude_skills/code-review-python)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/code-review-python"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/code-review-python/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/jamie-bitflight/claude_skills/code-review-python"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/code-review-python.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.01322 |
| Opus 5.5 | $0.00022 | $0.00529 |
| Sonnet 5.5 | $0.00011 | $0.00264 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
code-review-python 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 7d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Code Review Patterns
Stack-specific rules loaded by dh:code-reviewer when pyproject.toml or *.py files are detected.
Load /dh:review-principles before applying these checks.
When available, load /python-engineering:standards-for-python-development; it owns the shared
Python policy and contextual defaults. If that plugin is unavailable, use the checks below with
the target's supported Python versions, contracts, and active tooling. Report the unavailable
policy reference without making Python-engineering a prerequisite for review.
Type Annotations
- Check that public parameter and return annotations communicate the supported contract; apply the project's annotation gate, including explicit
Nonereturns where required. - Contain justified
Any, broadobject, and unchecked casts at explicit dynamic or external boundaries with typed outputs. An explanatory comment alone does not establish safety, and replacingAnywith broadobjectalone does not strengthen the contract. - Match data shapes to their purpose: typed mappings where mapping behavior is required, typed value objects for internal data, and runtime validation where external data needs it. Do not require
TypedDictfor every cross-module value or migrate a coherent dataclass/Pydantic/mapping design solely for uniformity. - Prefer native generics and union syntax for new code when the supported Python floor permits them; do not report supported existing syntax as a correctness defect.
- Check that a
Protocolor ABC models a real substitutable contract; preserve the project's coherent choice.
Linter Compliance
- Read the active linter configuration and report violations of its enforced rules; do not enable additional rules during review.
- Investigate bare catches and unintended library output for swallowed control signals or corruption of a caller's output contract. Prefer specific exception handling and the project's diagnostic channel.
- Flag unexplained constants, unused imports, and export ambiguity when they violate a project gate or obscure a consequential contract. Do not classify every numeric comparison as a defect.
- Preserve supported interpolation idioms, including deferred logging formatting; use the project's formatting rules rather than requiring a style migration.
- Check intended exports, including
__all__where the project or public import contract requires it.
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.
- 7d ago Changed · -1 lines 1db3d3361b5a
- 15d ago Changed · +3 lines · -13 tokens per session dabc7cda624a
- 1mo ago First seen · 106 lines · 68 tokens per session scan A b7b32d1f8814
code-review-python is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (67 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 1,322 once invoked, about $0.0002 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 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.
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…
python-review-checklist
Deterministic Python review checklist shipped with the CAO skills-lifecycle example.
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…
coding.make_function_private
Identify private or public functions in a file and rename with underscore.
plankton-code-quality
Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.