Borrowing it
Nothing to install: this file belongs to wananing/Smart-Health-Assistant. 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/wananing/Smart-Health-Assistant/main/CLAUDE.mdgit clone --depth 1 https://github.com/wananing/Smart-Health-AssistantWrote 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/wananing/smart-health-assistant/claude-md)<a href="https://agentmods.dev/instructions/wananing/smart-health-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/wananing/smart-health-assistant/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/wananing/smart-health-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/wananing/smart-health-assistant/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 | $0.04952 | $0.04952 |
| Opus 5.5 | $0.01981 | $0.01981 |
| Sonnet 5.5 | $0.00990 | $0.00990 |
| Haiku 4.5 | $0.00495 | $0.00495 |
Grade A, and why
Smart-Health-Assistant 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 21d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Smart Health Assistant (大健康智能助手) — a mobile-first, Chinese-language healthcare AI platform. A FastAPI + LangGraph backend routes each user turn to a specialist agent (clinic triage, insurance, lab-report interpretation, pharmacy, general advisor) and streams the reply over SSE, including structured UI card events that the React frontend renders. AGENTS.md at the repo root holds the team's contribution conventions (commit style, PR expectations, privacy rules) and applies alongside this file.
Development Commands
Backend (backend/, Python ≥3.13, managed with uv)
cd backend
uv sync # install deps from uv.lock
cp .env.example .env # then set LLM_PROVIDER + the matching API key
uv run python -m rag.ingest # first run: build the RAG vector store (~90MB model download)
uv run python -m rag.ingest --rebuild # after editing rag/documents/*.md
uv run uvicorn main:app --reload --port 8000 # dev server
# Regenerate the graph diagram after changing the graph shape
uv run python -c "from agents.graph import master_app; print(master_app.get_graph(xray=1).draw_mermaid())" > ../docs/images/graph.mmd
Server-side conversation memory is on by default (CHECKPOINTER=memory). Set CHECKPOINTER=sqlite (+ optional CHECKPOINT_DB_PATH, default checkpoints.sqlite, gitignored) to survive restarts. Details: docs/langgraph-runtime.md.
Tests are split into two kinds. Keep them separate when running or adding tests:
# Deterministic unit tests (unittest, no network, no API key). pytest also works.
uv run python -m unittest test_llm.py test_vision.py test_main_config.py test_observability.py test_evals.py
uv run python -m unittest test_clinic_graph.py test_graph_build.py # clinic subgraph + checkpointer wiring
uv run python -m unittest test_handoff.py test_cards.py # Command handoffs + agent-emitted cards
uv run python -m unittest test_skill_tools.py # skill tool argument schemas
uv run python -m unittest test_voice_protocol.py test_voice_providers.py test_voice_render.py test_voice_gateway.py test_voice_clinic.py test_voice_volc_protocol.py test_voice_runs.py test_voice_contract.py # voice gateway (fake ASR/TTS)
uv run python -m unittest test_llm.py # one file
uv run python -m unittest test_llm.ModelSettingsTests.test_legacy_ark_configuration_remains_the_default # one test
# Manual scripts that call the configured LLM (need a real API key in .env; run explicitly, never in CI)
uv run python test_router.py # router prompt classification check
uv run python test_clinic.py # streams a clinic turn end-to-end
uv run python test_exit_phrases.py # exit-phrase routing
uv run python test_clinic_issue.py
uv run python test_voice_live.py loopback # real Volcengine ASR/TTS round trip (needs VOLC_VOICE_API_KEY)
uv run python test_voice_live.py e2e --calls 2 # live voice calls against a running server, prints latencies
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.
- 21d ago Changed · +8 lines · +782 tokens per session d436b60dc4be
- 29d ago Changed 9ecda984728e
- 1mo ago First seen · 148 lines · 4,170 tokens per session scan A b4107e4fde16
Smart-Health-Assistant CLAUDE.md is an instructions file published in the GitHub repository wananing/Smart-Health-Assistant (35 stars, last pushed 18d ago), licensed MIT. It adds 4,952 tokens to every session, about $0.0198 per session on Opus 5.5. 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 2026-09-24.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).