superpowers-zh is a Chinese community edition of superpowers, a collection of practical skills and development methods for AI coding tools. It helps users apply workflows such as brainstorming, test-driven development, debugging, code review, and other programming tasks across supported coding agents. The catalogue add-ons are the project's translated and original skills, instructions, hook, and plugin components.
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/jnMetaCode/superpowers-zhnpx agentmods add skills/jnmetacode/superpowers-zh/subagent-driven-developmentWrote 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/jnmetacode/superpowers-zh/subagent-driven-development)<a href="https://agentmods.dev/skills/jnmetacode/superpowers-zh/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/jnmetacode/superpowers-zh/subagent-driven-development/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/jnmetacode/superpowers-zh/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/jnmetacode/superpowers-zh/subagent-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 124 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00021 | $0.09207 |
| Opus 5.5 | $0.00008 | $0.03683 |
| Sonnet 5.5 | $0.00004 | $0.01841 |
| Haiku 4.5 | $0.00002 | $0.00921 |
Grade C, and why
subagent-driven-development scanned grade C with 1 finding 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 23d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
当覆盖整个分支的最终审查干净、且它的修复已合并时,删除**本计划**的工作区(`rm -rf <工作区>`)——现在 git 历史就是记录了。同级目录属于别的计划,别去动它们。 How it starts
The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
子智能体驱动开发
通过为每个任务分派一个全新的实现子智能体来执行计划:每个任务完成后做一次任务审查(规格合规性 + 代码质量),全部任务结束后再做一次覆盖整个分支的宽范围审查。
为什么用子智能体: 你把任务委派给具有隔离上下文的专用智能体。通过精心设计它们的指令和上下文,确保它们专注并成功完成任务。它们绝不应继承你会话的上下文或历史记录——你要精确构造它们所需的一切。这样也能为你自己保留用于协调工作的上下文。
核心原则: 每个任务一个全新子智能体 + 任务审查(规格 + 质量)+ 结尾宽范围审查 = 高质量、快速迭代
旁白: 工具调用之间最多说一句简短的旁白——进度账本和工具结果本身就是记录。
持续执行: 不要在任务之间停下来向你的人类伙伴确认。不间断地执行计划里的所有任务。唯一该停下的理由是:你无法解决的 BLOCKED 状态、确实妨碍推进的歧义,或所有任务已完成。"我该继续吗?"之类的询问和进度小结都在浪费他们的时间——他们让你执行计划,那就执行。
做裁决,不要停摆。 一个正在跑的计划不等人。冲突、歧义、计划缺陷、你本来想申请突破的上限——你自己定。规格是有约束力的权威,计划是它的论证,两者都答不上来的部分由你的判断来定。每个决定都以 Ruling: <你决定了什么> — <为什么> — <如果错了代价是什么> 记进账本,然后继续。一个错误的裁决,代价是你人类伙伴看得见、也撤得掉的返工;一个停在问题上的会话,代价是他们的一整天,而且什么也换不来。
只有四件事会让你停下,也只有这四件:不可逆或破坏性的操作;涉及安全的动作;这个工作树之外、按惯例应当先问一声的副作用(合并、推送到共享分支、发布);以及一个坏到每条前进路径都只能靠猜的计划。遇到这四类,停下来问。
何时使用
digraph when_to_use {
"有实现计划?" [shape=diamond];
"任务基本独立?" [shape=diamond];
"伙伴选了内联执行,或没有子智能体工具?" [shape=diamond];
"subagent-driven-development" [shape=box];
"executing-plans" [shape=box];
"手动执行或先头脑风暴" [shape=box];
"有实现计划?" -> "任务基本独立?" [label="是"];
"有实现计划?" -> "手动执行或先头脑风暴" [label="否"];
"任务基本独立?" -> "伙伴选了内联执行,或没有子智能体工具?" [label="是"];
"任务基本独立?" -> "手动执行或先头脑风暴" [label="否 - 紧密耦合"];
"伙伴选了内联执行,或没有子智能体工具?" -> "executing-plans" [label="是"];
"伙伴选了内联执行,或没有子智能体工具?" -> "subagent-driven-development" [label="否"];
}
与 Executing Plans(内联执行)的对比:
- 每个任务一个全新子智能体(无上下文污染),而不是一个上下文包揽所有任务
- 每个任务后做审查(规格合规性 + 代码质量),而不是只在结尾审查
- 代价是每个任务、每次审查各一个全新上下文;内联执行的代价是一个上下文加一个最终审查者
- 两者都在当前会话里运行,共用同一个计划工作区和账本,任务之间都不停顿
流程
digraph process {
rankdir=TB;
subgraph cluster_per_task {
label="每个任务";
"分派实现子智能体 (./implementer-prompt.md)" [shape=box];
"实现者有疑问?" [shape=diamond];
"回答问题,提供上下文" [shape=box];
"实现者实现、测试、提交、自审" [shape=box];
"生成审查包,分派任务审查者 (./task-reviewer-prompt.md)" [shape=box];
"规格 ✅ 且质量通过?" [shape=diamond];
"发现与计划原文冲突?" [shape=diamond];
"对冲突作出裁决, 把裁决记进账本" [shape=box];
"第 R/5 轮修复: R≤3 唤回原实现者; R≥4 换全新实现者 + 更强模型" [shape=box];
"分派定向复审 (./re-review-prompt.md)" [shape=box];
"所有发现都已解决?" [shape=diamond];
"R = 5?" [shape=diamond];
"逐条裁定未解决的发现" [shape=box];
"存在承重的发现?" [shape=diamond];
"裁决并继续; 只有每条路都靠猜时才停" [shape=box];
"把发现连同裁定搁置进账本" [shape=box];
"往账本追加完成行,标记待办完成" [shape=box];
}
"准备: 工作树、查账本、读计划、起飞前审查" [shape=box];
"还有任务?" [shape=diamond];
"分派最终代码审查者 (../requesting-code-review/code-reviewer.md)" [shape=box];
"最终审查有发现? 一次修复分派、一次定向复审、裁定残留项" [shape=box];
"最终审查干净: 删除本计划的工作区" [shape=box];
"使用 finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];
"准备: 工作树、查账本、读计划、起飞前审查" -> "分派实现子智能体 (./implementer-prompt.md)";
"分派实现子智能体 (./implementer-prompt.md)" -> "实现者有疑问?";
"实现者有疑问?" -> "回答问题,提供上下文" [label="是"];
"回答问题,提供上下文" -> "实现者实现、测试、提交、自审";
"实现者有疑问?" -> "实现者实现、测试、提交、自审" [label="否"];
"实现者实现、测试、提交、自审" -> "生成审查包,分派任务审查者 (./task-reviewer-prompt.md)";
"生成审查包,分派任务审查者 (./task-reviewer-prompt.md)" -> "规格 ✅ 且质量通过?";
"规格 ✅ 且质量通过?" -> "往账本追加完成行,标记待办完成" [label="是"];
"规格 ✅ 且质量通过?" -> "发现与计划原文冲突?" [label="否"];
"发现与计划原文冲突?" -> "对冲突作出裁决, 把裁决记进账本" [label="是"];
"对冲突作出裁决, 把裁决记进账本" -> "第 R/5 轮修复: R≤3 唤回原实现者; R≥4 换全新实现者 + 更强模型";
"发现与计划原文冲突?" -> "第 R/5 轮修复: R≤3 唤回原实现者; R≥4 换全新实现者 + 更强模型" [label="否"];
"第 R/5 轮修复: R≤3 唤回原实现者; R≥4 换全新实现者 + 更强模型" -> "分派定向复审 (./re-review-prompt.md)";
"分派定向复审 (./re-review-prompt.md)" -> "所有发现都已解决?";
"所有发现都已解决?" -> "往账本追加完成行,标记待办完成" [label="是"];
"所有发现都已解决?" -> "R = 5?" [label="否"];
"R = 5?" -> "第 R/5 轮修复: R≤3 唤回原实现者; R≥4 换全新实现者 + 更强模型" [label="否 - 进入下一轮"];
"R = 5?" -> "逐条裁定未解决的发现" [label="是 - 熔断触发"];
"逐条裁定未解决的发现" -> "存在承重的发现?";
"存在承重的发现?" -> "裁决并继续; 只有每条路都靠猜时才停" [label="是"];
"存在承重的发现?" -> "把发现连同裁定搁置进账本" [label="否"];
"把发现连同裁定搁置进账本" -> "往账本追加完成行,标记待办完成";
"往账本追加完成行,标记待办完成" -> "还有任务?";
"还有任务?" -> "分派实现子智能体 (./implementer-prompt.md)" [label="是"];
"还有任务?" -> "分派最终代码审查者 (../requesting-code-review/code-reviewer.md)" [label="否"];
"分派最终代码审查者 (../requesting-code-review/code-reviewer.md)" -> "最终审查有发现? 一次修复分派、一次定向复审、裁定残留项";
"最终审查有发现? 一次修复分派、一次定向复审、裁定残留项" -> "最终审查干净: 删除本计划的工作区";
"最终审查干净: 删除本计划的工作区" -> "使用 finishing-a-development-branch";
}
What ships with it
6 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.
- 23d ago Changed 9e3fc7a6089f
- 1mo ago Changed · +14 lines 0cb59782ed80
- 1mo ago Changed bc9d209b4fd3
- 1mo ago First seen · 342 lines · 21 tokens per session scan C 27081029a6b0
subagent-driven-development is a skill published in the GitHub repository jnMetaCode/superpowers-zh (8,362 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 9,207 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cocos-creator-hotupdate
A guide to updating a Cocos Creator game's scripts, resources, or settings after release, without submitting a new app-store version. It covers version files, partial downloads, checks, and rollback.
cocos-creator-tween-anim
Guidance for creating and managing animations in Cocos Creator, a game-development tool. It covers tweens, frame and Spine skeletal animations, performance, and cleanup when objects are destroyed.
cocos-creator-adaptation
A guide to making a Cocos Creator interface fit different phones, tablets, screen sizes, orientations, and notched displays. It covers the design resolution, layout anchoring, and safe areas where system UI does not cover the screen.
cocos-creator-bundle
A guide to splitting a Cocos Creator game into separately loaded resource bundles. A bundle is a packaged group of files, such as a scene, interface, sound, or shared resource.
cocos-creator-drawcall
A set of performance rules for Cocos Creator games focused on reducing draw calls, the number of separate rendering operations performed for a frame.
cocos-creator-ui-list
A Cocos Creator method for displaying long lists efficiently in games. Cocos Creator is a game-development tool, and a virtual list creates only the rows currently visible instead of every row.