claude-ralph: Instructions file for Claude Code

CLAUDE.md

claude-ralph CLAUDE.md is an instructions file for Claude Code from RobinOppenstam/claude-ralph. It costs 1,340 tokens per session, scanned A, original, MIT.

A setup and usage guide for claude-ralph, a script that repeatedly launches Claude Code to work through product requirements. Each run starts with a clean context while Git, progress.txt, and prd.json preserve the work state.

In plain words
What is it for?
Use it to install the scripts, create a list of user stories in prd.json, run one or more iterations, and inspect progress.
Why use it?
It lets longer projects be split into repeated coding sessions, so progress and learnings remain available after each session ends.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is RobinOppenstam/claude-ralph's own configuration. It tells Claude Code how to work on claude-ralph 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 claude-ralph configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RobinOppenstam/claude-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/RobinOppenstam/claude-ralph/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/RobinOppenstam/claude-ralph

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 claude-ralph CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/robinoppenstam/claude-ralph/claude-md/github.svg)](https://agentmods.dev/instructions/robinoppenstam/claude-ralph/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/robinoppenstam/claude-ralph/claude-md"><img src="https://agentmods.dev/badge/instructions/robinoppenstam/claude-ralph/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 claude-ralph CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/robinoppenstam/claude-ralph/claude-md"><img src="https://agentmods.dev/badge/instructions/robinoppenstam/claude-ralph/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,340 This file is loaded in full into every session.
When invoked 1,340 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01340 $0.01340
Opus 5 $0.00670 $0.00670
Sonnet 5 $0.00268 $0.00268
Haiku 4.5 $0.00134 $0.00134

Measured 9d ago against content hash 5194ee0e1cb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-ralph 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.

CLAUDE.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-ralph

An autonomous AI agent loop that runs Claude Code repeatedly until all PRD items are complete. Each iteration is a fresh Claude Code instance with clean context. Memory persists via git history, progress.txt, and prd.json.

Quick Start

# 1. Install ralph in scripts directory
mkdir -p scripts && cd scripts
git clone https://github.com/RobinOppenstam/claude-ralph ralph
chmod +x ralph/*.sh
cd ..

# 2. (Optional) Install skills globally for interactive use
./scripts/ralph/install-skills.sh

# 3. Create your prd.json (copy from example and edit)
cp scripts/ralph/prd.json.example scripts/ralph/prd.json

# 4. Run ralph from project root
./scripts/ralph/ralph.sh [max_iterations]

File Structure

your-project/
├── scripts/
│   └── ralph/                    # Ralph files (self-contained)
│       ├── ralph.sh             # Main loop script
│       ├── ralph-once.sh        # Single iteration script
│       ├── ralph-status.sh      # Status checker
│       ├── prompt.md            # Instructions for each iteration
│       ├── prd.json             # User stories with passes status
│       ├── progress.txt         # Append-only learnings log
│       ├── ralph.log            # Execution log
│       ├── .last-branch         # Current branch tracker
│       ├── archive/             # Previous runs
│       └── skills/              # Claude Code skills
│
└── [Project root]                # Your project files
    ├── src/                      # Source code (created by Ralph)
    ├── package.json              # Dependencies (created by Ralph)
    └── ...                       # Other project files

How It Works

  1. Loop starts - Ralph reads prd.json
  2. Pick story - Selects highest priority story where passes: false
  3. Implement - Claude Code implements the story
  4. Quality check - Runs typecheck, tests, lint
  5. Commit - If checks pass, commits changes
  6. Update PRD - Marks story as passes: true
  7. Log learnings - Appends to progress.txt
  8. Repeat - Until all stories pass or max iterations reached

Read the full file on GitHub · 168 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 · 168 lines · 1,340 tokens per session scan A 5194ee0e1cb8

Subscribe to this mod's changes

claude-ralph CLAUDE.md is an instructions file published in the GitHub repository RobinOppenstam/claude-ralph (11 stars, last pushed 6mo ago), licensed MIT. It adds 1,340 tokens to every session, about $0.0067 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.

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