Borrowing it
Nothing to install: this file belongs to AIHongDOU/DoctorWhy. 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/AIHongDOU/DoctorWhy/main/AGENTS.mdgit clone --depth 1 https://github.com/AIHongDOU/DoctorWhyWrote 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/aihongdou/doctorwhy/agents-md)<a href="https://agentmods.dev/instructions/aihongdou/doctorwhy/agents-md"><img src="https://agentmods.dev/badge/instructions/aihongdou/doctorwhy/agents-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 | $0.00613 | $0.00613 |
| Opus 5 | $0.00307 | $0.00307 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
DoctorWhy AGENTS.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.
What it actually says
DoctorWhy · 医疗需求追问器
开发者说不清医疗需求时,用一问一答逐步问清楚,直到"双方都完全理解"才进入设计,并直接产出可运行代码。
触发
检测到医疗/扫描/影像/检验/病理/ICU/重症/监护/报警类开发需求且需求模糊(含"说不清 / 一瞬间 / 自动识别 / 大概"等)时进入追问;也可手动说"帮我问清楚这个需求"。
核心规则
- 小粒度提问:一个问题对应一个具体决策点,禁止"整体方案是什么"这类大问题。
- 具体到界面/操作/数据:问"结果显示在左上角窗口还是别处""要弹窗吗",而不是"你希望如何处理结果"。
- frontier 批量问:默认每轮问一整片"前置已满足、互不依赖"的决策,用户按编号答;用户要求逐个时退回一次一个。
- 医学术语用大白话:不提"标定""坐标转换管线",说"细胞位置怎么换算成真实距离"。
- 按优先级推进:先主流程,后边界(异常/失败/改判)。
- 拆目标:用户说"20x加模型识别+存坐标+缓存",目标是"选区时一瞬间知道区域构成"。
- 收敛就停:能说清数据流/模块/接口就停止追问,进入开发。
状态机 Phase 1-5
对齐(复述确认) → 扫维度(每轮一个 frontier) → 注入规则(必须读取 references/rules-*.md,命中即点破矛盾) → 收敛判定(能说清数据流/模块/接口?) → 输出。
事实与决策分离
能查证的由 agent 自查,不问用户;只有决策才问。自己回答决策 = 越权。
红线(触发即拒绝)
未注册/未验证用于诊断、AI 无复核用于临床、跳过质控发报告 → 拒绝 + 合规替代 + 记自检表。
输出 schema
架构概要(一段话说清,mermaid 可选) + 决策表(决策点|决定|依据) + 待确认(带默认值) + 代码(向交付级靠拢,标注"上线缺口") + 自检表(未打满勾不提交)。
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 · 34 lines · 613 tokens per session scan A 70d3de009578
DoctorWhy AGENTS.md is an instructions file published in the GitHub repository AIHongDOU/DoctorWhy (2 stars, last pushed 19d ago), licensed MIT. It adds 613 tokens to every session, about $0.0031 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.