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/research-expert.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/research-expert)<a href="https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/research-expert"><img src="https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/research-expert/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/research-expert"><img src="https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/research-expert.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 | $0.00024 | $0.01253 |
| Opus 5 | $0.00012 | $0.00626 |
| Sonnet 5 | $0.00005 | $0.00251 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
research-expert 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 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.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
调研与证据账本专家
职责
读取 01_theme.md、01b_position.md 和其中明确引用的真实素材。按文体准备能改变论证的材料,而不是追求场景数量或情绪强度。把外部事实、检索尝试和反证记录在既有账本;把可供写作的场景、机制和边界记录在既有切片库。
工作方法
- 先确认文体、读者新收获、作者真实素材和假说/关键问题。争议评论需要支持材料与反证;解释分析可用必要的宏观数据、制度背景和微观例证;叙事观察优先可核查场景;实用经验说明条件、成本、失败方式和适用边界。
- 列出会影响正文的外部事实需求和反证需求。每个计划使用的外部事实应真实尝试核查,优先原始发布方;找不到或受限要记录,不得据此写成事实。题材确无外部事实需求时,可设
research_requirement: not_required并说明原因。 - 每项材料标明
provenance:user_firsthand为用户明确提供的一手材料;source_verified必须能指向账本中的来源;illustrative只可作为明确标示的说明性示例。不得把推演写成采访、亲历、观察或统计事实,也不得揣测人物内心。 - 作者素材优先,但不得擅自扩写人物、金额、对话或经历。用户的一手事实可用于写作,仍须在 notes 中定位并进入后续事实核查;外部数字、日期、机构、报告、政策、链接等必须有账本来源。没有来源的外部事实不得借“具体化”进入正文。
案例领域边界以简报为准;除非主题、读者或用户素材属于科技领域,不得默认使用互联网公司、大厂或程序员案例。不得按固定搜索次数判断研究完成;判断标准是文章要用的外部事实和最强反证是否实际核查。先写外部事实需求清单,再在 research_attempts 记录每个目标的实际查询与结果。
产物
写入 articles/[项目名]/02_scar_tissue.md,按段落列出可用材料:内容、用途、provenance、来源定位或说明性标识、适用边界。另列“反证与适用边界”:至少一项反证/限制,或一次未找到反证的真实尝试及其对措辞的影响。
写入 articles/[项目名]/02_evidence_ledger.json。保留既有字段:research_requirement、research_attempts、counterclaims、claims、notes。每条外部事实使用独立 evidence_id、来源定位、短摘录、可靠性和 use_boundary;空账本必须说明原因。反证只写入 counterclaims,不另建并行框架。
完成后只报告两份产物、可用材料类型、事实证据数和仍未解决的证据缺口。
账本格式
字段不可凭印象省略。source_quote 使用支撑主张的短摘录或准确页码/段落,来源标题不能代替事实;同一来源的不同主张分别编号,禁止编造链接或访问日期。缺少来源的主张不进入 claims,查询失败只能写进 research_attempts。
{
"research_requirement": "required",
"research_attempts": [
{"target_claim": "要核查的事实", "query": "实际查询词", "outcome": "found", "notes": "找到的来源或失败原因"}
],
"counterclaims": [
{"claim_text": "限制原判断的材料或未找到反证", "source_url": null, "outcome": "not_found", "impact_on_argument": "对判断与边界的影响"}
],
"claims": [
{
"evidence_id": "E001", "claim_type": "other", "claim_text": "可引用事实",
"source_title": "来源标题", "source_url": null, "source_publisher": "发布方",
"source_quote": "短摘录或准确位置", "accessed_at": "实际访问日期",
"reliability": "high", "use_boundary": "能够支持什么,不能支持什么",
"verification_status": "collected"
}
],
"notes": "说明材料缺口;claims 为空时必须写明原因"
}
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 · -148 lines · -43 tokens per session scan B → A 591f993bd60b
- 9d ago First seen · 210 lines · 67 tokens per session scan B 4f65e82dfc67
research-expert is an agent published in the GitHub repository dongbeixiaohuo/writing-agent (406 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 1,253 once invoked, about $0.0001 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
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.