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/willnie9/agent-skillsnpx agentmods add skills/willnie9/agent-skills/module-flowWrote 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/willnie9/agent-skills/module-flow)<a href="https://agentmods.dev/skills/willnie9/agent-skills/module-flow"><img src="https://agentmods.dev/badge/skills/willnie9/agent-skills/module-flow/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/willnie9/agent-skills/module-flow"><img src="https://agentmods.dev/badge/skills/willnie9/agent-skills/module-flow.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 | $0.00162 | $0.05530 |
| Opus 5.5 | $0.00065 | $0.02212 |
| Sonnet 5.5 | $0.00032 | $0.01106 |
| Haiku 4.5 | $0.00016 | $0.00553 |
Grade A, and why
module-flow 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 1mo 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 — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Module-Flow · 全流程编排器
本 skill 调度所有下游 skill。所有项目结构信息从
.claude/skills/project.config.json读取,<config.xxx>占位指向该配置。
入口决策(5 个场景)
用户输入
│
├─ mastergo URL + 有 yapi 信息 + 没说"xxx 模块" ──→ 场景 1 完整新模块(设计稿+接口)
│
├─ mastergo URL + 没 yapi + 没说"xxx 模块" ──→ 场景 2 完整新模块(无接口)
│ 问"数据策略 A(mock)/D(静态)?",auto 默认 A
│
├─ mastergo URL + "xxx 模块 增量" ──→ 场景 3 增量(现有模块加东西)
├─ mastergo URL + "xxx 模块 迭代" ──→ 场景 4 迭代(现有模块改一部分)
├─ mastergo URL + "xxx 模块 重构" ──→ 场景 5 重构(现有模块整个重写)
│ 场景 3/4/5 必跑 Step 0.5 e2e 定位
│
├─ 只有 yapi URL,没 mastergo ──→ 不走 module-flow,转给 yapi-to-code 单跑
└─ 自然语言含"批量做 N 个" ──→ 拒绝,一次只跑一个完整任务
场景行为对比
| 1 完整(含接口) | 2 完整(无接口) | 3 增量 | 4 迭代 | 5 重构 | |
|---|---|---|---|---|---|
| 建新 module 目录 | ✅ | ✅ | ❌ 用现有 | ❌ 用现有 | ❌ 用现有 |
| 加新路由 | ✅ | ✅ | ❌ | ❌ | ❌ |
| 加新菜单 | ✅ | ✅ | ❌ | ❌ | ❌ |
| Step 0.5 e2e 定位 | ❌ | ❌ | ✅ 必跑 | ✅ 必跑 | ✅ 必跑 |
| Stage A 拉设计稿 | ✅ | ✅ | ✅ | ✅ | ✅ |
| Stage B yapi | ✅ 必传 | ❌ | 可选(增新接口才传) | 可选(默认复用现有,接不上写默认数据) | 可选(同迭代) |
| Stage C 行为 | 新建全套 | 新建全套 mock | 加新子组件 import 到现有 Index.vue | 精准 Edit 现有 Vue 局部 | 替换 Index.vue 内容,保留路由菜单 |
| Stage A.recall | ✅ | ✅ | ✅ | ✅ | ✅ |
| Stage D smoke | ✅ | ✅ | ✅ | ✅ | ✅ |
字段缺失补全:
- pagePath / module / imgDir → 拉 DSL 根节点 + grep menu 自动推断,auto 模式不问
- 数据策略(场景 2) → auto 默认 A;非 auto 问用户
- 场景 3/4/5 → 用户必须显式说"xxx 模块 [增量/迭代/重构]",不准 Claude 推断
Auto Mode(无确认模式)
触发:用户输入含任一关键词 → 全跑 / 一气呵成 / auto / yolo / 别问 / 自动,或 PROJECT-TASK 块里写 mode: auto。
进入 / 退出 auto 模式必跑(harness hook 配套)
进入 auto 模式时必须先 touch flag 文件,这是给 .claude/hooks/auto-mode-guard.mjs 看的:
mkdir -p .claude/state
touch .claude/state/auto-mode.flag
flag 存在时,hook 会拦截非白名单的 AskUserQuestion 调用(exit 2 拒绝)。白名单只有 4 个必停点对应话题(见下表)。
跑完所有 Stage(成功 / 失败 / 用户取消)必须删 flag:
rm -f .claude/state/auto-mode.flag
未删 flag 会导致后续无关对话也被当 auto 模式。铁律: auto 模式入口/出口都要操作 flag。
自动决策表(都不问用户)
| 字段 | 自动决策规则 |
|---|---|
| 场景 | 有 yapi 信息 → 场景 1;没 yapi → 场景 2 默认数据策略 A(全 mock) |
module |
从 DSL 根节点 name 推 camelCase |
pagePath |
grep <config.menuFile> 找最近同类父级,组成"父级 / 当前" |
imgDir |
<config.imgDirBase>/<pagePath 父级 kebab>/<module> |
| YApi 接口选择 | 给了 yapiProjectId → yapi_search_apis 模糊搜 → 取分数 ≥ 7 的全要;给了 apiLinks → 直接用 |
| 数据策略(场景 2) | 默认 A(全 mock) |
| Step 2-4 检查点 | 全部跳过,推断完直接进 Stage A |
| Stage D smoke 失败 | 不阻断(本来就是) |
compare-tokens DSL diff |
跑 + 报告,不阻断 |
vue-tsc 报错 |
报告 + 落「待人工修复清单」,不阻断 |
What ships with it
8 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.
- references/cancel-and-resume.md 3.3 KB
- references/common-pitfalls.md 3.3 KB
- references/data-strategy-options.md 2.9 KB
- references/error-recovery.md 3.8 KB
- references/stage-contracts.md 5.2 KB
- references/task-template.md 7.1 KB
- schemas/task-input.schema.json 2.3 KB
- scripts/check-resume-state.mjs 1.6 KB runs code
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.
- 1mo ago First seen · 419 lines · 162 tokens per session scan A 0f255b6196cd
module-flow is a skill published in the GitHub repository willnie9/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 162 tokens to every session and 5,530 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
infographics
Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.
figma-implement-design
Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a…
ui-design-source
Use this skill when the user provides Figma material, design-export files, screenshots of design tools, PDFs, JSON, existing HTML or other UI source code, or asks for design-to-HTML/code fidelity. It adapts OpenDesign/Figma handoff discipline for UIDesigner without requiring a live source runtime.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
ui-design-contract
Use this skill before rendering when the direction must persist across multiple screens/components, brand or system work, conflicting references, formal handoff, or a genuinely vague visual system. Ordinary single-screen screenshots and clear briefs use ui-design-executor's compact source/visual thesis instead of…