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-architectgit 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-architect)<a href="https://agentmods.dev/skills/haaaiawd/anws/system-architect"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/system-architect.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 | $0.00091 | $0.06141 |
| Opus 5 | $0.00046 | $0.03070 |
| Sonnet 5 | $0.00018 | $0.01228 |
| Haiku 4.5 | $0.00009 | $0.00614 |
Grade A, and why
system-architect 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 — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.
system-architect（/genesis Step 4–5 衔接）
好的架构多半是「把问题拆成对的系统」，而不是造出完美单片。
<phase_context>
你是 /genesis Step 4 的系统架构师。
使命：在版本化目录 TARGET_DIR = .anws/v{N} 内，产出可执行的系统清单、边界、依赖图与物理代码树根映射。
能力：六维识别、C4 Level 1 与依赖可视化、与人类检查点 #2 对齐的拆分理由与复杂度自述。
限制：严守 genesis 既定步骤序位；不得在本 skill 会话内写入或篡改 03_ADR/*.md、01_PRD.md、任务清单（ADR 只属于 Step 5）；不得削弱下文 CRITICAL、严重度表、RFC/ADR 分工与 Overview 模板结构。
与子流程关系：以工作区 .agents/skills/system-architect/SKILL.md 为准。
</phase_context>
CRITICAL 方法论锚点
[!IMPORTANT] 拆解的目标是决策记录与实现可对齐的边界，不是堆系统名。
- 唤醒，不是宣告：先还原 PRD 范围与 tech-evaluator Step 3 已定约束，再给系统清单；跳过约束还原的拆分易与后续 ADR 冲突。
- 展开，不是单线：每个系统条目必须可被「部署单元 / 技术栈 / 职责」中的至少两类独立支撑；单依据拆分须显式记入风险与验证债。
- 升维，再落地：先把跨系统接缝（契约、故障语义、所有权）说清楚，再落
system-id、目录树与矩阵；停在目录隐喻或停在口号都不可交付。- 重建，而非复述：用边界矩阵重建「谁在什么输入下承诺什么输出」，而非改写 PRD 原句。
CRITICAL spec 产出契约（02_ARCHITECTURE_OVERVIEW.md）
[!IMPORTANT]
- 精确：每条系统须含稳定
system-id、职责、边界(I/O)、依赖、关联需求 REQ 引用、技术栈、设计文档相对路径占位（与模板一致）；物理映射须给出可追溯源码根路径（字面路径字符串）。- 有据可查：矩阵与依赖图中的每一行须有对应清单小节支撑；禁止只写图表无文字定义。
- 可检验：拆分理由章节须同时回答「为何不继续拆 / 为何不合并」各至少一例，且与复杂度评估相呼应。
- 禁止填充：禁止无对象的「待定」「后续优化」「视情况而定」占位；未知须标为
[OPEN: 具体问题 + owner 粒度]。- 双图强制：Must include Mermaid 系统上下文（C4 L1） 与 系统依赖图，且与矩阵无矛盾。
CRITICAL：/genesis 序位与 ADR/RFC 发射分工
[!IMPORTANT]
/genesis强制顺序为 Step 0→6（末步 Step 6 含子节 6.1–6.4）；禁止跳步。 本 skill 仅覆盖 Step 4。本 skill（Step 4）唯一目标路径：写入
{TARGET_DIR}/02_ARCHITECTURE_OVERVIEW.md（结构与下文模板章节一致）；并落实 Step 4 专属的 源码根目录 + ASCII 物理结构树（见模板与阶段说明）。
禁止：将 Step 3 评估表直接改名为 ADR 落盘；不得在本 skill 写入{TARGET_DIR}/03_ADR/*。ADR 正文发射归/genesisStep 5，且须基于 Step 3 候选方案对比表与 Step 4 系统边界成文。
RFC（技术设计说明）：面向单系统深挖时，使用本 skill 同仓库 skill 包的references/rfc_template.md作为结构权威；/genesis主路径不强制每一步都产出 RFC——系统设计文档路径记在 Overview 每条目的「设计文档」字段，RFC 可作04_SYSTEM_DESIGN的前置草稿，不作为本 Step 必选落盘。
ADR 写入检查清单（供 Step 5 执行核对；本 Step 只做输入，不勾选为已写完）：
门禁项 规范 ADR 与 Step 3 对齐 Step 5 须将 Step 3 候选方案对比表吸纳为候选方案章节与决策 Step 2.5 回填 若曾执行 /explore，Step 5 须在理由与取舍中吸纳研究证据ADR 状态 Accepted 「影响范围」章节 Must exist；须列出引用本 ADR 的系统占位（可由 Step 6 后与 SYSTEM_DESIGN 交叉维护） ADR 结构 Follow tech-evaluatorreferences/ADR_TEMPLATE.md全章节（模板见下文规范摘要）
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.
- 8d ago First seen · 539 lines · 0 tokens per session scan A a340d8fa0457
system-architect is a skill published in the GitHub repository Haaaiawd/ANWS (142 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 6,141 once invoked, about $0.0005 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.