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 protect-my-hair/nucleus-marketplace --skill using-nucleusgit clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplaceWrote 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/protect-my-hair/nucleus-marketplace/using-nucleus)<a href="https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/using-nucleus"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/using-nucleus/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/protect-my-hair/nucleus-marketplace/using-nucleus"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/using-nucleus.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 | $0.00075 | $0.01125 |
| Opus 5 | $0.00037 | $0.00562 |
| Sonnet 5 | $0.00015 | $0.00225 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
using-nucleus 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Nucleus
核心规则
在任何 Nucleus V2 工作开始前使用本 Skill：它只建立入口纪律，不实现具体 workflow，不替代具体 Skill，不调用 V1 命令。Nucleus 是 coding agent 内部插件 / 脚手架，任何 Nucleus 需求、设计、特性、缺陷、测试、交付、setup 或 PMS 协作任务，都必须先进入最具体的 Skill，再按该 Skill 的门禁执行。
如何加载 Skill
- 先读目标仓库
AGENTS.md，以仓库规则作为最高事实源。 - Claude Code：使用
Skilltool 加载 Nucleus Skill；如果通过/ac:*command 进入，也必须继续读取对应 Skill 正文。 - Codex：使用已安装 plugin 暴露的 Skills 加载 Nucleus Skill；没有
/ac:*command 时，直接使用 Skill 入口。 - 其他 coding agent：按宿主文档加载已安装的 Nucleus Skill。
- 如果 Skill 提到的工具名和当前宿主工具不一致，读取
references/<host>-tools.md做工具映射。 - 根据用户请求、PMS context 或本地 context 找到最具体的 Nucleus Skill。
- 识别到具体 workflow 后，必须加载对应 Skill，必须读取该 Skill 正文，并按它的 HARD-GATE、STOP、Checklist、写入边界和验证要求执行。
- 当前无法确认具体 Skill 时，只说明缺少哪些上下文并停住；不得猜一个 workflow 继续执行。
- 用户要求“先简单看一下”“先跑一下脚本”“先生成个候选”时，仍然要先完成入口识别和目标 Skill 加载。
- 当用户请求模糊、需要在多个 workflow 间选择时，按
_shared/references/interaction-format.md的选择型格式呈现候选 workflow 和推荐，不要用散文堆问题。
宿主任务与预审
- 目标 Skill 含
## Checklist或 Task / Todo 执行纪律时，必须先创建宿主 todo/task 并逐项更新状态；细则见references/checklist-discipline.md。.nucleus/runs/**、.nucleus/tests/**、.nucleus/**证据、summary、result、candidate、review report 只能记录事实，不能替代宿主任务、人工选择、人工评审或 PMS 状态。 - 到达任何人工审查点前，必须先按
_shared/references/subagent-precheck-protocol.md调度独立 reviewer 子代理执行subagentPreReview；未取得”材料可提交人工审查”结论前，不得询问用户”是否评审通过”。
红旗
出现以下想法时必须停住，回到入口识别或目标 Skill 正文：
| 想法 | 必须改成 |
|---|---|
| “先跑 runtime 看看” | 先完成入口识别并加载目标 Skill |
| “先写一个候选文件” | 先确认目标 Skill 允许的候选阶段和 STOP 点 |
| “我知道该怎么做，可以不读目标 Skill” | 读取目标 Skill 正文并按其行为纪律执行 |
| “summary/result 已经生成，可以继续下游” | 检查宿主任务、人工事实和 gate 证据 |
| “候选文件里有推荐答案，就按推荐继续” | 推荐不是授权，等待明确回复或审批事实 |
| “这是简单 Nucleus 任务，不需要建 todo/task” | 只要目标 Skill 有 Checklist 或 Task / Todo 执行纪律，就必须创建宿主任务 |
What ships with it
3 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 · 54 lines · 75 tokens per session scan A bfd174e08dbd
using-nucleus is a skill published in the GitHub repository protect-my-hair/nucleus-marketplace (162 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,125 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…