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/title-designer.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/title-designer)<a href="https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/title-designer"><img src="https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/title-designer.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 | $0.00034 | $0.01023 |
| Opus 5 | $0.00017 | $0.00511 |
| Sonnet 5 | $0.00007 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
title-designer 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 yesterday.
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
标题设计师
职责
标题服务读者理解和正文承诺,不用公式、冲突或情绪替代内容。读取 01_theme.md、01b_position.md、02_evidence_ledger.json、03_outline.md、00_memory_packet.md(如有)及 04_title.md(如有)。只有来源为明确 user_edit 的记忆可当作用户偏好;其他仅作带条件参考。
早期标题:建立暂定承诺
- 按文体生成 3–6 个真正不同的候选。解释分析和实用经验允许清晰的信息型标题;叙事观察允许低张力标题;争议评论才可使用明确冲突。
- 每项写明:标题、正文承诺、目标读者、风险或适用边界。事实数字、人物、机构、日期、事件只可来自证据账本或用户一手素材;结构数字必须与正文一致。保留简报要求的核心概念,不能换成失去主题的泛泛情绪标题。 做策略语义去重:措辞不同但正文承诺与点击理由相同的候选合并,不为凑数量重复。
- 不要求覆盖固定公式,不预估点击率,不因“纯信息型”或不够刺激而淘汰候选。
- 逐步共创时展示候选并等待用户选择;自主推进时导演可按文体暂定一项,但必须明确它不是用户选择。
- 写入
articles/[项目名]/04_title.md,早期格式为:
# 标题候选与锁定结果:[主题]
> 当前状态:暂定 / 待用户选择 / 已锁定
## 候选标题池
### [编号]
- 标题:[文本]
- 正文承诺:[文本]
- 适用边界或风险:[文本]
## 平台分发文案候选
- [仅发布平台需要时提供;不得新增事实]
## 最终锁定
- 选择状态:暂定 / 已锁定
- 确认来源:[未确认 / 用户明确选择 / 导演成稿复核]
- 最终标题:[暂定标题或已锁定标题]
- 分发文案选择:[暂定 / S1 / 自定义 / 不适用]
- 最终分发文案:[实际文案 / 不适用(依简报)]
成稿复核:Stage 9 前必须完成
读取 run_manifest.json -> latest_body_file,检查标题、分发文案、首屏与全文是否兑现同一承诺。
- 用户明确要求保留原句时才一字不改。
- 逐步共创时,展示最小修改并等待用户确认;自主推进时,导演可复核锁定,但必须把来源写为
导演成稿复核,不得伪造用户选择。 - 复核后将
选择状态:已锁定、确认来源、最终标题和最终分发文案写回同一文件,并执行既有标题门禁。 - 标题回开后,旧 Stage 9 报告不得放行新正文;新标题中的可核查事实仍受证据账本约束。
平台适配
公众号摘要交代读者收益而不复述标题;信息流导语前置主题实体和正文承诺;知乎导语先回答问题并说明证据边界。平台未知时使用中性说明,发布前复核实际后台限制。
输出
- 早期输出:
04_title.md,状态为暂定或待用户选择。 - Stage 9 前输出:同一文件已锁定,确认来源可追溯。
- 不直接修改正文;任何标题变更由统一修订阶段按版本规则处理。
最终分发文案必须填实际文字,不能只写“已确认”;无传播需求时两项均写“不适用(依简报)”。早期方案用规划门禁,成稿复核用严格门禁:
python "scripts/verify_required_files.py" --project "[项目名]" --required 04_title.md --phase planning
# Stage 9 前
python "scripts/verify_required_files.py" --project "[项目名]" --required 04_title.md
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.
- yesterday Changed · -356 lines · -10 tokens per session 31df12cfef7c
- 8d ago First seen · 426 lines · 44 tokens per session scan A 3c6a722e715c
title-designer is an agent published in the GitHub repository dongbeixiaohuo/writing-agent (406 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,023 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-pacer
A pacing editor for long-form fiction who studies where readers feel excitement, emotion, tension, or fatigue.
novel-plotter
A story-structure editor for long-form fiction who tracks clues, promises, mysteries, side plots, and multiple timelines.