What is health-mcp CLAUDE.md?

Project-specific instructions for Claude Code, an AI coding assistant, in the health-mcp repository. They explain which tools and dashboard component library to use and how the project is wired.

Building and editing the dashboard, using Cloudflare Kumo UI components, checking component documentation, and preserving the project's Tailwind, Vite, and theme configuration.

They keep the assistant's changes consistent with the repository instead of making guesses about components, styling, or setup.

How Gavinxiong668/health-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Gavinxiong668/health-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Gavinxiong668/health-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Gavinxiong668/health-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gavinxiong668/health-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/gavinxiong668/health-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gavinxiong668/health-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gavinxiong668/health-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gavinxiong668/health-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gavinxiong668/health-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,993 This file is loaded in full into every session.

When invoked 1,993 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01993	$0.01993
Opus 5.5	$0.00797	$0.00797
Sonnet 5.5	$0.00399	$0.00399
Haiku 4.5	$0.00199	$0.00199

Measured 2mo ago against content hash 6270fbb82f0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

health-mcp 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 2mo 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.

CLAUDE.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — health-mcp

Behavioral guide for Claude Code working in this repo. Extends ~/.claude/CLAUDE.md; project rules win on overlap.

Human-facing project overview: README.md.

Preferred MCPs and tooling

Reach for these before generic alternatives.

Kumo UI (Cloudflare) — the dashboard component library

Package: @cloudflare/kumo — installed in apps/dashboard. Built on Base UI + Tailwind v4.

Docs CLI (use it instead of guessing component APIs):

npx @cloudflare/kumo ls            # list all 42 components grouped by category
npx @cloudflare/kumo doc Button    # full prop schema + examples for one component
npx @cloudflare/kumo docs          # dump every component's docs (very long)

Setup wiring (already done in this repo, keep intact):
- apps/dashboard/src/styles.css imports @cloudflare/kumo/styles/tailwind before tailwindcss and has @source "../node_modules/@cloudflare/kumo/dist/**/*.{js,jsx,ts,tsx}" so Tailwind picks up the utilities Kumo uses.
- apps/dashboard/vite.config.ts registers @tailwindcss/vite.
- apps/dashboard/index.html sets data-mode="dark"|"light" on <html> from localStorage.theme / prefers-color-scheme. Toggle theme by writing that attribute (and persisting to localStorage).
Policy:
- Always check npx @cloudflare/kumo doc <Name> first when reaching for a new Kumo primitive — examples + prop shape live there.
- Prefer the granular @cloudflare/kumo/components/<name> entry point when bundle size matters; the barrel import (@cloudflare/kumo) is fine for general use.
- Use semantic Kumo tokens (bg-kumo-base, text-kumo-strong, text-kumo-subtle, ring-kumo-line, bg-kumo-{success,warning,danger,info}-tint, etc.) instead of raw colors. They handle light + dark automatically via light-dark().
- Compound APIs differ from shadcn: triggers use a render={(props) => …} prop, not asChild. Dialog has Dialog.Root, Dialog.Trigger, then the <Dialog> panel (not <DialogContent> from shadcn). Tabs takes a tabs={[{value,label}]} array, not <TabsList>/<TabsTrigger>.

Read the full file on GitHub · 100 lines

Changes

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.

2mo ago First seen · 100 lines · 1,993 tokens per session scan A 6270fbb82f0d

Subscribe to this mod's changes

health-mcp CLAUDE.md is an instructions file published in the GitHub repository Gavinxiong668/health-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,993 tokens to every session, about $0.0080 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 2026-08-31.

health-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
health-mcp CLAUDE.mdGavinxiong668/health-mcp	Instructions file	1	1mo ago	MIT	A	1,993	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

health-mcp: Instructions file for Claude Code