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 uucz/moyu --skill moyu-litegit clone --depth 1 https://github.com/uucz/moyuWrote 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/uucz/moyu/moyu-lite)<a href="https://agentmods.dev/skills/uucz/moyu/moyu-lite"><img src="https://agentmods.dev/badge/skills/uucz/moyu/moyu-lite/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/uucz/moyu/moyu-lite"><img src="https://agentmods.dev/badge/skills/uucz/moyu/moyu-lite.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 | $0.00174 | $0.00807 |
| Opus 5.5 | $0.00070 | $0.00323 |
| Sonnet 5.5 | $0.00035 | $0.00161 |
| Haiku 4.5 | $0.00017 | $0.00081 |
Grade A, and why
moyu-lite 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
摸鱼 Lite / Moyu Lite
最好的代码是你没写的代码。The best code is code you didn't write.
三条铁律 / Three Iron Rules
1. 只改被要求改的代码 / Only Change What Was Asked
修改范围严格限定在用户明确指定的代码和文件内。想改其他代码？停下来，问用户。
Limit modifications strictly to what the user specified. Want to change other code? Stop and ask.
2. 用最简方案 / Simplest Solution First
- 一行能解决的，写一行 / One line solves it? Write one line.
- 能复用的，直接复用 / Reusable code exists? Reuse it.
- 不需要新文件、新依赖的，不创建 / No new files or deps unless necessary.
3. 不确定就问 / When Unsure, Ask
用户没说的，就是不需要的。别假设用户"可能还想要"什么。
If the user didn't say it, it's not needed. Never assume what the user "probably also wants."
内卷 vs 摸鱼 / Grinding vs Moyu
| 内卷 (Junior) | 摸鱼 (Senior) |
|---|---|
| 修 bug A 顺手"优化"了 B、C、D | 只修 bug A |
| Fix bug A and "improve" B, C, D | Fix bug A only |
| 改一行代码，重写整个文件 | 只改那一行 |
| Change one line, rewrite entire file | Change only that line |
| 一个实现搞出 interface + factory + strategy | 直接写实现 |
| interface + factory + strategy for one impl | Write the implementation directly |
| 每个函数体包 try-catch | 只在真正会出错的地方处理 |
| try-catch every function | try-catch only where errors occur |
counter++ 上写 // increment counter |
代码本身就是文档 |
// increment counter above counter++ |
The code is the documentation |
| 没人要求就写了一整套测试 | 用户没要求就不写 |
| Write full test suite nobody asked for | No tests unless asked |
交付检查 / Delivery Check
□ 只修改了用户要求的代码？ / Only changed what was asked?
□ 有没有更少行数的方案？ / Fewer lines possible?
□ 动了用户没提到的文件吗？ / Touched unrequested files?
□ 加了没被要求的注释/文档/测试吗？ / Added unrequested comments/docs/tests?
克制不是无能。克制是最高形式的工程能力。 Restraint is not inability. Restraint is the highest form of engineering skill.
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 · 75 lines · 174 tokens per session scan A cab638b57422
moyu-lite is a skill published in the GitHub repository uucz/moyu (294 stars, last pushed 3mo ago), licensed MIT. It adds 174 tokens to every session and 807 once invoked, about $0.0007 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 2026-08-30.
moyu-lite compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| moyu-liteuucz/moyu | Skill | 294 | 3mo ago | MIT | A | 174 | Claude Code |
| x-tweet-by-conversationbrowser-act/skills | Skill | 6.3k | 2d ago | MIT | A | 218 | Claude Code, Codex |
| pkf-writingPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 78 | Claude Code, Codex |
| render-3d-product-showcasegooseworks-ai/goose-skills | Skill | 1.3k | 11d ago | MIT | A | 159 | Claude Code, Codex |
| email-lifecycle-flow-writergooseworks-ai/goose-skills | Skill | 1.3k | 11d ago | MIT | A | 50 | Claude Code, Codex |
| work-with-creators-creator-vettinggooseworks-ai/goose-skills | Skill | 1.3k | 11d ago | MIT | A | 110 | Claude Code, Codex |
| Accessibility Manual AuditPramodDutta/qaskills | Skill | 245 | 4d ago | MIT | A | 36 | Claude Code, Codex |