ralph-help

ralph-help is a command for Claude Code from runnithan/claudex-setup. It costs 7 tokens per session (336 once invoked), scanned A, original, MIT.

A help command for Ralph Loop, a method that repeatedly gives an AI the same development request so it can build on files and Git history.

In plain words
What is it for?
Use it to view Ralph Loop guidance and learn the available commands and options.
Why use it?
It explains how to start, limit, complete, or cancel those repeated work cycles.

Command for Claude Code

Part of the claudex-setup plugin — 3 skills, 21 commands, 22 agents shipped together

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.

agentmods
npx agentmods add commands/runnithan/claudex-setup/ralph-help
Clone the repo
git clone --depth 1 https://github.com/runnithan/claudex-setup

Made for: Claude Code.

Or install claudex-setup, the plugin that ships this one along with the rest of its 3 skills, 21 commands, 22 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 ralph-help

README.md
[![agentmods](https://agentmods.dev/badge/commands/runnithan/claudex-setup/ralph-help.svg)](https://agentmods.dev/commands/runnithan/claudex-setup/ralph-help)
Your own site
<a href="https://agentmods.dev/commands/runnithan/claudex-setup/ralph-help"><img src="https://agentmods.dev/badge/commands/runnithan/claudex-setup/ralph-help.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 336 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00007 $0.00336
Opus 5 $0.00003 $0.00168
Sonnet 5 $0.00001 $0.00067
Haiku 4.5 $0.00001 $0.00034

Measured 3d ago against content hash 6615c9b4258c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralph-help 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 3d 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/commands/ralph-help.md · 49 lines

What it actually says

Ralph Loop Help

Explain the following to the user:

What is Ralph Loop?

Ralph Loop implements the Ralph Wiggum technique, an iterative development methodology based on continuous AI loops, pioneered by Geoffrey Huntley.

Core concept: The same prompt is fed to Claude repeatedly. Claude sees its own previous work in files and git history, building incrementally toward the goal.

Each iteration:

  1. Claude receives the SAME prompt
  2. Works on the task, modifying files
  3. Tries to exit
  4. Stop hook intercepts and feeds the same prompt again
  5. Claude sees its previous work in the files
  6. Iteratively improves until completion

Available Commands

/ralph-loop PROMPT [OPTIONS]

Start a Ralph loop in your current session.

Options:

  • --max-iterations <n>, Max iterations before auto-stop
  • --completion-promise <text>, Promise phrase to signal completion

Examples:

/ralph-loop Refactor the cache layer --max-iterations 20
/ralph-loop Add tests --completion-promise "TESTS COMPLETE"
/ralph-loop Fix the auth bug --completion-promise "FIXED" --max-iterations 10

/cancel-ralph

Cancel an active Ralph loop (removes the loop state file).

When to Use

Good for: Well-defined tasks with clear success criteria, tasks requiring iteration, greenfield projects.

Not good for: Tasks requiring human judgment, one-shot operations, unclear success criteria.

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. 3d ago First seen · 49 lines · 7 tokens per session scan A 6615c9b4258c

Subscribe to this mod's changes

ralph-help is a command published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed 3d ago), licensed MIT. It adds 7 tokens to every session and 336 once invoked, about $0.0000 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 2026-08-31.