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 skills add brightbear2026/research-agent --skill deep-researchgit 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/skills/brightbear2026/research-agent/deep-research)<a href="https://agentmods.dev/skills/brightbear2026/research-agent/deep-research"><img src="https://agentmods.dev/badge/skills/brightbear2026/research-agent/deep-research.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 | $0.00064 | $0.00774 |
| Opus 5 | $0.00032 | $0.00387 |
| Sonnet 5 | $0.00013 | $0.00155 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
deep-research 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 8d 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
deep-research 技能
本技能是「深度研究」流程的入口。推荐用 /deep-research <课题> [depth=快速|标准|深度] [mode=regular|plan|execution] 触发。三模式由 workflow_policy.py 状态机统一控制：常规模式确认三次，计划模式仅大纲后确认并停止，执行模式仓库流程零确认。
何时使用
用户要求就某课题做系统、广泛、深入、可验证的研究，并产出双格式报告时。
流程（六阶段，确认点由状态机决定）
- 启动：课题定义/边界、≥15 研究问题、中英文关键词矩阵、搜索策略 → 检查点。
- 广泛调研：论文/人物/头部企业/政策标准/市场数据/券商与投行研报/案例七维搜索 + 证据库脚手架 + 发现/争议/缺口 → 检查点。
- 大纲：基于调研生成三级大纲（每章目标/问题/证据/图表/截图/可选 Diagram Design 图/结论）→ 检查点。
- 分章深研：登记逐章状态，每章写研究卡并派
researcher执行；完成时校验.md/.meta.json配对，中断后从首个未完成章节继续。 - 组装与总编辑：源标签
[[SRC|...]]去重→分配[n]→写data/citations.csv与_assembled_report.md；由report-editor基于 argument map 压缩、去重、重组为research_report.md。 - 交付：
screenshot.py（真实截图）→diagram_assets.py（可选解释图）→render_html.py→evidence.py→qc.py --strict（含事实就近引用、独立来源、内容禁忌、最低完整度、图片与事实漂移）终检 →workflow_policy.py record-debt→ README。两段式交付：核心检查exit 0即可交付；死链/链接警告/来源时效/段落级数值来源等 advisory 项写入data/qc_debt.json作为已跟踪技术债，不阻断交付。
红线（见 CLAUDE.md）
不编造任何来源/数据/观点/截图；无法确认写「暂未找到可靠公开来源」；区分事实/观点/判断；关键数值 ≥2 独立来源；截图必须真实（失败落占位，禁止伪造）；引用闭环、截图、漂移审计、可读性等核心检查以 qc.py exit 0 为准，advisory 项（死链等）入 qc_debt.json 异步收尾、不阻断交付。
完整执行细则
见 .claude/commands/deep-research.md（canonical）。工具用法见 CLAUDE.md。
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.
- 8d ago First seen · 26 lines · 64 tokens per session scan A 2a45156b7762
deep-research is a skill published in the GitHub repository brightbear2026/research-agent (2 stars, last pushed 19d ago), licensed MIT. It adds 64 tokens to every session and 774 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.