What is ralph-to-ralph CLAUDE.md?

Project instructions for Ralph-to-Ralph, an autonomous system that recreates software products from a URL. They describe its inspection, building, and quality-check phases, along with the project's commands and technical standards.

Use them when working on Ralph-to-Ralph projects, especially for onboarding, starting the development server, checking code, running unit or end-to-end tests, building for production, and updating the database schema.

They give the agent the project-specific rules it needs to run checks, tests, builds, database updates, and development tasks consistently.

How namuh-eng/ralph-to-ralph configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to namuh-eng/ralph-to-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/namuh-eng/ralph-to-ralph/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/namuh-eng/ralph-to-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/namuh-eng/ralph-to-ralph/claude-md/github.svg)](https://agentmods.dev/instructions/namuh-eng/ralph-to-ralph/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/namuh-eng/ralph-to-ralph/claude-md"><img src="https://agentmods.dev/badge/instructions/namuh-eng/ralph-to-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/namuh-eng/ralph-to-ralph/claude-md"><img src="https://agentmods.dev/badge/instructions/namuh-eng/ralph-to-ralph/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 809 This file is loaded in full into every session.

When invoked 809 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	$0.00809	$0.00809
Opus 5	$0.00404	$0.00404
Sonnet 5	$0.00162	$0.00162
Haiku 4.5	$0.00081	$0.00081

Measured 10d ago against content hash bc354fa87eb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ralph-to-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 10d 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ralph-to-Ralph: Autonomous Product Cloner

What This Is

A three-phase autonomous system that clones any SaaS product from just a URL. Phase 1: Inspect (Claude + Ever CLI) → Phase 2: Build (Claude) → Phase 3: QA (Codex + Ever CLI)

Tech Stack

Language & Framework: Configured during onboarding (see language and stackProfile in ralph-config.json)
Styling & UI: Installed during onboarding based on stackProfile
Database: Installed during onboarding (default: Postgres)
Testing: Installed during onboarding (template provides unit test + E2E config)
Linting: Installed during onboarding (template provides linter config)

Commands

All commands go through make. The Makefile is a contract — onboarding wires up real recipes based on your stack.

make check — typecheck + lint/format
make test — run unit tests
make test-e2e — run E2E tests (requires dev server)
make all — check + test
make dev — start dev server on port 3015
make build — production build
make db-push — push schema to database

Quality Standards

Strict type checking enabled (language-specific: TypeScript strict, Go vet, etc.)
Every feature must have at least one unit test AND one E2E test
Run make check && make test before every commit
Small, focused commits — one feature per commit

Architecture

src/ (or language equivalent) — populated by onboarding based on stackProfile
Source layout depends on the template — read BUILD_GUIDE.md (copied from template during setup) for stack-specific structure
tests/ — unit tests
tests/e2e/ — E2E tests
packages/sdk/ — SDK package (if target product has an SDK)
scripts/ — infrastructure and deployment scripts

Pre-configured (DO NOT reinstall or recreate)

Makefile — make check, make test, make test-e2e, make all (contract targets)
hack/run_silent.sh — output formatting helper used by Makefile

Stack Setup

Onboarding writes ralph-config.json and runs setup-stack.sh
The setup script copies template files, appends Makefile targets, installs dependencies
Check .ralph-setup-done to see which template was used
Read BUILD_GUIDE.md in the repo root for stack-specific build instructions

Read the full file on GitHub · 70 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.

10d ago First seen · 70 lines · 809 tokens per session scan A bc354fa87eb7

Subscribe to this mod's changes

ralph-to-ralph CLAUDE.md is an instructions file published in the GitHub repository namuh-eng/ralph-to-ralph (101 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 809 tokens to every session, about $0.0040 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.

Building agents Planning

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

ralph-to-ralph: Instructions file for Claude Code