Borrowing it
Nothing to install: this file belongs to HWYD/ai-mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HWYD/ai-mind/main/.agents/skills/ai-mind-step-audit/SKILL.mdgit clone --depth 1 https://github.com/HWYD/ai-mindWrote 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/hwyd/ai-mind/ai-mind-step-audit)<a href="https://agentmods.dev/skills/hwyd/ai-mind/ai-mind-step-audit"><img src="https://agentmods.dev/badge/skills/hwyd/ai-mind/ai-mind-step-audit/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/hwyd/ai-mind/ai-mind-step-audit"><img src="https://agentmods.dev/badge/skills/hwyd/ai-mind/ai-mind-step-audit.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 | $0.00139 | $0.03520 |
| Opus 5 | $0.00069 | $0.01760 |
| Sonnet 5 | $0.00028 | $0.00704 |
| Haiku 4.5 | $0.00014 | $0.00352 |
Grade A, and why
ai-mind-step-audit 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 10d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Mind Step Audit Skill
Skill 目标
使用本 Skill 审计 AI Mind 当前 specs task / tasklist step 的实现质量，辅助判断是否可以进入下一 Step。固定覆盖四类职责：
- Step 实现质量 Review
- 人工 Review 路线建议
- 关键代码讲解
- 是否可以进入下一 Step 的判断
重点判断：
- 是否符合当前 Step 目标
- 是否存在未完成项
- 是否实现了 Step 之外的内容
- 是否违反当前版本 Non-goals
- 是否破坏已有链路
- 是否存在 Agent / Resource / Tool / Stream / UI 风险
- 是否完成必要测试和验证
- 人工应该按什么顺序查看关键代码文件
- 本 Step 的核心实现链路是什么
- 是否可以进入下一 Step
Skill 不做什么
- 不直接继续实现下一 Step。
- 不自动修改代码，除非用户明确要求。
- 不扩大需求范围。
- 不替代人工最终验收。
- 不扫描无关目录做泛泛分析。
- 不根据猜测补项目背景。
- 不把 Codex Skill 和 AI Mind 产品运行时里的 Skill 混为一谈。
- 不默认以
docs/versions/、docs/releases/、docs/tasklists/公开展示文档作为 Review 事实来源。 - 不默认读取
private-folder/作为 Review 事实来源；它只用于用户明确要求回看草稿、历史过程或个人内部材料的场景。 - 不逐行讲解所有代码，只讲与当前 Step 强相关的关键实现链路。
- 不把受控 Agent 扩大成通用 Agent，除非当前正式 spec 明确允许。
必需输入
尽量要求调用者或当前 Codex 上下文提供：
- 当前版本号
- 当前 specs task / tasklist Step 原文
- 本 Step 的目标和完成标准
- 本轮改动摘要
- 修改文件列表
- 关键 diff 或相关代码
- 已执行命令和结果
specs/<version-topic>/spec.md中与本 Step 相关的目标、行为和 Non-goalsspecs/<version-topic>/plan.md中与本 Step 相关的路径、边界和验证策略specs/<version-topic>/tasks.md中对应 Step / taskspecs/<version-topic>/acceptance.md中对应验收标准specs/<version-topic>/decisions.md中相关决策- 相关 ADR 和 architecture docs
- 当前版本 Non-goals
- 希望重点 review 的风险点
如果缺少当前 Step 目标，不要泛泛 review；先提示需要补充 Step 上下文。
如果缺少测试结果，Review 中必须标记“验证不足”。
如果 Level C / D 变更无法找到对应 specs/，必须明确说明“缺少正式规格依据”，不要用 private-folder/ 草稿或公开展示文档替代正式 spec。
默认 Step 定位规则
如果用户没有明确指定某个 Step，默认尝试定位“最新已完成或当前待审 Step”：
- 优先使用用户明确提供的版本号、feature 名或 spec 路径，在
specs/<version-topic>/tasks.md中读取匹配任务。 - 如果用户没有提供版本号，可根据本轮 diff、README 当前版本、
AGENTS.md或最近修改的specs/推断候选 spec，并在 Audit 中说明这是推断依据。 - 在目标
tasks.md中选择序号最大的已完成或当前待审 Step。已完成 Step 以该 Step 范围内 checklist 均为[x]，或该 Step 的 review / verification 项已标记完成为主要信号。 - 如果最新 Step 与本轮 diff / 用户描述明显不一致，必须标记“Step 上下文存疑”，不要强行给出 PASS。
- 如果无法唯一定位当前 spec、tasklist 或最新 Step，必须先说明“缺少 Step 上下文”，并要求用户补充版本号、spec 路径或 Step 原文。
这个默认规则只用于 Step Audit 的上下文定位，不代表可以自动推进下一 Step，也不代表可以用 private-folder/ 或公开展示文档替代正式 specs。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 255 lines · 139 tokens per session scan A 29b932789b7a
ai-mind-step-audit is a skill published in the GitHub repository HWYD/ai-mind (19 stars, last pushed 2d ago), licensed MIT. It adds 139 tokens to every session and 3,520 once invoked, about $0.0007 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 skills, from other repositories
code-review-expert
Expert-level code review focusing on quality, security, performance, and maintainability. Use this skill for conducting thorough code reviews, identifying issues, and providing constructive feedback.
python-style
Validate Python code against style and architectural conventions.
go-proverbs
Validate Go code changes against Go Proverbs.
review
Review recent changes - run all validators and report status.
star-chamber
Multi-LLM craftsmanship council with live progress and debate mode for code review and design questions.
skill-author
Package and validate an existing skill draft for AutoVault when its frontmatter, resources, capabilities, or admission result need review.