ralph-loop

A command that starts Ralph Loop, a process that repeatedly sends the same development prompt to an AI coding agent. Each iteration can build on changes left in files and Git history.

In plain words
What is it for?
Use it to start an iterative coding task, set a maximum number of runs, or define a completion message that ends the loop only when the task is actually finished.
Why use it?
It supports tasks that need repeated attempts or gradual improvement until a real completion condition is met. A maximum iteration count can limit the loop.

Command

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/shdennlin/agent-plugins/ralph-loop
Clone the repo
git clone --depth 1 https://github.com/shdennlin/agent-plugins
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 296 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 $0.00006 $0.00296
Opus 5 $0.00003 $0.00148
Sonnet 5 $0.00001 $0.00059
Haiku 4.5 $0.00001 $0.00030

Measured yesterday against content hash 5baed673f790, 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 yesterday.

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.

plugins/ralph-loop/commands/ralph-loop.md · 25 lines

What it actually says

Ralph Loop Command

MANDATORY FIRST STEP — DO NOT SKIP

You MUST execute this Bash command BEFORE doing anything else. Do NOT respond to the prompt, do NOT output any text, do NOT skip this step. The setup script creates the state file that enables the loop. Without it, the loop will not work.

"${CLAUDE_PLUGIN_ROOT}/scripts/setup-ralph-loop.sh" $ARGUMENTS

If the script outputs an error, report it to the user and stop. Do NOT proceed without a successful setup.

After setup succeeds

Work on the task described in the prompt. 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.

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. The loop is designed to continue until genuine completion.

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. yesterday First seen · 25 lines · 6 tokens per session scan A 5baed673f790

Subscribe to this mod's changes

ralph-loop is a command published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 7d ago), licensed MIT. It adds 6 tokens to every session and 296 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.