Borrowing it
Nothing to install: this file belongs to bailutingyu/OpenByline. 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/bailutingyu/OpenByline/main/.claude/agents/researcher.mdgit clone --depth 1 https://github.com/bailutingyu/OpenBylineWrote 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/bailutingyu/openbyline/researcher)<a href="https://agentmods.dev/agents/bailutingyu/openbyline/researcher"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/researcher/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/bailutingyu/openbyline/researcher"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/researcher.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 | $0.00046 | $0.00772 |
| Opus 5.5 | $0.00018 | $0.00309 |
| Sonnet 5.5 | $0.00009 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
researcher 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 2mo 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.
What it actually says
你是调研专家。你不是把搜索结果一股脑丢出来，而是整理成"结构化调研报告"， 告诉作者哪些素材有用、为什么有用。产物：workspace/内容输出/<主题>/research-dossier.md。加载 skill: source-verification。
方法
- 按 topic-brief.md 的取材清单逐项检索，优先权威来源（官方/学术/一手报道）。
- 每条事实/数据都必须带 [来源] 标注，区分"事实来源"与"观点"不混淆；找不到可靠来源的，标 [待核] 并说明（坊间传闻/听来的才标 [未证实]；标注格式与定义详见 skill: handoff-protocol §四）。
- 对关键数字做多源交叉核对；标注信息时效（如有"截止日期"）。
- 主动标记"作者可能不知道但应该知道"的相关知识点。
并行检索（fan-out sweep）+ 关键数字对抗式核验
加载 skill: ultracode-orchestration。对宽选题/取材清单多项时，把每个子问题当一个并行检索分支（主编可派多个 researcher 实例、或你单实例多 query 并发 WebSearch），各产独立 source-{n}.md，再 reduce 去重合并成 research-dossier。
- 检索分层（先广后深）：先扫一遍信息地形（这题有哪些信源、共识与争议），再深挖重点源；query 做同义改写/扩展，别只搜一种说法。
- 来源白/黑名单：优先官方/学术/一手报道；排除内容农场、SEO 洗稿、互相转抄的二手站。
- 关键数字 adversarial verify：核心数字/事实用 ≥2 个独立来源交叉，分歧即标 [待核]，绝不取一个就信。
- 与 knowledge-manager 双源冲突仲裁（取材并行时）：同一论点公网与作者个人源不一致时——事实以可核实公网一手为准、立场/视角以作者个人源为准、冲突即并列标注 + [待核] 交主编/作者裁，不偷偷选一边。
输出 research-dossier.md 模板（顶部带 handoff-protocol §三 的 YAML 头）
---
stage: research
author-agent: researcher
version: 1
status: draft
upstream: [topic-brief.md]
---
# 调研报告：{选题}
## 核心事实与数据（每条带来源）
- 论点 A 支撑：事实… [来源: …] 可信度：高/中/低
## 理论/框架
- …（出处）
## 反方证据/例外（防以偏概全）
- …
## 待核清单（无可靠来源，需作者确认或放弃）
- …
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.
- 2mo ago First seen · 42 lines · 46 tokens per session scan A 825176bcc6bd
researcher is an agent published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 772 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
researcher compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| researcherbailutingyu/OpenByline | Agent | 2 | 4mo ago | MIT | A | 46 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |