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 Basic-XYZ/baku-skills --skill baku-mind-cleanergit clone --depth 1 https://github.com/Basic-XYZ/baku-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/basic-xyz/baku-skills/baku-mind-cleaner)<a href="https://agentmods.dev/skills/basic-xyz/baku-skills/baku-mind-cleaner"><img src="https://agentmods.dev/badge/skills/basic-xyz/baku-skills/baku-mind-cleaner/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/basic-xyz/baku-skills/baku-mind-cleaner"><img src="https://agentmods.dev/badge/skills/basic-xyz/baku-skills/baku-mind-cleaner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00121 | $0.02282 |
| Opus 5 | $0.00060 | $0.01141 |
| Sonnet 5 | $0.00024 | $0.00456 |
| Haiku 4.5 | $0.00012 | $0.00228 |
Grade A, and why
baku-mind-cleaner 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 12d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baku Mind Cleaner
用于帮助用户从“需求和事项很多 / 思路很乱 / 不知道先做什么”的状态，进入“我知道现在该做哪一步”的状态。
核心目标不是一次性解决所有事情，也不是重新做需求分析，而是降低认知负担，把混乱内容变成清晰、可排序、可立即启动的下一步。
目标边界
使用本技能时，只做三件事：
- 把用户已经说出的需求、事项、担忧和依赖分门别类。
- 判断哪些现在该动、哪些需要补信息、哪些可以暂缓。
- 给出一个立刻能做的小动作，必要时再给 2-3 个后续动作。
不要把它扩展成：
- 完整项目管理、排期、路线图或 OKR。
- 复杂业务需求澄清、PRD 设计或系统方案评审。
- 个人状态评估或人生决策建议。
如果用户需要复杂需求澄清，转入需求分析类流程；如果用户已经明确要求编码、修 bug 或改文件，不要用本技能拖成整理会话。
工作原则
- 先判断输入状态，再决定是追问、整理还是直接给行动顺序。
- 先降低混乱感，再追求完整性；不要把整理本身变成新负担。
- 输出要具体到“下一步可以立刻做什么”。
- 优先找最小可行动作，而不是宏大计划。
- 对不确定信息标记为“需澄清”，不要假装确定。
- 默认短输出：先给 1 个立即动作，再给最多 3 个后续动作。
- 除非用户要求导出或复盘，不要输出大表格和长计划。
流程
1. 输入状态路由
先判断用户是否已经给出足够材料。
| 输入状态 | 处理方式 |
|---|---|
| 只说“很乱 / 不知道先做什么” | 邀请用户继续倒出事项，不要求有逻辑。 |
| 已经给出一大段内容 | 直接分类整理，不要求用户重新说一遍。 |
| 目标清晰但执行顺序乱 | 不重新讨论目标，只整理顺序、依赖和第一步。 |
| 明确要求导出待办或结构化数据 | 输出 JSON 或紧凑清单，不加解释性长文。 |
| 明确要求编码、调试、改文件 | 不触发本技能，直接进入对应工程流程。 |
可使用类似话术：
你先不用整理，直接把脑子里的东西都倒出来就行。我会帮你分类、排序、拆下一步。
如果用户只说了一部分，继续轻轻追问：
- “还有吗？”
- “还有什么一直挂在脑子里？”
- “有没有那种不急但一直消耗你的事？”
- “有没有你担心忘掉、但还没写下来的事？”
当用户表示“差不多了 / 没了 / 就这些”后，进入整理。不要连续追问超过两轮；材料不完整但足够启动时，直接给低风险下一步。
2. 分类整理
把用户内容拆成以下类别：
| 类别 | 含义 |
|---|---|
| 可行动 | 明确可以推进的事项 |
| 需澄清 | 因信息不足、目标不明或口径不清而无法推进的事项 |
| 等待依赖 | 需要别人回复、确认、交付或前置条件完成的事项 |
| 项目块 | 需要多个步骤才能完成的较大事项 |
| 噪音/担忧 | 占用注意力但暂时不能直接行动的担忧、风险或干扰 |
| 可暂缓 | 暂时不重要、可以延后或不处理的内容 |
整理时尽量用用户自己的语言，不要过度改写。
3. 识别优先级
对每个任务或项目，按以下维度判断优先级：
- 紧急性：有没有明确截止时间？是否马上会产生后果？
- 重要性：是否影响关键目标、收入、承诺、关系或关键项目？
- 阻塞性：不做它是否会卡住其他事情？
- 能量匹配：以用户当前状态，是否适合立刻做？
- 完成成本：能否在 5-30 分钟内完成一个小切口？
优先级使用四档：
| 优先级 | 定义 | 处理方式 |
|---|---|---|
| P0 | 今天必须处理，否则有明显后果 | 立即拆下一步 |
| P1 | 重要且会影响后续进展 | 今天或明天安排 |
| P2 | 有价值但不紧急 | 放入待办池 |
| P3 | 暂时不用处理或可以丢弃 | 暂存或删除 |
不要把所有内容都标成高优先级。
4. 排行动顺序
从所有事项中排出最小行动顺序。优先选择：
- 能解除多个阻塞的事
- 截止时间最近的事
- 做完能明显降低压力的事
- 5-15 分钟内能启动的事
- 当前能量状态下最容易开始的事
如果用户当前状态不适合高强度推进，优先推荐低成本启动动作。
5. 生成下一步行动
每个推荐动作必须满足：
- 动词开头
- 小到可以立刻开始
- 有明确完成标准
- 最好能在 5-30 分钟内推进
避免输出：
- “整理一下项目”
- “好好规划”
- “推进工作”
改成：
- “打开项目文档，列出还缺的 3 个信息”
- “给 A 发一条确认截止时间的消息”
- “把今天必须完成的事项写成 3 条待办”
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.
- 12d ago First seen · 250 lines · 121 tokens per session scan A 45419e246945
baku-mind-cleaner is a skill published in the GitHub repository Basic-XYZ/baku-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 2,282 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
inbox-zero
Scan your support inbox and batch-process tickets with quick actions (reply, tag, assign, close).
ticket-summarize
Summarize a support ticket thread into key points and action items.
weekly-digest
Generate a weekly support digest and post it to Slack.
zoho-desk-triage
Pull open tickets from Zoho Desk and triage by priority and department.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
37signals-way
Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…