Taiwan-Health-MCP: Instructions file for Codex

AGENTS.md

Taiwan-Health-MCP AGENTS.md is an instructions file for Codex, OpenCode from healthymind-tech/Taiwan-Health-MCP. It costs 1,696 tokens per session, scanned A, original, MIT.

A repository guide for a health-data project built with Node.js, TypeScript, Next.js, and a database. It explains the folder layout, development commands, coding rules, and testing practices.

In plain words
What is it for?
Use it when changing, building, or testing the Taiwan Health MCP repository, especially its backend, web interface, database, data loaders, or documentation.
Why use it?
It gives a coding agent the project’s current structure and rules, while pointing out old files and approaches that should be ignored.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is healthymind-tech/Taiwan-Health-MCP's own configuration. It tells Codex and OpenCode how to work on Taiwan-Health-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Taiwan-Health-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to healthymind-tech/Taiwan-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/healthymind-tech/Taiwan-Health-MCP/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/healthymind-tech/Taiwan-Health-MCP

Made for: Codex, OpenCode.

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.

agentmods badge for Taiwan-Health-MCP AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/healthymind-tech/taiwan-health-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/healthymind-tech/taiwan-health-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/healthymind-tech/taiwan-health-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/healthymind-tech/taiwan-health-mcp/agents-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.

agentmods 80×15 button for Taiwan-Health-MCP AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/healthymind-tech/taiwan-health-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/healthymind-tech/taiwan-health-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,696 This file is loaded in full into every session.
When invoked 1,696 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01696 $0.01696
Opus 5 $0.00848 $0.00848
Sonnet 5 $0.00339 $0.00339
Haiku 4.5 $0.00170 $0.00170

Measured 13d ago against content hash b213152fe9e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Taiwan-Health-MCP 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 13d 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.

AGENTS.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

node-server/ contains the entire backend (Node.js / TypeScript): the MCP server (src/server.ts, src/mcp.ts), the service layer (src/*Service.ts — ICD, drug, lab, FHIR, SNOMED, …), the admin console backend (src/admin/*.ts), and every dataset loader (src/loaders/*.ts — ICD, LOINC, SNOMED, RxNorm, FHIR IG, Taiwan FDA drug/supplements/food, embeddings). web/ is the Next.js front-end (public pages in app/, the admin SPA in admin-app/, verbatim legacy HTML in legacy/). db/ holds schema.sql and migrations/. docs/ is the MkDocs source for the published site. src/prompts/ holds runtime LLM prompts and is the only thing left under src/. fhir-code/ holds source datasets (untracked; see docs/data-sources/test-data.md).

There is no Python in this repository. The backend was fully migrated to Node in 2026-07; src/*.py, loader/ and requirements.txt are gone. pyproject.toml, pytest.ini and requirements-dev.txt are dead leftovers — ignore them. requirements-docs.txt is the live one (MkDocs).

Root admin-ui/ is a dead leftover (Vite React, nothing builds or references it). The real admin SPA lives in web/admin-app/, mounted under the Next.js /admin catch-all. Edit web/admin-app/, never root admin-ui/.

Build, Test, and Development Commands

  • docker compose up -d: start the full stack (nginx, web, app, admin-worker, postgres, pgbouncer, redis, minio). nginx on :8080 (WEB_PORT) is the only published entry pointapp is not reachable on :8000 from the host.
  • docker compose build app web && docker compose up -d --no-deps app web: redeploy after a code change.
  • admin-worker is a separate image (Dockerfile.worker) that executes all import jobs. Any node-server/ change that touches job/loader code (adminJobs.ts, the *Service.ts layer, loaders/*) must also be deployed to it: docker compose build admin-worker && docker compose up -d --no-deps admin-worker. Rebuilding only app leaves the worker running stale code.
  • cd node-server && npm run build: compile TypeScript to dist/.
  • cd node-server && npm test: run the test suite (node --test over src/**/*.test.ts).
  • cd node-server && npm run typecheck: type-check without emitting.
  • Data import: enable the admin console (ADMIN_ENABLED=true + credentials) and import modules from the Modules tab; admin-worker runs the loader stages. There is no standalone data-loader container and no loader CLI.

Read the full file on GitHub · 103 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.

  1. 13d ago First seen · 103 lines · 1,696 tokens per session scan A b213152fe9e6

Subscribe to this mod's changes

Taiwan-Health-MCP AGENTS.md is an instructions file published in the GitHub repository healthymind-tech/Taiwan-Health-MCP (163 stars, last pushed 1mo ago), licensed MIT. It adds 1,696 tokens to every session, about $0.0085 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.

Related

Other instructions, from other repositories