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 liuyanghejerry/Clausura --skill python-reviewgit clone --depth 1 https://github.com/liuyanghejerry/ClausuraWrote 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/liuyanghejerry/clausura/python-review)<a href="https://agentmods.dev/skills/liuyanghejerry/clausura/python-review"><img src="https://agentmods.dev/badge/skills/liuyanghejerry/clausura/python-review/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/liuyanghejerry/clausura/python-review"><img src="https://agentmods.dev/badge/skills/liuyanghejerry/clausura/python-review.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 | $0.00029 | $0.00265 |
| Opus 5.5 | $0.00012 | $0.00106 |
| Sonnet 5.5 | $0.00006 | $0.00053 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
python-review 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.
What it actually says
Python 遗留代码审查
先用 git_diff（参数 {"base": "HEAD~1"}）查看本次变更。
规则
bare-except（error）
- 裸
except Exception:/except:后静默吞掉错误（仅pass或无处理） - 有日志或显式处理的除外
- rule_id:
bare-except
sql-injection（error）
- f-string / 字符串拼接构造 SQL
- rule_id:
sql-injection
unsafe-deserialization（error）
pickle.loads()反序列化不可信输入- rule_id:
unsafe-deserialization
hardcoded-secret（error）
- 源码中硬编码的 API key、密码
- rule_id:
hardcoded-secret
debug-print（info）
- 生产代码中遗留的
print()调试输出 - rule_id:
debug-print
每个 finding 附带 location（文件 + 行号）与证据（代码片段）。
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 · 34 lines · 29 tokens per session scan A 53d81f1f3ca5
python-review is a skill published in the GitHub repository liuyanghejerry/Clausura (204 stars, last pushed 26d ago), licensed MIT. It adds 29 tokens to every session and 265 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 2026-08-30.
Other skills, from other repositories
setup-pre-commit
Use when bootstrapping or extending the pre-commit hook chain (Husky + lint-staged + Prettier + typecheck + integration tests) for an EVOKORE-style TypeScript repo, including detecting an existing setup, surfacing the diff, and never silently overwriting a configured chain.
quality-gate
Use when you need to check if current work meets quality thresholds before proceeding to the next phase or merging.
pull-request-feedback-loop
Handles PR review feedback by fetching comments, grouping issues, fixing one group at a time, and verifying before replies.
claude-c-suite-audit
Use when auditing or release-checking the Claude C-Suite plugin's own command conformance.
claude-c-suite-cto
Use for architecture, tech debt, refactoring, dependency, scaling, migration, and codebase health reviews.
claude-c-suite-dx-lead
Use for developer experience, API ergonomics, SDK usability, docs quality, onboarding, and error-message reviews.