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/lupingluke-ai/general-ai-specnpx agentmods add skills/lupingluke-ai/general-ai-spec/module-designerWrote 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/lupingluke-ai/general-ai-spec/module-designer)<a href="https://agentmods.dev/skills/lupingluke-ai/general-ai-spec/module-designer"><img src="https://agentmods.dev/badge/skills/lupingluke-ai/general-ai-spec/module-designer/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/lupingluke-ai/general-ai-spec/module-designer"><img src="https://agentmods.dev/badge/skills/lupingluke-ai/general-ai-spec/module-designer.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 | $0.00127 | $0.05039 |
| Opus 5 | $0.00063 | $0.02520 |
| Sonnet 5 | $0.00025 | $0.01008 |
| Haiku 4.5 | $0.00013 | $0.00504 |
Grade A, and why
module-designer 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 10d 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Module Designer
Overview
把"模块设计"和"idea 拆分"合并到一次对话里完成。读设计输入(brainstorming / figma / 访谈)→ 与用户在对话收敛模块边界 → 自动拆分为 N 条 backlog idea(每条自动建议 type)→ 生成 module 文档 + 写入 backlog → 全量重渲染 roadmap。
职责边界: 只负责 L0→L1→L2 的设计层工作。PRD 生成由 prd-writer,技术规划由 change-propose,执行/审查由 change-dispatch / change-review。
Announce at start: "Running module-designer: designing module and decomposing into backlog."
When to Use
- 用户说"帮我设计一个 XX 模块" / "帮我把这个想法拆一下"
- 用户触发
/design "<主题>"(新建模块) - 用户触发
/design M-NNN(对已有模块增量更新) - 用户触发
/design review M-NNN(复盘重排,允许较大幅度修改) - 有新的
design/inputs/**素材需要转化为模块+idea
Bash 命令规范
- 每条命令独立调用 — 不用
&&、||、;串联 - 管道可以用 — 如
git log | head - 并行无依赖时分开调用 — 多个独立 Bash tool call
输出物清单
单次运行产出(通过 governance/module-designer/M-NNN-RNNN PR 合入 main;RNNN 为该模块下一治理修订号):
design/modules/M-NNN-<slug>.md(新建或增量更新)product/backlog.md(新增 N 行 idea,含"模块"列 + 自动建议的 type)design/roadmap.md的 3 段 AUTO 区(ARCHITECTURE + DEPENDENCIES + PROGRESS).logs/module-designer/M-NNN.md复盘日志
Phase 0 — 同步远程
在读任何文件之前,先同步远程状态:
git checkout main
git pull --ff-only origin main
目的:
- 保证 M-NNN / B-NNN 编号分配不冲突
- 保证读到最新的 backlog 和 roadmap
- 保证不在过时基线上设计
失败处理: 冲突时提示用户先解决再继续。
Phase 1 — 输入定位
根据触发参数分派:
| 触发 | 动作 |
|---|---|
/design "<主题>" |
新建模式:分配下一个 M-NNN,等 Phase 2 对话收敛 slug |
/design M-NNN |
增量模式:读 design/modules/M-NNN-*.md 现状 |
/design review M-NNN |
复盘模式:允许修改已有模块边界/依赖;禁止改已归档 backlog |
M-NNN 分配(全局递增)
ls design/modules/ | grep -oE 'M-[0-9]+' | sort -Vu | tail -1
取最大值 +1;无已有模块时从 M-001 起。
治理修订号(防止增量模式被永久 checkpoint 卡住)
新模块使用 R001。已有模块按 ## 修订历史 的有效记录数 +1 得到 RNNN;同一 main 快照上的并发会话会得到同一 revision scope,只有一个 governance PR 能进入,其余返回 PENDING,待先到者合并后重新同步并计算下一 revision。scope 一次只代表一次状态转换,不能永久复用裸 M-NNN。
B-NNN 预分配(全局递增)
在 Phase 3 对话确定要拆几条 idea 后,按顺序从当前 backlog 最大 B-NNN 之后预留:
grep -oE 'B-[0-9]+' product/backlog.md | sort -Vu | tail -1
若无输出则从 B-001 起。初始化模板不得包含真实 B-NNN 占位编号,避免污染首次分配。
What ships with it
1 file 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.
- 10d ago First seen · 375 lines · 127 tokens per session scan A 3a813def0197
module-designer is a skill published in the GitHub repository lupingluke-ai/general-ai-spec (5 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 5,039 once invoked, about $0.0006 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
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
handdrawn-diagram
Generate a hand-drawn (sketch-style) architecture or flow diagram as a committable image (SVG + PNG). Use when the user wants a sketch-aesthetic diagram for a README, docs, or hackathon/Devpost submission that still has correct, legible text and per-group color. Authors a Mermaid look:handDrawn source and renders it…
c4-diagrams
Use when explaining existing code architecture, visualizing a new system before detailed design, mapping software boundaries, or creating C4-style diagrams in ASCII or Mermaid.
dpf-ux-fit-review
Use before code or PR handoff for UI-impacting DPF work — any route, viewport, dashboard, metric, card, button, empty state, navigation, or admin/settings/config screen, form, or field. Config forms are UI surfaces.
agent-hephaestus
UI, accessibility, and interaction-quality review.
pm-prototype
Cross-phase prototyping engine. Turns a scoped chunk of the product (a feature, a PRD initiative, the whole product, or any slice) into a tool-ready prototype spec that a prototyping tool (Lovable, v0/Vercel, Base44, Figma Make) can build with minimal loss of context. Gate-checks whether a prototype is worth it…