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 commands/luohaothu/everything-codex/python-reviewgit clone --depth 1 https://github.com/Luohaothu/everything-codexWhat 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 | $0.00032 | $0.01821 |
| Opus 5 | $0.00016 | $0.00911 |
| Sonnet 5 | $0.00006 | $0.00364 |
| Haiku 4.5 | $0.00003 | $0.00182 |
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 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python 代码审查
此命令调用 python-reviewer 代理进行全面的 Python 专项代码审查。
此命令的功能
- 识别 Python 变更:通过
git diff查找修改过的.py文件 - 运行静态分析:执行
ruff、mypy、pylint、black --check - 安全扫描:检查 SQL 注入、命令注入、不安全的反序列化
- 类型安全审查:分析类型提示和 mypy 错误
- Pythonic 代码检查:验证代码是否遵循 PEP 8 和 Python 最佳实践
- 生成报告:按严重程度对问题进行归类
使用时机
在以下情况使用 /python-review:
- 编写或修改 Python 代码后
- 提交 Python 变更前
- 审查包含 Python 代码的拉取请求时
- 接手新的 Python 代码库时
- 学习 Pythonic 模式和惯用法时
审查类别
关键 (必须修复)
- SQL/命令注入漏洞
- 不安全的 eval/exec 使用
- Pickle 不安全反序列化
- 硬编码的凭证
- YAML 不安全加载
- 隐藏错误的裸 except 子句
高 (应该修复)
- 公共函数缺少类型提示
- 可变默认参数
- 静默吞掉异常
- 未对资源使用上下文管理器
- 使用 C 风格循环而非推导式
- 使用 type() 而非 isinstance()
- 无锁的竞态条件
中 (考虑)
- 违反 PEP 8 格式规范
- 公共函数缺少文档字符串
- 使用 print 语句而非 logging
- 低效的字符串操作
- 未使用命名常量的魔法数字
- 未使用 f-strings 进行格式化
- 不必要的列表创建
运行的自动化检查
# Type checking
mypy .
# Linting and formatting
ruff check .
black --check .
isort --check-only .
# Security scanning
bandit -r .
# Dependency audit
pip-audit
safety check
# Testing
pytest --cov=app --cov-report=term-missing
使用示例
User: /python-review
Agent:
# Python Code Review Report
## Files Reviewed
- app/routes/user.py (modified)
- app/services/auth.py (modified)
## Static Analysis Results
✓ ruff: No issues
✓ mypy: No errors
⚠️ black: 2 files need reformatting
✓ bandit: No security issues
## Issues Found
[CRITICAL] SQL Injection vulnerability
File: app/routes/user.py:42
Issue: User input directly interpolated into SQL query
```python
query = f"SELECT * FROM users WHERE id = {user_id}" # Bad
修复:使用参数化查询
query = "SELECT * FROM users WHERE id = %s" # Good
cursor.execute(query, (user_id,))
[高] 可变默认参数 文件:app/services/auth.py:18 问题:可变默认参数导致共享状态
def process_items(items=[]): # Bad
items.append("new")
return items
修复:使用 None 作为默认值
def process_items(items=None): # Good
if items is None:
items = []
items.append("new")
return items
[中] 缺少类型提示 文件:app/services/auth.py:25 问题:公共函数缺少类型注解
def get_user(user_id): # Bad
return db.find(user_id)
修复:添加类型提示
def get_user(user_id: str) -> Optional[User]: # Good
return db.find(user_id)
[中] 未使用上下文管理器 文件:app/routes/user.py:55 问题:异常时文件未关闭
f = open("config.json") # Bad
data = f.read()
f.close()
修复:使用上下文管理器
with open("config.json") as f: # Good
data = f.read()
摘要
- 关键:1
- 高:1
- 中:2
建议:❌ 在关键问题修复前阻止合并
所需的格式化
运行:black app/routes/user.py app/services/auth.py
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 · 321 lines · 32 tokens per session scan A f853da10b147
python-review is a command published in the GitHub repository Luohaothu/everything-codex (24 stars, last pushed 21d ago), licensed MIT. It adds 32 tokens to every session and 1,821 once invoked, about $0.0002 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.