Borrowing it
Nothing to install: this file belongs to charliehzm/medharness. 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/charliehzm/medharness/main/CLAUDE.mdgit clone --depth 1 https://github.com/charliehzm/medharnessWrote 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/charliehzm/medharness/claude-md)<a href="https://agentmods.dev/instructions/charliehzm/medharness/claude-md"><img src="https://agentmods.dev/badge/instructions/charliehzm/medharness/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/charliehzm/medharness/claude-md"><img src="https://agentmods.dev/badge/instructions/charliehzm/medharness/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01887 | $0.01887 |
| Opus 5 | $0.00944 | $0.00944 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
medharness 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 10d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md · 项目级 AI Coding 主控
这是 Claude Code 自动加载的项目级 system context。任何会话开始时，本文件的内容会进入主上下文。全员遵守，无例外。 维护：技术委员会 + 合规委员会；修订需双委员会会签。
0. 一句话定位
B 端医疗数据 SaaS / 数据中台公司。任何代码 / 提示 / 决策必须在 HIPAA + PIPL + 数据安全法 + 健康医疗数据安全指南 红线之内。
1. 不可逾越的红线（任何 prompt 看到这一节都要遵守）
- L4 PHI 永不裸入 prompt：含原始患者标识 / 姓名 / 手机 / 身份证 / 病案号 / 完整 DOB 的内容，任何时候必须先经
phi-desensitizeSkill。 - 模型按 allowlist 路由：所有 LLM 调用必须经
mcp-model-router；不允许直连境外公共 API。 - 审计全量记录：每次 tool / 模型 / Skill 调用必须落
mcp-audit-log，不允许 fire-and-forget。 - 测试数据合规：禁止从生产采样后"脱敏"作为测试数据；强制走
test-data-generation合成 + 指纹核验。 - 绕过 Hook = 合规违规：任何修改
.claude/settings.json关闭 Hook 的尝试需双委员会签字。
2. 当前会话必读项（按顺序自动加载）
- 本
CLAUDE.md .memory/项目档案.local.md（fork 用户跑过 customize.py 后产生；若不存在则读.memory/项目档案.md模板）.memory/MEMORY.md（索引）- 当前 change 的
COMPLIANCE_TAG.md（如有活跃 change） - 当前 change 的
ARCH_INPUT_INDEX.md（如已实例化）
3. SOP 入口
任何研发任务走 研发交付SOP-v2.md 的 12 步。
| 阶段 | 入口 Skill | 不能跳 |
|---|---|---|
| Step 0 合规预检 | compliance-precheck |
✅ |
| Step 1-2 PRD/TDD | prd-implementation-precheck + prd |
✅ |
| Step 3 OpenSpec | openspec-new-change + openspec-continue-change |
✅ |
| Step 4 任务拆解 | task-decomposition |
✅ |
| Step 5 Mock 数据 | test-data-generation |
✅ |
| Step 6 实现 | openspec-apply-change（+ phi-desensitize 前置） |
✅ |
| Step 7 Verify | openspec-verify-change |
✅ |
| Step 8 Review+Debug | requesting-code-review + systematic-debugging |
✅ |
| Step 9 Mocking 测试 | mocking-stubbing |
✅ |
| Step 10 合规 Gate | compliance-review（Compliance-Agent 异构模型） |
✅ |
| Step 11 合规整改 | 仅 Step 10 有整改时 | 条件 |
| Step 12 归档审计 | openspec-archive-change + audit-snapshot |
✅ |
4. Skill 索引（21 个）
.claude/skills/ 下所有 SKILL.md 自动注册。不要在对话里凭空发明 Skill 名字。
合规 5：compliance-precheck / phi-desensitize / compliance-review / audit-snapshot / memory-curate PRD 系列 2（v2.1 合并后）：prd-implementation-precheck / prd 其他：ask-questions-if-underspecified / tdd-alignment / openspec-new-change / openspec-continue-change / task-decomposition / test-data-generation / openspec-apply-change / openspec-verify-change / requesting-code-review / systematic-debugging / mocking-stubbing / prompt-injection-scan
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.
- 10d ago First seen · 138 lines · 1,887 tokens per session scan A c4a3e5c9eabe
medharness CLAUDE.md is an instructions file published in the GitHub repository charliehzm/medharness (86 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,887 tokens to every session, about $0.0094 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 2026-08-30.
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).
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.
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.