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 hydah/thequeen --skill scratchgit clone --depth 1 https://github.com/hydah/thequeenWrote 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/hydah/thequeen/scratch)<a href="https://agentmods.dev/skills/hydah/thequeen/scratch"><img src="https://agentmods.dev/badge/skills/hydah/thequeen/scratch/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/hydah/thequeen/scratch"><img src="https://agentmods.dev/badge/skills/hydah/thequeen/scratch.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 | $0.00133 | $0.01075 |
| Opus 5.5 | $0.00053 | $0.00430 |
| Sonnet 5.5 | $0.00027 | $0.00215 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
scratch 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 2mo 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
Scratch
Overview
低门槛的临时信息捕获区。核心解决两个问题：不丢东西和被定期消化。
与 todo/ 的区别：
- todo 是行动承诺（"我要做这件事"），scratch 是信息捕获（"我注意到了这个"）
- todo 有优先级和完成状态，scratch 只有"待处理/已处理"
- scratch 条目可以升级为 todo，也可以升级为 question/tech/issue/decision 等正式实例
单文件设计：scratch/scratch.md——不用想文件名，一屏看完所有待处理项，因为有消化机制不会无限膨胀。
When to Use
- 用户随口提到一个问题，但还不值得开
question/ - 用户有个临时想法或灵感，还没想清楚
- 用户观察到某个现象，不是 todo 也不是 issue，但应该记下来
- 用户说"记一下"、"想到个事"、"有个问题"、"有个想法"等
不应触发本 skill 的场景：
- 用户明确说"加个 todo" → 路由到
personal-todo - 用户有明确的结构化问题要分析 → 路由到
question/或deep-questioner
Workspace Contract
- 速记文件固定为
scratch/scratch.md - 不创建其他文件（条目升级后，正式文档创建在目标目录）
- 两个分区：
## 待处理和## 已处理 - 每条速记格式：
- YYYY-MM-DD | 🏷️ 一句话描述💡想法/灵感❓问题/疑问👀观察/信号🔗线索/参考💭随想/杂念
Workflow
Step 1: 判断操作类型
| 意图 | 操作 |
|---|---|
| 空参数 / "看看" | 查看速记 |
| 一句话描述 | 添加速记 |
| "升级" / "展开" | 升级速记为正式文档 |
| "丢弃" / "不要了" | 丢弃速记 |
| "清理" | 批量清理 |
Step 2: 添加速记
- 自动判断类型标签（含"?"→❓，含"可以/如果"→💡，含"发现/注意到"→👀，含"链接/文章"→🔗，其他→💭）
- 在
## 待处理区末尾追加 - 使用当前日期
Step 3: 升级速记
- 匹配待处理区的目标条目
- 判断升级方向（question/tech/issue/decision/todo/playbook）
- 创建正式文档（如有模板则使用）
- 建立双向链接：scratch 中记录
→ [[目标文档路径]]，目标文档标注来源 - 将条目从"待处理"移到"已处理"
Step 4: 丢弃速记
将条目移到"已处理"，标注 → 已丢弃：<原因>
Step 5: 批量清理
- 读取所有待处理条目
- 标出超过 7 天未处理的条目
- 逐条建议：升级 / 丢弃 / 保留
Editing Rules
- 修改前必须先读取目标文件
- 优先使用当前 AI 工具提供的最小粒度编辑能力做精确修改
- scratch skill 只允许写
scratch/scratch.md - 升级操作创建的正式文档遵循目标目录的命名约定
- 不创建临时文件、备份文件
- 不要整文件覆盖已有的
scratch/scratch.md
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.
- 2mo ago First seen · 89 lines · 133 tokens per session scan A 3908e3eaa15f
scratch is a skill published in the GitHub repository hydah/thequeen (2 stars, last pushed 6mo ago), licensed MIT. It adds 133 tokens to every session and 1,075 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.