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/lync-cyber/cataforge/arc-designnpx skills add lync-cyber/CataForge --skill arc-designgit clone --depth 1 https://github.com/lync-cyber/CataForgeWrote 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/lync-cyber/cataforge/arc-design)<a href="https://agentmods.dev/skills/lync-cyber/cataforge/arc-design"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/arc-design.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 5.1 | $0.00071 | $0.01746 |
| Opus 5 | $0.00036 | $0.00873 |
| Sonnet 5 | $0.00014 | $0.00349 |
| Haiku 4.5 | $0.00007 | $0.00175 |
Grade A, and why
arc-design 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 6d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
架构设计 (arc-design)
能力边界
- 能做: 架构风格选型、模块划分、接口契约定义、数据模型设计、系统上下文建模
- 不做: 需求分析(req-analysis)、UI 设计(ui-design)、代码实现(implementer/TDD)
输入规范
- PRD功能需求(F-{NNN}列表)
- PRD非功能需求
- 技术选型结果(来自tech-eval)
输出规范
- 架构概览(风格 + 系统上下文图)
- 模块划分(M-{NNN}),每个模块映射PRD功能点
- 接口契约(API-{NNN}),完整request/response定义
- 数据模型(E-{NNN}),字段含类型和约束
- 目录结构 + 开发约定
执行流程
语言细则: 根据
framework.jsonproject.languages,按需载入本 skillreferences/lang-<lang>.md(仅 active 语言,逐个 Read),获取对应语言的技术选型细则(包/依赖管理、框架选项、并发模型、构建产物形态)。project.languages为空或未配置时跳过 lang-detail 载入,按语言无关原则做架构决策。
可选前置: Grill 深度澄清
触发与启用协议见 design-grill §启用门(项目偏好或阶段入口一次询问;询问不等于启用,用户明确接受后调用 design-grill arch [范围])。未启用即以 research user-interview 做普通澄清。Grill 发现会改变系统边界、数据含义、权限模型或核心流程的 PRD 缺口时,交回 req-analysis 澄清,不以技术假设填补;总结返回后再进入 Step 1。
Step 1: 需求分析与架构决策 (对应ARCH §1)
- 通过
cataforge context read prd#§2(功能需求)/prd#§3(非功能需求)按需分章节加载 - §1.1 确定项目类型: fullstack | backend-only | CLI | API-only (此决定影响orchestrator是否跳过Phase 3 UI设计)
- §1.2 架构风格选型: 结合tech-eval调研结果 决策标准: 团队规模 / 性能要求 / 部署环境 / 可维护性 不确定时必须通过research skill的user-interview指令向用户确认,不得直接标注[ASSUMPTION]跳过 决策记录: 三要素见 COMMON-RULES §决策记录要求
- §1.3 系统上下文图: Mermaid C4Context 格式(系统边界、外部依赖、用户交互)
- §1.4 技术栈: 每项技术填写(层次 | 技术 | 版本 | 选型理由 | 调研来源)表
Step 2: 模块划分 (对应ARCH §2)
- 从PRD功能点(F-{NNN})推导模块(M-{NNN})
- 每个模块包含:
- 职责: 单一职责描述
- 映射功能: F-{NNN}列表(引用PRD)
- 对外接口: API-{NNN}列表(引用 §3 接口契约)
- 依赖模块: M-{NNN}列表
- 内部关键组件: 类/组件列表
- 验证: 所有F-{NNN}至少被一个M-{NNN}覆盖(无遗漏)
- 模块间依赖应为有向无环
Step 3: 接口契约 (对应ARCH §3)
- 为每个对外接口定义API-{NNN}
- 格式使用YAML:
path: /api/v1/{resource} method: POST module: M-{NNN} request: headers: { Authorization: "Bearer {token}" } body: field1: { type: string, required: true, desc: "{说明}" } response: 200: { schema: "{ResponseType}" } 400: { schema: "ErrorResponse" } - 必填: request headers + body字段(type + required + desc)
- 必填: response成功码 + 错误码schema
Step 4: 数据模型 (对应ARCH §4)
- 描述实体关系(1:N / M:N / 继承等,Mermaid erDiagram 格式)
- 定义实体E-{NNN},字段表格(字段 | 类型 | 约束 | 说明)
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.
- 6d ago First seen · 103 lines · 71 tokens per session scan A 4dc22d3b09af
arc-design is a skill published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,746 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…