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 spec-writergit 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/spec-writer)<a href="https://agentmods.dev/skills/haaaiawd/anws/spec-writer"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/spec-writer/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/spec-writer"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/spec-writer.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 | $0.00083 | $0.03316 |
| Opus 5 | $0.00042 | $0.01658 |
| Sonnet 5 | $0.00017 | $0.00663 |
| Haiku 4.5 | $0.00008 | $0.00332 |
Grade A, and why
spec-writer 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 9d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
需求侦探手册
“软件开发最难的部分，不是如何实现，而是精确定义到底要实现什么。”
你的任务是消灭歧义。
genesis Step 2（范围与衔接）
本模板相对 templates/.agents/skills/spec-writer 增加 craft 脚手架、spec 契约（落盘语义）、子代理编排与 completion；下列「执行清单 / 方法论 / 10 维歧义扫描表 / User Story 质量闸门表」的规范性效力不变——追问苏格拉底行为、一次性一个问题、[NEEDS CLARIFICATION] 硬上限、Non-Goals 与 User Story 闸门等规则** verbatim 适用**。
craft scaffolding（产物脚手架）
在执行清单第 4 步（落盘 01_PRD.md）前，骨架必须先就位；填内容时不得删模板中的规范性章节，无信息则写 [NOT APPLICABLE | reason] 或 [ASSUMPTION]，不得留白假装完成。
| 工件 | 路径 | 必须满足 |
|---|---|---|
| 版本目录 | .anws/v{N}/ |
v{N} 与宿主 genesis / 会话约定一致；首轮创建或显式沿用既有 v{N}，禁止 silent fork。 |
| PRD | .anws/v{N}/01_PRD.md |
唯一权威 Step 2 产出；内容由 references/prd_template.md 驱动；禁止仅以聊天长篇代替落盘。 |
| 模板 | references/prd_template.md |
起草 PRD 前全文读取；标题层级与必选段落以模板为准，额外附录允许但不可替代模板必选节。 |
就绪检查（内部，可向用户简述）：已选 v{N}；已读本 SKILL + prd_template.md；已枚举至少 3 条 User Story 草稿与 ≥3 Non-Goals 再进入落盘段落扩展。
spec 契约（PRD 落盘语义）
[!IMPORTANT] PRD 段落在合并进 genesis 链路时视作可对下游断言的契约草稿（架构、任务分解、challenge），须同时满足：
- 可验证：凡写入「必须 / 禁止 / SLA / 用户数 / 兼容性」类陈述，须有 Given-When-Then、指标或枚举；否则不得标为已实现需求，只可
[ASSUMPTION]或删至 Non-Goals。- 可定位：每条 User Story 带
[REQ-XXX]；术语与系统在 PRD 内与下文「涉及系统」引用自洽（下游以02_ARCHITECTURE_OVERVIEW.md对齐时不得无故改名）。- 可收敛歧义：
[NEEDS CLARIFICATION]≤ 3（硬限制）；超限则默认值 +[ASSUMPTION: …]；禁止对已声明的通用默认（见原文 10 维扫描节）再行追问刷数。- 可追溯价值：每条需求能一句话对齐用户价值；Non-Goals 与 Goals 互斥且无空洞「也许不做」。
- 一致性：同一事实在摘要与详情中不二次矛盾表述；修正采用原子段落替换，不留互相打架的并排说法。
Challenge / 下游专用对齐：若在报告或附件中摘录 PRD 结论，摘录须带 小节锚点 或 01_PRD.md Stable 标题，禁止只写「见 PRD」。
子代理编排（可选）
当宿主支持并行子会话时：
| 角色 | 职责 |
|---|---|
| 父代理 | 选定 v{N}、加载用户意图与上下文、合并本子代理返回的结构化块、去重与同主题择优、对 .anws/v{N}/01_PRD.md 保持 单写者、跑完强制「10 维歧义扫描」与 User Story 质量闸门并最终交付用户确认。 |
| 子代理 | 只吃有界切片：例如「仅生成澄清问题批次（附推荐答）」「仅提取 / 重写 User Stories（仍为草稿）」「仅对 10 维表中第 k 维做 Clear/Partial/Missing 标注 + 补丁建议」「仅将感觉词改写为度量候选列表」；返回 Markdown 结构化块 + 锚点建议；不假设已读父代理专有上下文。 |
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.
- 9d ago First seen · 154 lines · 83 tokens per session scan A f648576f914a
spec-writer is a skill published in the GitHub repository Haaaiawd/ANWS (142 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 3,316 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.