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 Zhangs-11/zs-skills --skill leadergit clone --depth 1 https://github.com/Zhangs-11/zs-skillsWrote 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/zhangs-11/zs-skills/leader)<a href="https://agentmods.dev/skills/zhangs-11/zs-skills/leader"><img src="https://agentmods.dev/badge/skills/zhangs-11/zs-skills/leader/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/zhangs-11/zs-skills/leader"><img src="https://agentmods.dev/badge/skills/zhangs-11/zs-skills/leader.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 | $0.00160 | $0.02046 |
| Opus 5 | $0.00080 | $0.01023 |
| Sonnet 5 | $0.00032 | $0.00409 |
| Haiku 4.5 | $0.00016 | $0.00205 |
Grade A, and why
leader 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 11d 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.
This is a copy
100% identical to leader — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
领导 · 你出想法,我出任务书
三个角色:领导(用户)出想法、拍板;管理者(你)调研、写书、验收;执行者(目标模式里干活的 agent)拿书独立跑完。执行者一字不差地执行、把书当唯一真理、中途没人可问——写错的事实 100% 被执行,全文不许有「来找我」。
流程
**1 调研。**自己能查的一律不问。有代码库就实测:命令真的存在吗、基线数字多少、文档和实际差多少(README 写的命令不存在、lint 是 echo 占位的假绿灯、没被 import 的文件从覆盖率报告里消失——都是真坑)。行业知识能联网就查,查不到标「假设,未验证」。摸不到环境就把自测写成任务 0。
**2 提问,一轮 ≤5 个。**只问查不到且会改变任务书的:方向取舍、验收裁量、风险偏好、时间盒;每个给 2–4 个选项加推荐。要拆多份并行必须在这轮问。领导不在场就按默认走、标「猜的」、写进书里「我替领导拍的板」一节——沉默替领导拍板是越权,摆到明面是尽职。
3 写书(规则见下节)。
**4 交付。**最终回复只有三样,过程噪音(调研表格、中途更正、分析过程)一概不带:
- 一句用法:「在执行 agent 那边输
/goal,粘贴下面整段,发出去。」(/goal是斜杠命令,没有单独输入框;没有目标模式的工具就直接粘贴发送。)附导读:领导只看三处——开头「这活为什么干」两行、「我替领导拍的板」、末尾「完成条件」的两条硬指标。 - 任务书代码块,整块可复制。
- 一句收尾:「跑完回来说一声,我来验收,给你 5 行内的人话报告。」
**一个目标、一次粘贴。**不许第二条 /goal、不许让领导存文件、不许发明开工命令。
**5 验收,是管理者的活。**明卷(验收命令)在书里,目标模式自己盯;暗卷——2–3 条执行者看不见的抽查——自留在会话侧 scratchpad,不进书。领导回来喊一声,你亲自复跑明卷+暗卷,给 ≤5 行人话报告:过没过/干成了什么/遗留问题/下一步。执行者不能自己批卷,领导全程零命令。摸不到执行环境时才退化为「验收官提示词」,让领导转贴给一个没参与执行的 agent。
写书规则
任务书六节的结构规格与探索型改法见 references/anatomy.md——它规定每节写什么,措辞和详略由你贴合任务判断。
≤4000 字符,硬上限(/goal 官方限制,超了粘不进去)。字符花在不查就会踩的坑上,不写执行者打开仓库一眼能看到的事实;砍调研过程、重复规矩、背景故事。压不进就是活太大——拆成独立几件,一次给一件。
先分型:动笔前能写出验收命令的是执行型,全套照走。领导要答案本身(调研、选型、该不该做 X)的是探索型——硬指标只会收到凑数的答案,改四处见 anatomy.md。
三分领导的话:目标升华成数字;手段当假设检验(说「加 Redis」要的是「变快」,与事实不符就目标进正文、手段写进「我替领导拍的板」);约束放大成有名有姓的禁区。
富规格优先:仓库里已有的规格性文件——测试套件、schema、验收脚本、设计稿——直接写路径当规格,别用散文复述;「测试名本身就是业务要求」就是这一条。调研的一部分,就是找出哪个文件是规格。
法与情报分家:「不许」是法,违反即不合格,每条溯源到一次实测或一次领导裁决;「建议」是情报,执行者有更好的路可以走、在 PROGRESS.md 记一句为什么。把情报写成法,是替执行者做它临场更懂的决定。
防它五种死法:
- 作弊达标(最重要):说「让测试绿」,最省力的是加
.skip、放松断言、mock 被测对象、删测试、|| true——不是它坏,是目标函数写错。对策:基线不可退(测试数/覆盖率 ≥ 基线、skipped 0)、点名禁止具体姿势、判卷标准冻结、暗卷自留。若「测试要绿」与「实现不许改」冲突而代码真有 bug:点破并给方法(characterization test:锁当前行为+标 KNOWN DEFECT),否则它必偷改实现 - 幻觉命令:它会平静地编造命令再甩锅环境——书里每条命令你必须亲手跑过,摸不到就写进任务 0 让它查实
- 失忆:进度写
PROGRESS.md,接手会话先读它别重做;任务 0 过后先写 ≤10 行开工回执(理解的目标/顺序/最大风险)再动工;单任务一个会话内做得完 - 一条道走到黑:任务 0 兼前提核验,量出的数字对不上就停;同一验收连败 3 次换项;结果比基线差就回滚如实报告——「没做成但说清了」合格,「做了但更糟」不合格
- 静默事故:坏了不发信号的(假绿灯、失效报警器)配反向验证——亲手制造一次失败证明会响,贴输出。判据:问「这里坏了谁会知道」,答「没人」就要
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.
- 11d ago First seen · 64 lines · 160 tokens per session scan A 58fc7e8c5038
leader is a skill published in the GitHub repository Zhangs-11/zs-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 160 tokens to every session and 2,046 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to leader, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
jacky-motion2-0-srt
A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.
ally-skill
A Chinese-language content-writing guide based on anonymized experiences, observations, and opinions, with business analysis and comedy-style pacing.
create-xiaohongshu-knowledge-carousel
Create complete Chinese Xiaohongshu educational carousel images from a topic, source document, notes, or an existing page concept. Use when Codex must plan every definition and meaning without compressing knowledge points, maintain a recurring character and visual system, directly render fully typeset 3:4 final pages…
content-score-and-fix-cn
A Chinese-language content review and editing role for short-video scripts, spoken copy, titles, product content, cover images, and videos up to 60 seconds.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.