What is copilot-ralph AGENTS.md?

A project guide for coding agents working on Ralph, a Go command-line tool that repeatedly asks GitHub Copilot to work on a task and checks whether it is finished.

Use it when changing Ralph’s Go code, terminal interface, Copilot integration, tests, or project structure.

It gives the agent the project’s architecture, coding conventions, testing rules, and error-handling expectations in one place.

How JanDeDobbeleer/copilot-ralph configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to JanDeDobbeleer/copilot-ralph. 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/JanDeDobbeleer/copilot-ralph/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/JanDeDobbeleer/copilot-ralph

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jandedobbeleer/copilot-ralph/agents-md/github.svg)](https://agentmods.dev/instructions/jandedobbeleer/copilot-ralph/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/jandedobbeleer/copilot-ralph/agents-md"><img src="https://agentmods.dev/badge/instructions/jandedobbeleer/copilot-ralph/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jandedobbeleer/copilot-ralph/agents-md"><img src="https://agentmods.dev/badge/instructions/jandedobbeleer/copilot-ralph/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,849 This file is loaded in full into every session.

When invoked 4,849 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.

Model	Per session	Once invoked
Fable 5.1	$0.04849	$0.04849
Opus 5.5	$0.01940	$0.01940
Sonnet 5.5	$0.00970	$0.00970
Haiku 4.5	$0.00485	$0.00485

Measured 2mo ago against content hash 7338b14953c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

copilot-ralph 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 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.

AGENTS.md · 945 lines

How it starts

The opening of the file, as written. The whole thing — 945 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ralph Development Guide for AI Agents

This comprehensive guide helps AI agents understand Ralph's architecture, conventions, and development patterns. Use this as your primary reference when working on Ralph.

Project Overview
Architecture
Package Structure
Development Patterns
Go Conventions
Bubble Tea Patterns
Copilot SDK Integration
Testing Guidelines
Error Handling
Code Style

Project Overview

Ralph is an iterative AI development loop tool that implements the "Ralph Wiggum" technique for self-referential AI development. It continuously feeds prompts to GitHub Copilot AI, monitoring for a "completion promise" phrase, with each iteration building on previous work.

Core Concept

User provides task → Ralph starts loop → AI iterates → Makes changes → Tests →
Checks for promise → If found: complete, else: continue → Max iterations reached or timeout

Technology Stack

Language: Go 1.22+
CLI: Cobra (command framework)
TUI: Bubble Tea (terminal UI framework)
AI: GitHub Copilot SDK
Testing: testify (assertions and mocks)

Architecture

High-Level Architecture

┌─────────────────────────────────────────────────────────────┐
│                        CLI Layer                            │
│  (cmd/ralph, internal/cli)                                  │
│  - Command parsing                                          │
│  - Flag handling                                            │
│  - Entry point                                              │
└────────────────┬────────────────────────────────────────────┘
                 │
┌────────────────▼────────────────────────────────────────────┐
│                        TUI Layer                            │
│  (internal/tui)                                             │
│  - Terminal UI screens                                      │
│  - User interactions                                        │
│  - Visual feedback                                          │
└────────────────┬────────────────────────────────────────────┘
                 │
┌────────────────▼────────────────────────────────────────────┐
│                       Core Layer                            │
│  (internal/core)                                            │
│  - Loop engine                                              │
│  - State management                                         │
│  - Business logic                                           │
└────────────────┬────────────────────────────────────────────┘
                 │
┌────────────────▼────────────────────────────────────────────┐
│                       SDK Layer                             │
│  (internal/sdk)                                             │
│  - Copilot SDK wrapper                                      │
│  - Session management                                       │
│  - Tool handling                                            │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 945 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.

2mo ago First seen · 945 lines · 4,849 tokens per session scan A 7338b14953c0

Subscribe to this mod's changes

copilot-ralph AGENTS.md is an instructions file published in the GitHub repository JanDeDobbeleer/copilot-ralph (54 stars, last pushed 9mo ago), licensed MIT. It adds 4,849 tokens to every session, about $0.0194 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 2026-08-30.

copilot-ralph AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
copilot-ralph AGENTS.mdJanDeDobbeleer/copilot-ralph	Instructions file	54	9mo ago	MIT	A	4,849	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	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

copilot-ralph: Instructions file for Codex