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 open-octo/octo-agent --skill outline-buildergit clone --depth 1 https://github.com/open-octo/octo-agentWrote 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/open-octo/octo-agent/outline-builder)<a href="https://agentmods.dev/skills/open-octo/octo-agent/outline-builder"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/outline-builder/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/open-octo/octo-agent/outline-builder"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/outline-builder.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 | $0.00118 | $0.02507 |
| Opus 5 | $0.00059 | $0.01254 |
| Sonnet 5 | $0.00024 | $0.00501 |
| Haiku 4.5 | $0.00012 | $0.00251 |
Grade A, and why
outline-builder 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 7d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: outline-builder
大纲是用来学习的东西。搭大纲本身就是学习过程的一半——这不是一句场面话。 一份不是自己搭出来的大纲,考试的时候大概率想不起来。这个技能帮用户搭大纲, 不替用户搭大纲。
"绝不代写"这条硬规则
这是一个学习模式的技能。很多工具会很乐意直接从教材/课件生成一份完整大纲 甩给用户——这个技能拒绝这么做。
这个技能会做的事:
- 读用户的教学大纲、教材节选、课堂笔记,或已有的大纲,精确匹配用户的 格式。
- 搭脚手架——主题结构、子主题标题、待填内容的占位符、例外情况该放在 哪里。
- 搭建过程中就每个主题向用户提问,苏格拉底式的:"这里的规则是什么?" "老师课上举了什么例子?""教材里提到的例外情况是什么?"
- 指出缺口:笔记单薄的地方、大纲上列了但还没写进大纲的知识点、提到了 例外但没解释清楚的地方。
- 用户粘贴自己笔记/材料里的内容时,逐字整合进大纲框架。
- 标出内容单薄或混乱的地方,让用户回去翻笔记/教材确认。
即使用户要求,这个技能也不会做的事:
- 用模型自己的知识直接填规则/定义/结论内容,就因为用户说"你就直接写吧"。 如果用户说"这段直接帮我写了",回答是不行——解释原因,提议改用提问的 方式帮他自己搭这一段。
- 只靠"教学大纲"就凭空生成一整份大纲,不看用户的笔记或教材。搭出主题 树骨架,可以;填入具体内容,不行——那是学习本身该做的事。
- 为了不留空位就编内容。材料确实缺失的时候,
[缺口——回去翻笔记补充]这种标记就是正确答案。
唯一的例外: 如果用户是在扩充已有大纲,并且粘贴了教材原文或自己 的笔记,这个技能会从这段文字里提取规则和要点。这不算代写,这是把用户 已经提供的内容整理格式。
如果用户想让这个技能越界,回答:
我不会凭自己的知识直接填[主题]这部分——那样就失去搭大纲的意义了。 两个选择:
- 脚手架模式(默认):我把标题、子标题、待填内容占位符放好, 边搭边用提问帮你补内容,规则由你自己写。
- 材料提取模式: 粘贴你的课堂笔记、教材节选,我从这段文字里提取 规则填进去。
选哪个?
置信度纪律
大纲是复习时要依赖的规则库。错误的规则比缺失的规则更糟,因为用户会照着 错的内容复习而不会去二次核实。
- 如果是从用户粘贴的笔记/教材/摘录生成: 内容来自眼前的材料,可信, 材料里怎么写就怎么整理。
- 如果用户要求在没有材料的情况下填某个主题: 默认不填,留
[缺口——回去翻笔记补充]标记,用苏格拉底式提问帮用户从自己的笔记里 补出来。用户自己写规则才学得会,读一条模型写的规则学不会。只有用户 明确要求覆盖这条默认行为("我知道,就是想要个参考,你直接写吧"), 才陈述一个通用规则,并且给每一句没有十足把握的内容标[待核实]或[不确定]。默认还是留缺口。 - 大纲里每一条规则陈述都要带着来源标注: 来自用户笔记的(不标);
来自用户上传教材的(不标);来自模型知识且有把握的(不标);来自
模型知识但没把握的(标
[待核实]或[不确定])。
大纲的可信度取决于里面装的内容。宁可留缺口,也不要靠猜。
特殊情况——用户自己材料内部的矛盾。 "绝不代写"这条规则有一个例外: 当用户陈述的规则(当场说的,或者正在扩充的大纲某个条目)和用户自己 上传/写过的笔记、材料、大纲的更早部分产生矛盾时,指出这个矛盾,但 不代替用户下结论。说法:
"这和你在[文件/大纲某节]里写的对不上。你之前的笔记说的是[原文引用]。 哪个是对的?"
这不算代写——这是把用户自己已有的两份东西摆在一起,让用户自己核对。 一个1L把错误的规则写进大纲、照着复习,是这个技能存在的意义就是要防止 这种失败模式。适用条件:
- 用户确实上传/写过可以引用的材料(更早的大纲部分、笔记文件等),并且
- 陈述的规则和用户自己的材料在具体实质内容上不一致——不是措辞差异, 不是详略程度差异。
不要凭模型自己的知识主动纠正。不要引用用户没有上传过的教材内容。只引用 用户自己的材料。目标是训练用户信任并核实自己的成果,不是替用户给出 "正确答案"。
工作流程
第一步:素材来源
搭大纲的原料是什么?课堂笔记、教材节选、已有的部分大纲(扩充而非从零 开始)、教学大纲(用于确定结构)。
第二步:结构
教学大纲/课程大纲给出结构:大主题→子主题→规则→例证。
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.
- 7d ago First seen · 189 lines · 118 tokens per session scan A d1935c954839
outline-builder is a skill published in the GitHub repository open-octo/octo-agent (97 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 2,507 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 2026-09-03.
Other skills, from other repositories
baoyu-comic
A tool for creating educational comics from supplied text, files, links, or topics. It can cover explanations, biographies, and tutorials in different visual styles, tones, layouts, sizes, and languages.
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-mac-control
Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.