writing-agent: Agent for Claude Code

.claude/agents/research-expert.md

research-expert is an agent for Claude Code from dongbeixiaohuo/writing-agent. It costs 24 tokens per session (1,253 once invoked), scanned A, original, MIT.

A research agent that digs up highly specific human details, costs, and industry practices for an article, while keeping a ledger of factual sources.

In plain words
What is it for?
Use it to research an article’s topic, identify what external facts need verification, and record supporting sources.
Why use it?
It gives the writer concrete material and makes facts such as dates, names, numbers, and policies traceable to evidence.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is dongbeixiaohuo/writing-agent's own configuration. It tells Claude Code how to work on writing-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything writing-agent configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/dongbeixiaohuo/writing-agent/main/.claude/agents/research-expert.md
Clone the repo
git clone --depth 1 https://github.com/dongbeixiaohuo/writing-agent

Made for: Claude Code.

Wrote 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.

agentmods badge for research-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/research-expert/github.svg)](https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/research-expert)
Your own site
<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.

agentmods 80×15 button for research-expert

Your own site · 80×15
<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>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,253 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 591f993bd60b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.claude/agents/research-expert.md · 62 lines

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.md01b_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

  1. 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。
  2. 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。
  3. 每项材料标明 provenanceuser_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。
  4. 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_requirementresearch_attemptscounterclaimsclaimsnotes。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"
}

Read the full file on GitHub · 62 lines

Changes

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.

  1. 2d ago Changed · -148 lines · -43 tokens per session scan B → A 591f993bd60b
  2. 9d ago First seen · 210 lines · 67 tokens per session scan B 4f65e82dfc67

Subscribe to this mod's changes

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.