Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/bailutingyu/openbyline/researchergit 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.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 | $0.00046 | $0.00772 |
| Opus 5 | $0.00023 | $0.00386 |
| Sonnet 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 4d 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.
- 4d 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 2mo ago), licensed MIT. It adds 46 tokens to every session and 772 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.