Borrowing it
Nothing to install: this file belongs to brightbear2026/research-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.
curl -O https://raw.githubusercontent.com/brightbear2026/research-agent/main/CLAUDE.mdgit 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/instructions/brightbear2026/research-agent/claude-md)<a href="https://agentmods.dev/instructions/brightbear2026/research-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/brightbear2026/research-agent/claude-md.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 | $0.02646 | $0.02646 |
| Opus 5 | $0.01323 | $0.01323 |
| Sonnet 5 | $0.00529 | $0.00529 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade A, and why
research-agent CLAUDE.md 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 6d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研究代理项目约定（research-agent）
本仓库是一个面向 Claude Code、Codex/ChatGPT Work 与 Hermes/Agent-Skills harness 的多入口深度研究代理：Claude Code 以 /deep-research <课题> 触发，Codex/ChatGPT Work 以 $deep-research-work 触发，Hermes/兼容 harness 读取根目录 SKILL.md；三者共享同一六阶段状态机、schema v2、聚合与 QC 工具。最终在 projects/<课题slug>/ 落地 Markdown + HTML 报告与证据矩阵——每个课题一个独立 slug 文件夹，互不覆盖。领域定位：科技/产业。
本仓库的来源分层和 QC 阈值按科技/产业研究设计，不默认适用于医疗诊断、治疗建议、法律意见、诉讼策略或个人投资建议。若用户把这些高风险主题放入范围，必须明确提示领域边界，并另行采用相应专业标准、最新法规/指南与合格专家复核；不得把本项目的“QC 通过”表述为专业意见。
不可违反的红线
- 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。
- 无法确认的信息必须写明「暂未找到可靠公开来源」，不得用标题或二手转述臆造内容。
- 截图必须来自 Playwright 真实捕获（
tools/screenshot.py），失败则落占位符 + 索引，禁止用 AI 图/拼接/base64 冒充原始截图。 - 区分 事实 / 人物观点 / 机构观点 / 行业共识 / 争议 / 研究判断 / 推测，不得把观点写成事实、把推测包装成定论。
来源可信度分层（详见 references/source_rubric.md）
| 等级 | 来源类型 | 工具映射（科技/产业） |
|---|---|---|
| A 一级·原始 | 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·权威研究 | 智库、行业协会、具名券商/投行研报、分析师、高校、国际机构报告 | WebSearch + WebFetch |
| C 三级·专业媒体 | 主流财经/科技/行业媒体深度报道 | WebSearch |
| D 四级·一般内容 | 自媒体、聚合站、论坛、匿名社媒、营销软文 | 仅作线索，不得作关键结论唯一依据 |
关键结论不得只依赖 C/D 级来源。
券商研报作为研究输入
- 将券商/投行研报纳入广泛调研和分章深研，重点用于产业链拆解、盈利预测、市场一致预期、估值假设与专家线索。完整、具名、可追溯且披露方法的研报通常为 B 级；转载摘要/截图为 C 级，来源不明的研报聚合为 D 级线索。
- 评级、目标价、盈利预测、市场空间测算等必须标
【机构观点·券商名称·发布日期】，不得写成事实。研报转引的财报、政策、标准和数据库，应尽量回溯原始来源并另行登记，不能把二手数据当作 A 级。 - 同一研报的官网版、平台版和转载版只算一个来源；同一券商研究所默认使用同一
independence_group。关键事实/数值仍须用原始来源或另一独立机构交叉验证。 - 在 chapter meta 的来源对象中标
source_type=broker_report，并尽量记录authors、report_type、covered_entity_or_industry、page_or_location、forecast_horizon、key_assumptions、conflict_disclosure与访问限制。交付时由聚合器生成data/broker_report_list.csv。 - 不绕过登录、验证码、付费墙或授权控制，不传播未授权全文。完整规则见
references/source_rubric.md。
交叉验证
一级数值类结论（市场规模/收入/用户/份额/融资/排名）须 ≥2 独立来源。来源冲突时：列出各数据 + 口径 + 时间 + 机构，进 evidence/controversy_matrix.csv，给条件性结论，不得简单二选一。正文【事实】段中的数值声明同样适用此规则——单一 C/D 级来源支撑的数值会被 qc.py 标记为 advisory（写入 data/qc_debt.json），建议补独立第二来源或改标【推测】。
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.
- 6d ago First seen · 85 lines · 2,646 tokens per session scan A 98799a2095f7
research-agent CLAUDE.md is an instructions file published in the GitHub repository brightbear2026/research-agent (2 stars, last pushed 17d ago), licensed MIT. It adds 2,646 tokens to every session, about $0.0132 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.