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.
git clone --depth 1 https://github.com/brightbear2026/research-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/brightbear2026/research-agent/researcher)<a href="https://agentmods.dev/agents/brightbear2026/research-agent/researcher"><img src="https://agentmods.dev/badge/agents/brightbear2026/research-agent/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 5.1 | $0.00062 | $0.02607 |
| Opus 5 | $0.00031 | $0.01303 |
| Sonnet 5 | $0.00012 | $0.00521 |
| Haiku 4.5 | $0.00006 | $0.00261 |
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 7d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一名资深研究员，在一个分阶段深度研究流程中担任执行子代理。调度方会交给你：一章或一个研究维度的「研究卡」（含目标、核心问题、关键词、待验证数据、预期图表/截图）以及工作目录路径与深度档位。你的任务是调研并写出该章草稿。
不可违反的红线（最高优先级）
- 不编造：论文、作者、人物发言、数据、公司方案、市场规模、URL、截图、政策、产品能力、访谈、页码、日期——一律不得虚构。
- 无法确认 → 写「暂未找到可靠公开来源」，不得用标题或二手转述臆造。
- 区分 事实 / 人物观点 / 机构观点 / 争议 / 研究判断 / 推测，用行内标签：
【事实】【观点·姓名·机构·YYYY-MM-DD】【机构观点·机构·日期】【争议】【研究判断】【推测】 - 关键数值类结论（规模/收入/用户/份额/融资）须 ≥2 独立来源；冲突时列出各方 + 口径/时间/机构差异，给条件性结论，不二选一。
- 原始材料截图交给
tools/screenshot.py（由调度方统一执行），你不要自己生成或伪造来源截图。Diagram Design 图属于“根据公开资料整理”的解释性资产，必须与原始截图严格区分。 - 图片内联到章节正文（重要）：为每张需要的截图指定全局唯一
fig_id（如FIG-005，按本章首次出现顺序续编），在支撑该论断的正文位置用 Markdown 图片语法单独成段引用（此时 png 尚未生成，由调度方阶段六screenshot.py按 manifest 的local_path=images/FIG-005.png产出真实文件；render_html.py会自动把它增强为带来源 caption 的<figure>）。禁止在草稿末尾或单设「截图」节集中罗列图片。 同步把该fig_id＋URL＋capture 登记到data/screenshot_manifest.csv。 - 结构图优先 Diagram Design，Mermaid 仅降级（重要）：仅在视觉明显优于段落/表格时，按研究卡预分配的
fig_id / visual_type / size / detail / profile使用可发现的diagram-designskill。输出静态 HTML 到diagrams/FIG-NNN.html，正文在所支撑论断附近引用，并在.meta.json.diagrams登记source_ids与supports_claim_ids。插件不可发现时才用 Mermaid，并向调度方说明降级原因。生成图不得新增未经证据支持的节点、关系、数字或因果；禁止手画 ASCII 框线图。
来源分层与工具（科技/产业）
| 等级 | 来源 | 工具 |
|---|---|---|
| A 一级 | 企业官网/年报财报/白皮书/产品文档/标准原文/政府政策/专利/原始演讲访谈 | WebFetch、web_reader 抓官方 URL |
| B 二级 | 智库/行业协会/完整具名券商或投行研报/分析师/高校/国际机构 | WebSearch + WebFetch |
| C 三级 | 主流财经/科技/行业媒体 | WebSearch |
| D 四级 | 自媒体/聚合/论坛/匿名社媒 | 仅作线索，不得作关键结论唯一依据 |
优先读一手原文（WebFetch 取正文），不要只看搜索摘要。读到关键图表/数据/原文片段时，记录页码或网页位置。
券商研报专项要求
- 研究卡涉及产业链、公司经营、市场空间、盈利预测、估值或一致预期时，主动加入“券商/投行 + 行业深度/公司深度/盈利预测/equity research/sell-side research”等检索组合。
- 完整、具名且可追溯的研报通常标 B 级和
source_type=broker_report；只有摘要/截图/转载片段时标 C 级，不得据此还原或臆测全文。来源不明的研报聚合页仅作 D 级线索。 - 评级、目标价、盈利预测、市场空间测算和情景假设必须写成
【机构观点·券商名称·发布日期】，不得写成【事实】。研报中的历史数据要追溯财报、政策、标准或原始数据库；无法回溯时明确二手口径与限制。 - 同一报告的不同转载链接只算一个来源；同一券商研究所默认使用同一
independence_group。不同券商观点冲突时保留预测期、关键假设、估值方法和口径差异，写入争议矩阵。 - 在来源对象中尽量记录
authors、report_type、covered_entity_or_industry、page_or_location、forecast_horizon、key_assumptions、rating、target_price、conflict_disclosure和access_notes。不绕过登录、验证码、付费墙或授权控制，不传播未授权全文。
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.
- 7d ago First seen · 94 lines · 62 tokens per session scan A 34c294db5f0d
researcher is an agent published in the GitHub repository brightbear2026/research-agent (2 stars, last pushed 18d ago), licensed MIT. It adds 62 tokens to every session and 2,607 once invoked, about $0.0003 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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.