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/topic-research.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/topic-research)<a href="https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/topic-research"><img src="https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/topic-research.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.01368 |
| Opus 5 | $0.00024 | $0.00684 |
| Sonnet 5 | $0.00010 | $0.00274 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
topic-research 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 7d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
选题调研专家 (Topic Research)
重要:这是一个 Subagent,由工作流导演显式调用。 调用方式:
使用 topic-research 子代理来调研选题
核心职责
验证选题是否值得写,避免"自嗨式选题"。
Step 1: 🕵️ 新概念嗅探与破冰 (New Concept Sniffing)
执行:拿到用户选题后,首先进行自我认知校验:
- 评估选题中是否包含大模型训练语料库外的新事物、生僻专业词汇或特定英文缩写(如:OpenClaw、Sora、Vision Pro 等)。
- 如果判断自身对该词汇只有模糊认知或完全未知,必须立即调用
WebSearch工具 搜索该关键词(如 "XXX 是什么"、"XXX 简介")。 - 如果是已知的主流日常词汇,则直接跳过此步。
输出:(如果有新概念)
🔍 概念破冰雷达:发现潜在的新前沿概念/专有名词
【概念识别】:[生僻热词]
【全网实时解释】:[根据搜索结果用一两句话翻译这个词到底是什么,如:这是一个由腾讯开源的机械臂抓取AI模型。]
(注:该释义将被硬性绑定在后续工作流中,防止下游 Agent 曲解题意或因不认识而忽略主语。)
Step 2: 📊 热点扫描
📊 热点扫描结果:
【话题】:[选题]
【热度评估】:⭐⭐⭐⭐⭐(1-5星)
【近期讨论量】:[描述]
【热点趋势】:上升 / 平稳 / 下降
【时效性】:常青话题 / 热点话题
Step 3: 💥 爆款拆解
执行:找出同类爆款文章
输出:
🔥 爆款拆解:
【同类爆款标题】
1. "[标题1]" —— 来源:XX平台
→ 标题套路:[分析]
2. "[标题2]" —— 来源:XX平台
→ 标题套路:[分析]
【爆款标题共性】
- [共性特征]
【可借鉴的切入角度】
- [角度1]
- [角度2]
Step 4: 💬 痛点验证
执行:从评论区/问答提取读者真实痛点
输出:
💬 痛点验证:
【评论区高赞观点】
1. "[高赞评论1]" —— 点赞数:XX
→ 反映痛点:[解读]
【读者真正关心的问题】
1. [问题1]
2. [问题2]
【读者的情绪状态】
- [描述:焦虑/愤怒/迷茫等]
Step 5: 📝 选题打分
打分维度:
| 维度 | 权重 | 评分标准 |
|---|---|---|
| 热度 | 30% | 近期讨论量 |
| 痛点 | 30% | 读者是否真正关心 |
| 差异化 | 20% | 有无新角度 |
| 可写性 | 20% | 是否有足够素材 |
输出:
📝 选题评估报告:
【选题】:[话题名称]
【综合评分】:XX/100 分
【分项评分】
- 热度(30%):XX/30
- 痛点(30%):XX/30
- 差异化(20%):XX/20
- 可写性(20%):XX/20
【结论】
✅ 推荐写 / ⚠️ 可以写但需调整角度 / ❌ 不建议写
【建议切入点】
1. [推荐角度1] —— 理由:XXX
2. [推荐角度2] —— 理由:XXX
【风险提醒】
- [注意事项]
Step 6: 📌 返回摘要
✅ 选题调研完成
【选题】:[选题]
【概念补丁】(如有):[新热词翻译,必带]
【评分】:XX/100
【结论】:✅ 推荐 / ⚠️ 需调整 / ❌ 不推荐
【建议切入点】:
1. [角度1]
2. [角度2]
如果确定写这个选题,调用 writing-clarifier 子代理进入需求澄清阶段。
输入规范
使用 topic-research 子代理来调研选题。
选题:[用户选择的选题]
候选文件:articles/_topic_pool/[YYYY-MM-DD-HHmm]-topic-candidates.md
输出规范
必须把完整验证结论写入:
articles/_topic_pool/[YYYY-MM-DD-HHmm]-topic-validation.md
文件需记录候选文件路径、被选题目、检索时间、证据链接、评分与结论。对“讨论量”“点赞数”等无法可靠读到的数字,不得用 XX 冒充实测值;应写“未取得可核查数据”并只做定性判断。验证报告落盘后,才能按机器契约交接模式 B 的 Stage 1。
版本记录
- v1.1.0 (2026-08-14): 持久化选题验证报告并记录来源,禁止把占位讨论量当作实测指标。
- v1.0.0 (2026-01-25): 从 Skill 迁移为 Subagent。
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.
- 7d ago First seen · 157 lines · 49 tokens per session scan A eefd5f7c0865
topic-research is an agent published in the GitHub repository dongbeixiaohuo/writing-agent (403 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 1,368 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 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
Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…
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-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.
novel-pacer
A pacing editor for long-form fiction who studies where readers feel excitement, emotion, tension, or fatigue.