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 agentmods add skills/willnie9/agent-skills/module-flownpx skills add willnie9/agent-skills --skill module-flowgit clone --depth 1 https://github.com/willnie9/agent-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/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.svg" alt="Measured on agentmods" 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 | $0.00162 | $0.05530 |
| Opus 5 | $0.00081 | $0.02765 |
| Sonnet 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 3d 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.
- 3d 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 2mo ago), licensed MIT. It adds 162 tokens to every session and 5,530 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
banana
Direct, generate, edit, compare, and review visual assets with current Google Gemini image models. Use for image creation, image editing, reference-based consistency, product and character visuals, text-bearing graphics, grounded diagrams, video-derived images, and multi-model image portfolios.
opencompany-design
Use this skill to generate well-branded interfaces and assets for OpenCompany (opencompany.sh), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
web-clone
网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支，并强制核对任何 AI 二手分析里的可执行代码。.
julilaoshi-design
Public-safe julilaoshi-design workflow for official Pencil MCP execution and the free browser-first julilaoshi-design Web 2.0 editor. Use when a task needs Pencil handshake/canvas edits, .pen execution, screenshot review, or lightweight HTML design-to-web tweaking without redistributing official Pencil or leaking…
game-ui-workflow
Orchestrates an end-to-end game UI workflow from game design (GDD), PRD, and UI interaction logic through design specification, screen-system extension, page image generation, component breakdown, sprite-sheet splitting, PNG ZIP packaging, atlas packing, engine JSON handoff, asset registration, and validation. Use…
mermaid-skill
Generate Mermaid diagrams (.mmd) and export to PNG/SVG/PDF using mmdc CLI or Kroki API. USE THIS SKILL when user mentions diagram, flowchart, sequence diagram, class diagram, ER diagram, state machine, architecture, visualize, git graph, 画图, 架构图, 流程图, 时序图, 类图, ER图, 甘特图, 状态机. PROACTIVELY USE when explaining ANY system…