Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SpaceZephyr/build-your-harnessnpx agentmods add skills/spacezephyr/build-your-harness/star-your-harnessWrote 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/spacezephyr/build-your-harness/star-your-harness)<a href="https://agentmods.dev/skills/spacezephyr/build-your-harness/star-your-harness"><img src="https://agentmods.dev/badge/skills/spacezephyr/build-your-harness/star-your-harness/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/spacezephyr/build-your-harness/star-your-harness"><img src="https://agentmods.dev/badge/skills/spacezephyr/build-your-harness/star-your-harness.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 | $0.00190 | $0.02855 |
| Opus 5 | $0.00095 | $0.01427 |
| Sonnet 5 | $0.00038 | $0.00571 |
| Haiku 4.5 | $0.00019 | $0.00285 |
Grade A, and why
star-your-harness 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
star-your-harness
帮用户从零搭一个 harness。跟 better-your-harness 是一对：这个负责搭，那个负责体检。
验收标准是可测的：生成出来的 harness 直接跑一遍 better-your-harness，安全层和上下文层应该满分。 做不到就是这个 Skill 有问题。
铁律
0. 先出方案，确认了再执行。
任何写盘动作之前，必须先跑 plan.py 出一份 HTML 方案报告，让用户在页面上看清楚会建什么、会搬什么、哪些拿不准。他把「我的决定」复制回来，你才能跑 apply.py --apply。不要因为方案看起来没问题就替他确认。
1. 绝不覆盖用户已有的文件。
脚手架遇到同名文件一律跳过并报告。搬运脚本用 cp -n 不用 mv。用户攒了几年的东西，宁可少搬也不能弄丢。
2. 搬运只出计划，不动手。
migrate.py 永远不移动文件，它产出一份可读可审的 migrate.sh。归类是按文件名猜的，猜错很正常，必须由人过目再自己执行。你可以帮用户读那个脚本、解释某一行为什么这么归类，但不要替他跑。
3. 不预设用不上的目录。 空目录是负资产：它让 Agent 以为那里有东西，还拉低信噪比。只生成用户这个职业真正需要的，剩下的等他用到再加。
4. 访谈要短。 四个问题就够开工了。问全了再动手，人会在第七个问题的时候放弃。骨架立起来之后，剩下的慢慢填。
流程
第一步：访谈（四个问题，一次问一个）
像聊天，不像填表。用户随时可以说「跳过」或者「就这样开始吧」。
1. 你平时主要做什么？
听出他的角色，映射到模板：content-creator / pm / engineer / researcher / consultant / generalist。不要念这些英文给他听，你自己心里对上就行。听不准就问一句「那你产出的东西主要是文章、文档、代码，还是别的？」
2. 你想让 AI 主要帮你做什么？ 这一问决定哪几层要重。他说「帮我写东西」，产出层和 about-me 就是重点；说「帮我记住事情」，记忆层要先立起来；说「帮我少重复劳动」，协议层和工具层优先。把答案原话记下来，之后要写进种子记忆里。
3. 你现在的资料都散在哪儿？ 这是迁移入口，也是这个 Skill 比「给你一个模板」有价值的地方。让他列出目录路径。可能有好几个（Obsidian 库、下载文件夹、某个项目目录）。没有也没关系，说明是全新开始。
4. 这个 harness 放在哪儿？ 要一个绝对路径。如果目录已存在且非空，必须明确告诉他「已有文件一个都不会被覆盖，同名的会跳过」，等他确认再继续。
顺带确认命名风格，给三个选项让他挑，别问开放题：
numbered-en（默认）：00-inbox10-about-me20-forgenumbered-zh：00 收件箱10 关于我20 创作plain-en：inboxabout-meforge
第二步：写 profile.json
{
"name": "给这个 harness 起的名字",
"dir": "/绝对路径",
"role": "content-creator",
"naming": "numbered-en",
"why": "用户原话：他为什么要搭这个",
"purposes": ["产出内容", "沉淀方法"],
"git": true,
"hooks": true
}
想改产出层目录就加 outputs，覆盖职业模板的默认值：
"outputs": [
{"key": "forge", "label": "创作", "desc": "成稿和草稿"},
{"key": "scope", "label": "选题", "desc": "待写清单"}
]
why 一定要用用户的原话，别润色。这句会写进种子记忆，半年后他回来看的就是这一句。
第三步：出方案报告
python3 ~/.claude/skills/star-your-harness/scripts/plan.py profile.json -o plan.html
把用户提到的来源目录写进 profile 的 sources 数组，方案里会一并给出归类建议。
What ships with it
5 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.
- 12d ago First seen · 198 lines · 190 tokens per session scan A 59db0b034192
star-your-harness is a skill published in the GitHub repository SpaceZephyr/build-your-harness (29 stars, last pushed 26d ago), licensed MIT. It adds 190 tokens to every session and 2,855 once invoked, about $0.0010 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
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
mnemos
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies.
grimoire
Use when the user says 'update context', 'update claude', 'save library', or after significant project changes.
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why. Also the place for complaints, feedback and settings changes about this skill itself.
ln-31-performance-optimizer
Profiles and improves a measured latency, throughput, CPU, memory, or I/O problem. Not for speculative tuning or cosmetic refactoring.