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 craft-authoringgit 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/craft-authoring)<a href="https://agentmods.dev/skills/haaaiawd/anws/craft-authoring"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/craft-authoring/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/craft-authoring"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/craft-authoring.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 | $0.00038 | $0.01207 |
| Opus 5 | $0.00019 | $0.00603 |
| Sonnet 5 | $0.00008 | $0.00241 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
craft-authoring 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 10d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Craft Authoring - 脚手架与自检
本 skill 承接 /craft 中“如何写成”的细节。
/craft 给方向，这里给落地。方向如果没有落地，会变成口号；落地如果没有方向，会变成机械动作。
全局写作协议
- 禁止使用 emoji。
- 允许拟人叙事，但语气必须克制、理性、专业。
- 使用短句，每句表达单一语义。
- 每个 Step 固定回答：做什么 / 为什么 / 怎么验收。
- 先给意义，再给规则，再给验证。禁止只写漂亮话。
判断准绳：
- 好文档让执行者更清醒、更稳定、更可复现。
- 坏文档让执行者更兴奋，却更依赖临场发挥。
与
output-contract的分工：本节只定义 Workflow / Skill / Prompt 撰写脚手架；持久化报告的共用 spec、父子委派与单写者规则见.agents/skills/output-contract/SKILL.md。
与 CLI 安装清单的分工：哪些路径会随anws init复制、registry 与BUNDLE_POLICY边界见references/BUNDLE_POLICY.md。
Workflow 骨架（最小可用）
---
description: [一句话说明用途]
---
# /name
<phase_context>
你是 **[角色]**。
**使命**：...
**能力**：...
**限制**：...
**与用户的关系**：...
**Output Goal**: `路径`
</phase_context>
---
## CRITICAL 写作约束
> [!IMPORTANT]
> 写作约束由 `/craft` 主 workflow 统一定义，此处不重复展开。
---
## Step 1: [标题]
### 做什么
...
### 为什么
...
### 怎么验收
- ...
- ...
---
<completion_criteria>
- [可验证完成标准]
</completion_criteria>
Skill 骨架（description 必须是触发条件）
---
name: kebab-name
description: 当 [具体触发场景] 时加载。[能力概括]
---
# 标题
## 做什么
...
## 为什么
...
## 怎么验收
- 输入契约：...
- 输出契约：...
description 忌：泛化能力标签。
description 宜：明确触发场景与边界。
判断准绳：
一个好的 description 像门禁，不像标语。
它要决定“何时进入”，也要决定“何时不进入”。
Prompt 骨架
# 标题
## 做什么
...
## 为什么
...
## 怎么验收
- 约束：...
- 输出格式：...
防护语法速查
| 机制 | 用途 |
|---|---|
[!IMPORTANT] |
不可跳过节点 |
## CRITICAL |
边界醒目 |
你**必须** |
强制动作 |
<completion_criteria> |
完成定义 |
重要约束至少写清：做什么、为什么、偏航信号。
填充内容（Step 5 等价）
用 sequential-thinking 组织 3-5 个 thought，覆盖目标、易错点、每步 I/O、调研结论落点。
质量快检：
- 章节是否单问题回答
- 约束是否写明为什么
- 输出是否可验证
判断准绳：
如果一个段落不能告诉执行者“该做什么”，它就是噪声。
如果一个段落不能告诉执行者“为何如此”，它就是命令。
如果一个段落不能告诉执行者“如何验证”，它就是祈祷。
验证清单（输出前）
结构：
- frontmatter
phase_context（workflow 场景）CRITICAL块<completion_criteria>
内容：
- 路径与命名正确
- 触发条件清晰
- 输入输出契约完整
- 失败信号可被外部观察
What ships with it
3 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.
- 10d ago First seen · 187 lines · 38 tokens per session scan A 627aec30d000
craft-authoring is a skill published in the GitHub repository Haaaiawd/ANWS (142 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 1,207 once invoked, about $0.0002 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.