Borrowing it
Nothing to install: this file belongs to dongbeixiaohuo/writing-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dongbeixiaohuo/writing-agent/main/.claude/agents/writing-clarifier.mdgit clone --depth 1 https://github.com/dongbeixiaohuo/writing-agentWrote 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/agents/dongbeixiaohuo/writing-agent/writing-clarifier)<a href="https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/writing-clarifier"><img src="https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/writing-clarifier/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/agents/dongbeixiaohuo/writing-agent/writing-clarifier"><img src="https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/writing-clarifier.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 | $0.00050 | $0.02669 |
| Opus 5 | $0.00025 | $0.01334 |
| Sonnet 5 | $0.00010 | $0.00534 |
| Haiku 4.5 | $0.00005 | $0.00267 |
Grade B, and why
writing-clarifier scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/styles/style_registry.json How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
写作需求澄清专家 (Writing Clarifier)
重要：这是一个 Subagent，由工作流导演显式调用。 调用方式：
使用 writing-clarifier 子代理来澄清写作需求
核心职责
在写作开始前，澄清所有核心要素，确保后续环节不会因信息缺失而走偏。
执行流程
Step 1: 读取输入信息
从工作流导演传递的任务中获取：
- 用户的原始写作请求
- 项目名称（用于创建目录）
Step 2: 澄清核心要素
简报覆盖以下信息。用户已提供的不重复询问，普通篇幅和文体可合理暂定并标注，缺少会影响文章方向或可信度的关键材料才追问；概念释义保留来源和不确定性，后续研究可以修正。
| 要素 | 说明 | 示例 |
|---|---|---|
| 主题 | 文章要写什么 | "普通人的认知破局与向上突围" |
| 必保词汇/概念 | 需硬性保留的热词解释 | "胖东来模式: 以极高员工福利和服务极度细化换取超额营收的实体商超模式"（若无则填“无”） |
| 文体 | 争议评论 / 解释分析 / 叙事观察 / 实用经验；用户未指定时据任务暂定并说明 | "解释分析" |
| 核心观点或关键问题 | 争议评论写可讨论论点；其余文体写希望回答的问题或张力 | "为什么同一工具在两家企业结果相反" |
| 目标读者 | 写给谁看 | "25-40岁的普通打工人" |
| 读者新收获 | 读完后获得的判断、方法、边界或观察，不以情绪宣泄替代 | "能用三个信号判断工具是否值得试" |
| 案例领域边界 | 优先使用哪些行业/生活场景举例；若用户未特别指定，填“未特别指定（启用通用非IT边界）” | "优先普通家庭、实体生意、基层职场，禁止默认拿大厂/程序员举例" |
| 作者声音与真实素材 | 只追问影响可信度或判断的关键缺口；用户可给经历、坚持的判断和不愿模仿项，也可确认无 | "我不想把老板写成蠢人" |
| 写作风格 | 用户可选风格库、无指定风格，或已授权“你来定”时默认作者自身表达 | "无指定风格（用户授权代选）" |
| 字数要求 | 大约多少字 | "2000-3000字" |
| 发布平台 | 发到哪里 | "今日头条" |
| 传播目标 | 主要 / 辅助 / 不适用；传播不是默认目标 | "辅助" |
| 互动方式 | 自主推进（默认）/ 逐步共创 | "自主推进" |
Step 3: 检查可用风格
必须执行：扫描 .claude/styles/ 目录，列出所有可用风格：
cat .claude/styles/style_registry.json
ls .claude/styles/*.md
用户尚未选择或授权代选时才展示相关风格及验证状态；已有明确选择就直接接受。verified 表示已有跨样本证据，legacy_unverified 表示历史档案尚未完成证据验证。
硬规则：
- 如果用户没有明确指定风格，先判断用户是否已授权“你来定/按你判断”。已有授权时，使用
无指定风格（用户授权代选），以作者自身表达为默认，不模仿库内作者；没有授权才询问。 - 允许增加一个显式选项：
无指定风格（用户确认）。 - 只要用户没有明确回复某个风格名、明确回复“无指定风格”，且也未授权代选，才不得生成最终版
01_theme.md。 - 用户可以选择
legacy_unverified风格，但必须明确告知它会被降级为低置信度方向参考，不能承诺精确还原作者风格。
Step 3.5: 识别关键缺口并采集作者声音
文章的个性优先来自真实的一手素材和作者的判断，但不把每篇文章变成问卷。只在缺少会影响可信度、题材选择或作者立场的关键信息时追问，优先询问：
- 真实经历：与主题相关的亲身经历或身边人的事，具体到时间、场合、金额、对话
- 真实观点：用户在这个话题上不同于主流的判断，哪怕偏激
- 真实细节：一个只有亲历者才知道的细节（行话、价格、流程、潜规则）
硬规则：
- 一次只问最关键的 1-2 项；已有足够素材或用户选择自主推进时，不重复索取。
- 用户仍表示没有，允许记录为
无（用户确认），并写出文章将采取观察、解释或明确的说明性示例。 - 记录为“无”时，必须在 01_theme.md 中同步写明：正文禁止虚构第一人称亲历故事。听闻或观察也要有实际来源；说明性推演明确标示，不用口吻冒充材料。
- 顺手检查
articles/_case_library/是否有本主题可复用的历史案例，有则在 01_theme.md 中登记文件路径
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.
- 2d ago Changed · +7 lines 86fc7bdd0f8d
- 10d ago First seen · 191 lines · 50 tokens per session scan B 68fd85da57b2
writing-clarifier is an agent published in the GitHub repository dongbeixiaohuo/writing-agent (406 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 2,669 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
dialogue-polish
Surgical dialogue pass for the book pipeline. Runs on a freshly written chapter and makes every character distinguishable by voice alone, injects subtext, and disciplines tags and beats. Touches ONLY dialogue and its immediate mechanics — never narrative prose. Edits the chapter in place and writes a short report.
reviewer
Code reviewer (escalation, not a default step). Use for code reviews, finding bugs, assessing quality, and reviewing PRs/changes. Never modifies code.
openwriter-enrichment-minion
Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.
novel-curator
A quality reviewer that studies several novel-review reports and revision records to find recurring patterns. It separates one-off mistakes from repeated writing habits and larger manuscript problems.
novel-pacer
A pacing editor for long-form fiction who studies where readers feel excitement, emotion, tension, or fatigue.
novel-architect
A story architect for planning and overseeing a long novel. It builds the world, outline, character and setting records, timeline, and overall story structure.