medical-codes-mcp-server: Instructions file for Claude Code

CLAUDE.md

medical-codes-mcp-server CLAUDE.md is an instructions file for Claude Code from cyanheads/medical-codes-mcp-server. It costs 6,018 tokens per session, scanned A, a copy of obsidian-mcp-server AGENTS.md, Apache-2.0.

Project instructions for developing the medical-codes MCP server, an MCP tool that searches US medical code systems. They document the server's coding rules, error handling, logging, storage, and configuration patterns.

In plain words
What is it for?
Use them when developing or reviewing this server's tools, resources, handlers, and configuration. They also explain how the framework handles errors, user input, secrets, and request-scoped logging.
Why use it?
They give coding agents the context needed to change the server consistently and avoid patterns the project does not allow.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is cyanheads/medical-codes-mcp-server's own configuration. It tells Claude Code how to work on medical-codes-mcp-server 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 medical-codes-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cyanheads/medical-codes-mcp-server. 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/cyanheads/medical-codes-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/cyanheads/medical-codes-mcp-server

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.

agentmods badge for medical-codes-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cyanheads/medical-codes-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/cyanheads/medical-codes-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cyanheads/medical-codes-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/medical-codes-mcp-server/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.

agentmods 80×15 button for medical-codes-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cyanheads/medical-codes-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/medical-codes-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,018 This file is loaded in full into every session.
When invoked 6,018 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 70% copy Near-identical to another mod 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 $0.06018 $0.06018
Opus 5 $0.03009 $0.03009
Sonnet 5 $0.01204 $0.01204
Haiku 4.5 $0.00602 $0.00602

Measured 9d ago against content hash 51cbb2c58462, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

medical-codes-mcp-server 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 9d 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.

Origin

This is a copy

70% identical to obsidian-mcp-server AGENTS.md — 365 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Protocol

Server: medical-codes-mcp-server Version: 0.2.8 Framework: @cyanheads/mcp-ts-core ^0.12.3 Engines: Bun ≥1.3.0, Node ≥24.0.0 MCP SDK: @modelcontextprotocol/server ^2.0.0 Zod: ^4.4.3

Read the framework docs first: node_modules/@cyanheads/mcp-ts-core/CLAUDE.md contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.


Core Rules

  • Logic throws, framework catches. Tool/resource handlers are pure — throw on failure, no try/catch. Plain Error is fine; the framework catches, classifies, and formats. Use error factories (notFound(), validationError(), etc.) when the error code matters.
  • Use ctx.log for request-scoped logging. No console calls.
  • Use ctx.state for tenant-scoped storage. Never access persistence directly.
  • Need input the caller didn't supply? return ctx.requestInput(...) and read ctx.inputs when the handler is re-entered. Never await for user input mid-handler. No handler here does — every tool answers from the bundled index in one round.
  • Secrets in env vars only — never hardcoded.
  • Close the loop on issues. When implementing work tracked by a GitHub issue, comment on the issue with what landed and close it. Do both — a comment without a close leaves stale issues open; a close without a comment leaves no record of what shipped. The comment is for future readers — state the concrete changes, not the conversation that produced them.

Patterns

This server is tool-only (six medcode_* tools, no resources or prompts) and reads a bundled read-only SQLite index — handlers compose synchronous query methods on the code-index service.

Tool

import { tool, z } from '@cyanheads/mcp-ts-core';
import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
import { getCodeIndexService } from '@/services/code-index/code-index-service.js';
import { SYSTEM_IDS } from '@/services/code-index/types.js';

export const checkCodeTool = tool('medcode_check_code', {
  title: 'medical-codes-mcp-server',
  description: 'Validate whether a US medical code exists, is current, and is billable …',
  annotations: { readOnlyHint: true, idempotentHint: true, openWorldHint: false },

  input: z.object({
    code: z.string().min(1).describe('The code to validate, with or without dots.'),
    system: z.enum(SYSTEM_IDS).optional().describe('Force the lookup into this system. Omit to auto-detect.'),
  }),
  output: z.object({
    system: z.string().describe('The system the code was resolved in, echoed for chaining.'),
    code: z.string().describe('The code in display form (ICD-10-CM carries the dot).'),
    status: z.enum(['valid_billable', 'valid_not_billable', 'valid_header', 'terminated'])
      .describe('Discriminated validity status.'),
    billable: z.boolean().describe('True only when status is valid_billable.'),
    whyNot: z.string().nullable().describe('Explanation for non-billable/terminated, or null.'),
  }),

  // Typed per-tool error contract — ctx.fail is type-checked against these reasons.
  errors: [
    { reason: 'unknown_code', code: JsonRpcErrorCode.NotFound,
      when: 'The code does not exist in the named or detected system.',
      recovery: 'Check the code, or search by description with medcode_search_codes.' },
  ],

  handler(input, ctx) {
    const outcome = getCodeIndexService().checkCode(input.code, input.system);
    // … discriminate on outcome.kind; a non-billable/terminated code is a SUCCESS
    // result with a whyNot, NOT an error — only an absent code throws unknown_code.
    if (outcome.kind === 'resolved' && outcome.result.status === 'unknown') {
      throw ctx.fail('unknown_code', `Unknown code "${input.code}".`, { ...ctx.recoveryFor('unknown_code') });
    }
    ctx.log.info('Checked code', { code: input.code });
    return { /* … */ } as never;
  },

  // format() populates content[] — the markdown twin of structuredContent.
  // Different clients read different surfaces (Claude Code → structuredContent,
  // Claude Desktop → content[]); both must carry the same data.
  format: (result) => [{ type: 'text', text: `${result.code}: ${result.status}` }],
});

Read the full file on GitHub · 378 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. 9d ago First seen · 378 lines · 6,018 tokens per session scan A 51cbb2c58462

Subscribe to this mod's changes

medical-codes-mcp-server CLAUDE.md is an instructions file published in the GitHub repository cyanheads/medical-codes-mcp-server (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 6,018 tokens to every session, about $0.0301 per session on Opus 5. A static security scan graded it A with 0 findings. It is 70% identical to obsidian-mcp-server AGENTS.md, differing in 365 lines, and is treated as a copy.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens