A command that starts a Ralph Loop, an iterative development process that feeds the same task back after each attempt. It also keeps implementation notes for later review.

Use it for development tasks that benefit from repeated implementation and review. It sets up the loop and records notes about the work, constraints, and decisions.

It supports repeated passes over a coding task while preserving decisions and tradeoffs. The loop can continue until the work is complete or a genuine outside blocker is reported.

ralph-loop — Command by runnithan

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-loop

Clone the repo

git clone --depth 1 https://github.com/runnithan/claudex-setup

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 288 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.00288
Opus 5	$0.00006	$0.00144
Sonnet 5	$0.00002	$0.00058
Haiku 4.5	$0.00001	$0.00029

Measured 2d ago against content hash f1f1b07a3a5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralph-loop 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 2d 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-loop.md · 22 lines

What it actually says

Ralph Loop Command

Execute the setup script to initialize the Ralph loop:

.claude/scripts/setup-ralph-loop.sh $ARGUMENTS

Please work on the task. When you try to exit, the Ralph loop will feed the SAME PROMPT back to you for the next iteration. You'll see your previous work in files and git history, allowing you to iterate and improve.

Keep a running implementation-notes.md recording decisions and tradeoffs you had to make and anything else the reviewer should know; it gets read before the diff.

CRITICAL RULE: If a completion promise is set, you may ONLY output it when the statement is completely and unequivocally TRUE. Do not output false promises to escape the loop, even if you think you're stuck or should exit for other reasons.

SAFE EXIT: If the task turns out to be infeasible or blocked on something outside this loop's control, say so and stop: reporting infeasibility, with the evidence, is a valid completion, not a failure (it is NOT the completion promise; never output that falsely). Do not retry the same failing approach more than twice.

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.

2d ago First seen · 22 lines · 12 tokens per session scan A f1f1b07a3a5a

Subscribe to this mod's changes

ralph-loop is a command published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 288 once invoked, about $0.0001 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.

Building agents agents ai anthropic claude claude-code claude-code-plugin

multi-agent-optimize

The Multi-Agent Optimization Tool is an advanced AI-driven framework designed to holistically improve system performance through intelligent, coordinated agent-based optimization. Leveraging cutting-edge AI orchestration techniques, this tool provides a comprehensive approach to performance engineering across multiple…

wshobson/agents · 0 tokens

ship-an-mcp-server

Workflow recipe — make your product agent-usable by chaining 4 skills, spec to pricing.

mohitagw15856/pm-claude-skills · 19 tokens

auto

Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…

yonatangross/orchestkit · 99 tokens

ralph-loop