setup-ralph

setup-ralph is a skill for Claude Code from atournayre/claude-marketplace. It costs 18 tokens per session (1,039 once invoked), scanned B, original, MIT.

A setup workflow for Ralph, an autonomous AI coding loop that works through small user stories. It creates the project files and shows the command the developer can run afterward.

In plain words
What is it for?
Use it to prepare Ralph for a feature, create its project structure and story files, and receive the command needed to start the loop manually.
Why use it?
It turns a feature idea or product requirements document into a structured set of stories for repeated coding work. The setup keeps execution under the developer's control.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the dev plugin — 25 skills, 8 agents shipped together

Good fit Use it to prepare Ralph for a feature, create its project structure and story files, and receive the command needed to start the loop manually.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/atournayre/claude-marketplace/ralph
Install

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.

Any agent
npx skills add atournayre/claude-marketplace --skill ralph
Clone the repo
git clone --depth 1 https://github.com/atournayre/claude-marketplace

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 25 skills, 8 agents.

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 setup-ralph

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/atournayre/claude-marketplace/ralph"><img src="https://agentmods.dev/badge/skills/atournayre/claude-marketplace/ralph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,039 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00018 $0.01039
Opus 5 $0.00009 $0.00519
Sonnet 5 $0.00004 $0.00208
Haiku 4.5 $0.00002 $0.00104

Measured 12d ago against content hash 276fdab8afdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

setup-ralph scanned grade B with 1 finding 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/setup.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

🛑 NEVER execute the loop - only set up files and show instructions
dev/skills/ralph/SKILL.md · 118 lines

What it actually says

This skill ONLY sets up Ralph - you run the commands yourself.

<quick_start> Setup Ralph interactively (recommended):

/setup-ralph -i

Setup for specific feature:

/setup-ralph -f 01-add-authentication

What this does:

  1. Creates .claude/ralph/ structure in your project
  2. Runs setup script to create all Ralph files
  3. (If -i): Brainstorms PRD with you interactively
  4. Transforms PRD into user stories (prd.json)
  5. Shows you the command to run Ralph (you run it yourself)

After setup, you run:

bun run .claude/ralph/ralph.sh -f <feature-name>

</quick_start>

<critical_rule> 🛑 NEVER run ralph.sh or any execution commands automatically 🛑 NEVER execute the loop - only set up files and show instructions ✅ ALWAYS let the user copy and run commands themselves ✅ ALWAYS end by showing the exact command to run </critical_rule>

<when_to_use> Use this skill when:

  • Starting a new feature that can be broken into small stories
  • Setting up Ralph in a new project
  • Creating a new feature PRD interactively

Don't use for:

  • Simple single-file changes
  • Exploratory work without clear requirements
  • Major refactors without acceptance criteria </when_to_use>

Examples:

/setup-ralph /path/to/project -i              # Interactive PRD creation
/setup-ralph . -f 01-add-auth                 # Setup for specific feature
/setup-ralph -i -f 02-user-dashboard          # Interactive with specific name

<state_variables>

Variable Type Description
{project_path} string Absolute path to target project
{ralph_dir} string Path to .claude/ralph in project
{feature_name} string Feature folder name (e.g., 01-add-auth)
{feature_dir} string Path to task folder
{interactive_mode} boolean Whether to brainstorm PRD interactively
{prd_content} string PRD markdown content
{user_stories} array User stories extracted from PRD
{branch_name} string Git branch for the feature
</state_variables>

<entry_point> Load steps/step-00-init.md </entry_point>

<step_files>

Step File Purpose
00 step-00-init.md Parse flags, run setup script, create structure
01 step-01-interactive-prd.md Interactive PRD brainstorming and creation
02 step-02-create-stories.md Transform PRD into user stories (prd.json)
03 step-03-finish.md Show run command (user runs it themselves)
</step_files>

<execution_rules>

  1. Progressive Loading: Load one step at a time
  2. Script Execution: Use scripts/setup.sh to create files atomically
  3. Interactive Mode: If -i flag, run brainstorming conversation
  4. State Persistence: Track progress in feature_dir/progress.txt
  5. Resume Support: Detect existing PRD.md and resume from there
  6. NEVER RUN RALPH: Only setup and show commands - user runs them </execution_rules>

<success_criteria> ✅ Ralph structure created at {project_path}/.claude/ralph ✅ Feature folder created with PRD.md, prd.json, progress.txt ✅ User stories properly formatted in prd.json ✅ Clear run command provided to user (they run it themselves) </success_criteria>

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 118 lines · 18 tokens per session scan B 276fdab8afdc

Subscribe to this mod's changes

setup-ralph is a skill published in the GitHub repository atournayre/claude-marketplace (9 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 1,039 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens