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.
git clone --depth 1 https://github.com/JS-mark/skillsWrote 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/commands/js-mark/skills/write)<a href="https://agentmods.dev/commands/js-mark/skills/write"><img src="https://agentmods.dev/badge/commands/js-mark/skills/write/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/commands/js-mark/skills/write"><img src="https://agentmods.dev/badge/commands/js-mark/skills/write.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 | $0.00009 | $0.00683 |
| Opus 5.5 | $0.00004 | $0.00273 |
| Sonnet 5.5 | $0.00002 | $0.00137 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
write 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 1mo 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.
What it actually says
/write 小说创作命令
默认存储路径 ~/Desktop/novel/，用户可通过 /write /path/to/my-novel 或对话中指定自定义路径。确定后的路径记为 <NOVEL_ROOT>。
第一步：确定路径并加载存档（必须先执行）
- 确定
<NOVEL_ROOT>：- 如果命令带参数（如
/write ~/Documents/my-story），使用该路径 - 如果用户之前在对话中指定过路径，沿用该路径
- 否则使用默认路径
~/Desktop/novel/
- 如果命令带参数（如
- 使用 Glob 检查
<NOVEL_ROOT>/是否存在 - 如果存在，并行读取以下文件：
<NOVEL_ROOT>/outline.md（故事大纲）<NOVEL_ROOT>/characters.md（角色档案）<NOVEL_ROOT>/progress.md（创作进度）
- 使用 Glob 查找
<NOVEL_ROOT>/chapters/**/*.md，读取最近 1-2 章恢复上下文 - 向用户汇报当前状态：
📖 已加载创作存档 存储路径：<NOVEL_ROOT> 书名：《XXX》 当前进度：第X卷 · 第XX章 上章概要：XXX 下章预告：XXX
第二步：判断并执行
-
如果
<NOVEL_ROOT>/outline.md不存在：- 全新创作
- 使用 AskUserQuestion 询问是否使用默认路径
~/Desktop/novel/，还是自定义路径 - 确认后使用 Bash 创建
<NOVEL_ROOT>/及chapters/子目录 - 以热情友好的语气打招呼，介绍自己是创作搭档
- 询问用户想创作什么类型的小说
- 引导进入故事大纲阶段
-
如果大纲存在但
<NOVEL_ROOT>/characters.md不存在：- 大纲已完成，角色档案未完成
- 引导用户进入角色设计阶段
-
如果大纲和角色都存在：
- 根据 progress.md 和大纲确定下一章走向
- 直接开始创作下一章
第三步：创作输出
创作时
- 严格按照故事大纲推进
- 每章 3000-5000 中文字符
- 章末必须有钩子
- 如需素材，使用 WebSearch 搜索
创作后
- 使用 Write 保存章节到
<NOVEL_ROOT>/chapters/第X卷/第XXX章-标题.md - 使用 Write/Edit 更新
<NOVEL_ROOT>/progress.md - 附上进度报告
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.
- 1mo ago First seen · 66 lines · 9 tokens per session scan A 21a5c197546a
write is a command published in the GitHub repository JS-mark/skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 683 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.