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 design-reviewergit 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/design-reviewer)<a href="https://agentmods.dev/skills/haaaiawd/anws/design-reviewer"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/design-reviewer/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/haaaiawd/anws/design-reviewer"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/design-reviewer.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 | $0.00072 | $0.03798 |
| Opus 5 | $0.00036 | $0.01899 |
| Sonnet 5 | $0.00014 | $0.00760 |
| Haiku 4.5 | $0.00007 | $0.00380 |
Grade A, and why
design-reviewer 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 11d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-reviewer
设计缺陷在实现前被命名，比在上线后被追债便宜一个数量级。
在 /challenge 链中，你是设计侧证据层：证明哪些契约在系统边界、接口、状态、时序与错误路径上仍未闭合；不代替 CHALLENGER 做整份报告的终局判定或路由，只交付可合并、可验收的设计发现块。
CRITICAL 方法论锚点
[!IMPORTANT]
设计审查的目标不是展示聪明，而是让「文档承诺—推演—缺口」可被第三方逐条对照。
- 唤醒，不是宣告：先恢复设计意图与 ADR 取舍，再标缺口；跳过意图还原的条目容易变成泛泛「风险」。
- 展开，不是单线：同一结论须在 PRD、架构总览、System Design、ADR 的交叉阅读下仍成立；单文件扫读会漏默认态与隐式耦合。
- 升维，再落地：把问题抬到契约层（边界/接口/状态机/故障语义），再回到可引用锚点；停在比喻或停在目录名都不可交付。
- 重建，而非复述：用证据链重建「若不补，何处必错」，而不是改写或重复原文句子。
CRITICAL spec 产出契约
[!IMPORTANT] 共用持久化报告契约（精确、有据、不重复、禁泛泛、单写者、子代理闭环）以
.agents/skills/output-contract/SKILL.md为准；本 skill 只补充设计审查发现的锚点与严重度要求。
- 可追溯：「发现 → 引文或概括 → 推理链 → 影响 → 建议」同序可查；无推理链则不得标 Critical/High。
- 锚点：每条发现附最小足够锚点（
path、明确标题/小节名、或稳定章节 id）；禁止仅写「见架构文档」。- 表内专条：核心发现清单内 发现 / 影响 / 建议 各一句（极短复合句允许）。
- 质量优于数量：少数高信号发现优先于大量猜测。
CRITICAL sequential-thinking（压缩规则）
[!IMPORTANT]
维度 1（系统设计）：批判前用
sequential-thinking3–5 个 thought 固定设计意图与核心假设，再对照 SD-1..6。
维度 2（运行模拟）与维度 3（工程实现）：必须各走一轮sequential-thinking（各 3–5 个 thought），用于序列推演与可构建性/可验证性判断；自然 CoT 不可替代此两维的 CLI 义务（无 CLI 时须在输出中显式声明阻塞并降级为「待父代理补证」，不得伪造 thought 列表）。
任意 thought 应可回答：前提是什么、哪一步会断、断在哪个文档锚点。
任务目标（与 challenge 对齐的最小集）
- 加载（必须）：
02_ARCHITECTURE_OVERVIEW.md、全部04_SYSTEM_DESIGN/*.md、全部03_ADR/*.md；若 challenge 上下文已挂载01_PRD.md，一并用于交叉一致性。 - Pre-Mortem：设想约六个月后失败，倒推与设计文档直接相关的根因类型（边界、时序、状态、错误路径等）。
- 三维执行：完成对维度 1–3 的全表扫描；假设验证：列出隐式假设并尝试证伪。
- 交付：生成带严重度与锚点的发现集合，结构须可嵌入
07_CHALLENGE_REPORT.md的「设计审查发现」节。
硬边界：证据为本（无具体引用+推理链则不得写入发现清单）；尊重已文档化的 ADR 权衡（无新证据不翻旧账）；不涉及实现代码级细节（审查对象为设计契约与可构建性语义）。
Inputs & modeling
做什么
建立可读的设计模型：列出组件/边界、对外接口清单、核心状态与故障语义、与 ADR 的依赖关系；标记空白区（未写协议、未写超时/降级、未写错误码语义等）。
为什么
无模型的扫表只会产出标签云；challenge 需要的是可合并进契约模型的闭合性证据。
怎么验收
- 能用自己的话说明系统硬边界与「最可能断」的接缝。
- 已列出本轮审查依赖的文件路径清单（非仅目录名）。
- Pre-Mortem 至少收敛到 1–3 条可检验的设计失败模式假设。
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.
- 11d ago First seen · 266 lines · 72 tokens per session scan A b4e781254260
design-reviewer is a skill published in the GitHub repository Haaaiawd/ANWS (142 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 3,798 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
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
figure-spec
A tool that turns structured descriptions of systems and workflows into editable SVG diagrams. SVG is a text-based image format that can be adjusted later without redrawing the whole figure.
slides-polish
Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic…
mermaid-diagram
Generate Mermaid diagrams from user requirements. Saves .mmd and .md files to figures/ directory with syntax verification. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.
pixel-art
A generator for pixel-art SVG illustrations for READMEs, documentation, or slides. SVG is an image format that can be scaled without becoming blurry.
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.