A command for stopping an autonomous Ralph Wiggum loop, a setup that repeatedly works on a task without a new prompt. It reads the loop's saved state, stops it, and reports session and Git information.

Use it to stop an active loop, remove its saved loop state, show its task and duration, list commits made during the run, and suggest follow-up actions.

It gives developers a controlled way to halt repeated automated work and see what happened during the run.

ralph-stop — Command for Claude Code by Peaky8linders: A command for stopping an autonomous Ralph Wiggum loop…

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/peaky8linders/claude-cortex/ralph-stop

Clone the repo

git clone --depth 1 https://github.com/Peaky8linders/claude-cortex

Made for: Claude Code.

Or install cortex, the plugin that ships this one along with the rest of its 1 skill, 15 commands, 3 agents, 5 hooks, 2 MCP servers.

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/commands/peaky8linders/claude-cortex/ralph-stop.svg)](https://agentmods.dev/commands/peaky8linders/claude-cortex/ralph-stop)

Your own site

<a href="https://agentmods.dev/commands/peaky8linders/claude-cortex/ralph-stop"><img src="https://agentmods.dev/badge/commands/peaky8linders/claude-cortex/ralph-stop.svg" alt="Measured on agentmods" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 371 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00016	$0.00371
Opus 5	$0.00008	$0.00186
Sonnet 5	$0.00003	$0.00074
Haiku 4.5	$0.00002	$0.00037

Measured 4d ago against content hash 8df078e37e3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

ralph-stop 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/knowledge/.ralph-active 2>/dev/null

.claude/commands/ralph-stop.md · 62 lines

What it actually says

/ralph-stop — Halt Autonomous Loop

You are stopping a Ralph Wiggum autonomous loop.

Protocol

Step 1: Check Loop State

Read the loop file:

cat ~/.claude/knowledge/.ralph-active 2>/dev/null

If no loop file exists, report: "No active Ralph loop found."

Step 2: Read Loop Stats

Extract iteration count, start time, and task from the loop file.

Step 3: Remove Loop File and Cached State

rm -f ~/.claude/knowledge/.ralph-active
rm -f ~/.claude/knowledge/.ralph-search-cache

If the loop was started with --scope, deactivate the freeze:

/unfreeze

Step 4: Generate Summary

Show:

[Ralph] Loop stopped after {iteration} iterations.
  Task: {prompt}
  Started: {started_at}
  Duration: {calculated_duration}

Commits made during loop:
{git log --oneline from start time}

Recommend:
- Review accumulated commits: git log --oneline
- Push when ready: git push
- Capture learnings: /learn

Step 5: Show Git Summary

git log --oneline --since="STARTED_AT"
git diff --stat HEAD~{iteration_count} 2>/dev/null || git diff --stat

Step 6: Suggest Next Steps

/learn if 3+ iterations completed (substantial work)
Review and push commits
Run full test suite to verify everything still passes

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.

4d ago First seen · 62 lines · 16 tokens per session scan B 8df078e37e3d

Subscribe to this mod's changes

ralph-stop is a command published in the GitHub repository Peaky8linders/claude-cortex (11 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 371 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ralph-stop