Ralph Orchestrator is a framework that repeatedly runs AI-agent tasks until they finish or reach an iteration limit. Developers use it to coordinate autonomous coding work through command-line, web-dashboard, and MCP-server interfaces, with state managed per workspace. The catalogue entries provide agent skills, agents, instructions, and plugins for operating Ralph.
Borrowing it
Nothing to install: this file belongs to mikeyobrien/ralph-orchestrator. 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/mikeyobrien/ralph-orchestrator/main/AGENTS.mdgit clone --depth 1 https://github.com/mikeyobrien/ralph-orchestratorWrote 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/mikeyobrien/ralph-orchestrator/agents-md)<a href="https://agentmods.dev/instructions/mikeyobrien/ralph-orchestrator/agents-md"><img src="https://agentmods.dev/badge/instructions/mikeyobrien/ralph-orchestrator/agents-md.svg" alt="Measured on agentmods" 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 | $0.02870 | $0.02870 |
| Opus 5 | $0.01435 | $0.01435 |
| Sonnet 5 | $0.00574 | $0.00574 |
| Haiku 4.5 | $0.00287 | $0.00287 |
Grade A, and why
ralph-orchestrator 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 7d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
The orchestrator is a thin coordination layer, not a platform. Agents are smart; let them do the work.
Build & Test
cargo build
cargo test
cargo test -p ralph-core test_name # Run single test
cargo test -p ralph-core smoke_runner # Smoke tests (replay-based)
cargo run -p ralph-e2e -- --mock # E2E tests (CI-safe)
./scripts/setup-hooks.sh # Install pre-commit hooks (once)
IMPORTANT: Run cargo test before declaring any task done. Smoke test after code changes.
Web Dashboard
ralph web # Launch both servers (backend:3000, frontend:5173)
npm install # Install all dependencies
npm run dev # Dev mode (both)
npm run dev:server # Backend only
npm run dev:web # Frontend only
npm run test:server # Backend tests
Architecture
ralph-cli → CLI entry point, commands (run, plan, task, loops, web)
ralph-core → Orchestration logic, event loop, hats, memories, tasks
ralph-adapters → Backend integrations (Claude, Kiro, Gemini, Codex, Roo, etc.)
ralph-telegram → Telegram bot for human-in-the-loop communication
ralph-tui → Terminal UI (ratatui-based)
ralph-e2e → End-to-end test framework
ralph-proto → Protocol definitions
ralph-bench → Benchmarking
backend/ → Web server (@ralph-web/server) - Fastify + tRPC + SQLite
frontend/ → Web dashboard (@ralph-web/dashboard) - React + Vite + TailwindCSS
Key Files
| File | Purpose |
|---|---|
.ralph/agent/memories.md |
Persistent learning across sessions |
.ralph/agent/tasks.jsonl |
Runtime work tracking |
.ralph/loop.lock |
Contains PID + prompt of primary loop |
.ralph/loops.json |
Registry of all tracked loops |
.ralph/merge-queue.jsonl |
Event-sourced merge queue |
.ralph/telegram-state.json |
Telegram bot state (chat ID, pending questions) |
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.
- 7d ago First seen · 299 lines · 2,870 tokens per session scan A a3d5efb3a468
ralph-orchestrator AGENTS.md is an instructions file published in the GitHub repository mikeyobrien/ralph-orchestrator (3,126 stars, last pushed 4d ago), licensed MIT. It adds 2,870 tokens to every session, about $0.0144 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.
Other instructions, from other repositories
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.
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).
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).
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.
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.