菜单
PostToolUse hook — runs ruff security rules (`--select S`) on every `.py` you Edit/Write and forwards findings non-blockingly; fail-open, no manual invocation.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/muratovv/ai-hats --skill py-security-lint命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Backlog lifecycle on the `rack` CLI — create / ls / context / transition / plan-extract, with field edits via `--set` and hypotheses/proposals on the `rack hyp` / `rack proposal` groups. Use for any task lifecycle transition, backlog read, field edit, document, link, hypothesis, or proposal.
Maintainer-only quality gates — pre-push e2e+smoke to master, plus the ->merge and ->done gates on the two roads a card takes into it
Isolated development using git worktrees so the main branch stays clean. Use when starting any non-trivial task (execute state), doing parallel work on multiple tasks, making risky changes you might want to discard, or delegating to a sub-agent (automatic via ai-hats agent --isolation).
基于 SOC 职业分类
正在显示 SKILL.md
| name | py-security-lint |
| description | PostToolUse hook — runs ruff security rules (`--select S`) on every `.py` you Edit/Write and forwards findings non-blockingly; fail-open, no manual invocation. |
| ai_hats | {"runtime_hooks":{"PostToolUse":["[Truncated]"]}} |
| license | MIT |
Thin registration shell for a PostToolUse runtime-hook: after every agent
Edit/Write/MultiEdit of a .py, ruff's flake8-bandit security rules
(ruff check --isolated --select S) run on the file and any findings are
forwarded to the agent via non-blocking additionalContext. Defense-in-depth —
the project's CI lint stays the gate. Fail-open, kill switch
AI_HATS_SECURITY_LINT_OFF=1; full contract in the hook header:
hooks/py_security_lint.py.