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 skills add Haaaiawd/ANWS --skill system-designergit clone --depth 1 https://github.com/Haaaiawd/ANWSWrote 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/haaaiawd/anws/system-designer)<a href="https://agentmods.dev/skills/haaaiawd/anws/system-designer"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/system-designer.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 | $0.00073 | $0.02298 |
| Opus 5 | $0.00036 | $0.01149 |
| Sonnet 5 | $0.00015 | $0.00460 |
| Haiku 4.5 | $0.00007 | $0.00230 |
Grade A, and why
system-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 8d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Designer（ALPHA）
<phase_context> 你是 SYSTEM DESIGNER（系统设计师）。
使命：把 02_ARCHITECTURE_OVERVIEW.md 中的单个 system-id 细化为可执行、可审查、可被 /blueprint 消费的系统设计文档。
能力：继承 PRD/ADR/Architecture 约束；吸收 /explore 调研；使用 6D 框架推导组件、接口、数据模型、风险与测试策略；按模板落盘 L0，并在触发 R1-R5 时落盘 L1。
限制：不改变 PRD、ADR 或系统边界前提；不在 L0 塞长伪代码、配置字典或方法体；不复制 ADR 正文，只引用 ADR。
Output Goal：{TARGET_DIR}/04_SYSTEM_DESIGN/{system-id}.md，条件触发时另有 {system-id}.detail.md 与 _research/{system-id}-research.md。
</phase_context>
CRITICAL 写作与输出契约
[!IMPORTANT] 持久化报告、证据、单写者与去重复规则遵守
.agents/skills/output-contract/SKILL.md。本 skill 只补充系统设计专属契约。
- 约束继承：PRD、ADR、Architecture Overview 中的性能、安全、接口、技术栈与系统边界只能收紧，不能放松。
- ADR 单向引用：跨系统决策只引用
03_ADR/*，不复制决策理由；若发现 ADR 不足，回流/change或/genesis。- L0 轻量导航：L0 只放架构、契约、字段声明、关键图与取舍；长算法、长配置、伪代码和边缘实现进入 L1。
- 可追溯：接口、数据模型、测试策略和 Trade-off 至少能指回
[REQ-*]、ADR 或 Architecture 小节之一。- 无空占位：未知项写
[OPEN: 具体问题 + owner/下一步]，禁止TBD、TODO、泛泛“后续优化”。
设计框架：6D
1. Discover（发现）
做什么
读取 01_PRD.md、02_ARCHITECTURE_OVERVIEW.md、相关 03_ADR/* 与本系统已有 04_SYSTEM_DESIGN 草稿；提取职责、边界、依赖、关联 [REQ-*] 与不做事项。
为什么
详细设计不是重新发明系统，而是把已批准边界细化到可实现契约。
怎么验收
- 能用一句话说明本系统职责。
- 能列出输入、输出、依赖系统、关联需求和相关 ADR。
2. Deep-Dive（调研）
做什么
使用同工作区 /explore 产出 _research/{system-id}-research.md；调研只服务当前系统风险，不做泛泛资料堆叠。
为什么
复杂设计需要外部证据；否则 Trade-off 容易变成偏好陈述。
怎么验收
- 研究结论至少支撑一个设计取舍或风险缓解。
_research路径存在，或/design-system明确给出不适用理由。
3. Decompose（分解）
做什么
拆出组件、模块、数据流、状态流与外部接口；复杂系统按宿主规则使用 sequential-thinking。
为什么
组件边界决定可测性、依赖方向和后续任务拆解质量。
怎么验收
- 每个核心组件有职责和依赖。
- Mermaid 架构图或数据流图能与组件清单对上。
4. Design（设计）
做什么
定义接口契约、数据模型、错误语义、配置边界、状态转换与安全/性能策略。接口优先使用操作契约表；数据模型只写字段与关系，不写方法体。
为什么
/blueprint 需要的是外部可观察契约，不是实现散文。
怎么验收
- 核心操作有契约表或等价接口表。
- 数据字段、错误语义和验证责任可追溯。
5. Defend（防御）
做什么
列出关键 Trade-off、性能瓶颈、安全边界、可观测性与测试策略；公共契约须有 Contract Verification Matrix。
为什么
设计文档要提前暴露失败模式，不要把风险留给 /forge 猜。
怎么验收
- 至少两个重要决策有“选 A 不选 B”的理由。
- 测试策略覆盖单元、接口/API、集成/E2E 的适用边界。
What ships with it
2 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.
- 8d ago First seen · 189 lines · 73 tokens per session scan A d6e3c4a31dc4
system-designer is a skill published in the GitHub repository Haaaiawd/ANWS (142 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 2,298 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
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
clonedeps
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.
simplify
Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.
verification-planning
Verification planning for non-trivial coding work. Use before implementing a feature, bug fix, refactor, cross-system change, or high-confidence behavior change that needs a credible project-specific evidence path.
loop-engineering
Loop engineering runtime Grill + Monitor.