Borrowing it
Nothing to install: this file belongs to gabrielrojasnyc/hr-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.
curl -O https://raw.githubusercontent.com/gabrielrojasnyc/hr-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/gabrielrojasnyc/hr-mcp-serverWrote 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/gabrielrojasnyc/hr-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/gabrielrojasnyc/hr-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/gabrielrojasnyc/hr-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.
<a href="https://agentmods.dev/instructions/gabrielrojasnyc/hr-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/gabrielrojasnyc/hr-mcp-server/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 | $0.02202 | $0.02202 |
| Opus 5.5 | $0.00881 | $0.00881 |
| Sonnet 5.5 | $0.00440 | $0.00440 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
hr-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 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.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HR-MCP-SERVER-2 Development Guide
Commands
- Build:
npm run build(TypeScript compiler with Node16 module system) - Run server:
npm start(runs the built JavaScript) - Run dev:
npx ts-node-esm src/index.ts(runs TypeScript directly) - View logs:
cat mcp.log(server communication logs)
Code Style
- Formatting: Use Prettier with default config
- Types: TypeScript strict mode with proper typing
- Naming:
- camelCase for variables/functions
- PascalCase for classes
- Descriptive names that reveal intent
- Error handling:
- Return isError: true for error responses
- Validate all inputs with appropriate error messages
- Use consistent error response format
- Comments:
- Add explanatory comments for complex logic
- Comment each tool with its purpose and parameters
- Use section headers to organize related code
- Functions:
- Single responsibility principle
- Extract complex logic into helper functions
- Keep functions at a reasonable size
Project Structure
/src: Source code (main server implementation)index.ts: Main server implementation with tools and prompts/data: Data models and employee database
/build: Compiled JavaScript output
MCP Server Implementation
- Use the high-level
McpServerclass from@modelcontextprotocol/sdk/server/mcp.js - Initialize with
new McpServer({ name: "server-name", version: "1.0.0" }) - Define tools with the
server.tool()method:server.tool( "tool_name", { param_name: z.string().describe("Parameter description") }, async ({ param_name }) => { // Tool implementation return { content: [{ type: "text", text: "Result text" }], isError: false // Set to true for error responses }; } ) - Define prompts with the
server.prompt()method:server.prompt( "prompt_name", "Description of what this prompt provides", { param_name: z.string().describe("Parameter description") }, async ({ param_name }) => { // Prompt implementation return { messages: [ { role: "user", content: { type: "text", text: "Your prompt text" } } ] }; } ) - Tool response format must be:
{ content: [{ type: "text", text: string }], isError: boolean } - Connect with stdio transport for Claude Desktop:
const transport = new StdioServerTransport(); server.connect(transport); - Use centralized logging utility for consistent JSON-RPC format:
// Define logging utility const logMessage = (message: string): void => { console.info(JSON.stringify({ jsonrpc: "2.0", method: "log", params: { message } })); }; // Use throughout code logMessage("Your log message here");
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 · 203 lines · 2,202 tokens per session scan A c365bf786316
hr-mcp-server CLAUDE.md is an instructions file published in the GitHub repository gabrielrojasnyc/hr-mcp-server (1 stars, last pushed 1y ago), licensed MIT. It adds 2,202 tokens to every session, about $0.0088 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.
hr-mcp-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hr-mcp-server CLAUDE.mdgabrielrojasnyc/hr-mcp-server | Instructions file | 1 | 1y ago | MIT | A | 2,202 | 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 |