Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/jorben/mcp-server/agents-mdgit clone --depth 1 https://github.com/jorben/mcp-serverWhat 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 | $0.01085 | $0.01085 |
| Opus 5 | $0.00543 | $0.00543 |
| Sonnet 5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
mcp-server 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 2d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - MCP Server Development Guide
This document provides guidelines and commands for agents working on this codebase.
Project Overview
This is a TypeScript-based MCP (Model Context Protocol) server with a pluggable tool architecture. The server uses Express for HTTP endpoints and Zod for schema validation.
Build Commands
# Build TypeScript to JavaScript
npm run build
# Start production server
npm start
# Development with hot reload
npm run dev
# Run linting
npm run lint
# Fix linting errors automatically
npm run lint:fix
Testing
# Run all tests
npm test
# Run tests in watch mode
npm run test:watch
# Run tests with coverage
npm test -- --coverage
# Run a single test file
npx vitest run src/tools/echo/index.test.ts
# Run tests matching a pattern
npx vitest run -t "echo"
Environment Variables
| Variable | Default | Description |
|---|---|---|
PORT |
3000 |
Server port |
HOST |
0.0.0.0 |
Server host |
AUTHORIZATION_KEY |
- | Bearer token for API authentication (optional) |
Code Style Guidelines
TypeScript Configuration
- Target: ES2022
- Module: NodeNext
- Strict mode enabled
- Explicit return types: Off (optional, but recommended for public APIs)
- Use
unknowninstead ofanywhen type is uncertain
Naming Conventions
- Variables/Functions: camelCase (
toolRegistry,getAllTools) - Classes: PascalCase (
ToolRegistry,MCPTool) - Constants: SCREAMING_SNAKE_CASE for config values
- Files: kebab-case for general files, index.ts for directory entry points
- Interfaces: Prefix with
MCPfor domain types (MCPTool,MCPMethodDefinition)
Imports
- Use
.jsextension in imports even for TypeScript files (required for NodeNext module resolution) - Group imports in this order: external dependencies, internal modules
- Use named exports for utilities and classes
- Use default exports for tool modules
import { z } from 'zod';
import { MCPTool } from '../../types/mcp.js';
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.
- 2d ago First seen · 176 lines · 1,085 tokens per session scan A d1908def5f2d
mcp-server AGENTS.md is an instructions file published in the GitHub repository jorben/mcp-server (1 stars, last pushed 7mo ago), licensed MIT. It adds 1,085 tokens to every session, about $0.0054 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 2026-08-31.
Other instructions, from other repositories
PBP CLAUDE.md
Instructions for MadGapun/PBP, covering pbp — claude-code-memory, stand 2026-08-25 (v1.7.23 stable) — ehrliche zahlen, stand 2026-07-16 (v1.8.0-beta.6, prerelease) — hotfix #760, stand 2026-07-14 (v1.7.7) — scoring-fairness & praxis-funde and stand 2026-07-03 (v1.7.6) — alltags-fuehrung.
artel CLAUDE.md
Instructions for NicolasPrimeau/artel, covering artel, what it is, stack, layout and core primitives.
PBP AGENTS.md
Instructions for MadGapun/PBP, covering agents.md — pbp (persönliches bewerbungs-portal), projektübersicht, architektur, setup & tests and windows: doppelklick.
mcp-coolify AGENTS.md
AGENTS.md instructions for hecateq/mcp-coolify, covering ai coding assistant — save & restore instructions, 0. the 30-second elevator pitch, 1. hard rules — do not violate, 2. project structure and 3. workflow expectations.
mcp-coolify copilot-instructions.md
Copilot instructions for hecateq/mcp-coolify, covering github copilot — project context, tl;dr, mandatory constraints, domain concepts (must know before suggesting changes) and validation sequence (must run before commit).
immichctrl AGENTS.md
Instructions for lidless-labs/immichctrl, covering agents.md - working in this repo, every session, definition of done, memory owner and memory handoff (mandatory).