Skip to content
Agentmart
Submit a tool
This entry duplicates ralph-loop, which is the one we list in search.

ralph-loop

Self-referential development loop that runs until task completion.

Skill by tainn03

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tainn03-ralph-loop

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Self-referential development loop that runs until task completion. Includes Ralph Loop (basic), ULW Loop (with Oracle verification), and cancel-ralph functionality.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

What's inside

Skill name
ralph-loop
Description
Self-referential development loop that runs until task completion. Includes Ralph Loop (basic), ULW Loop (with Oracle verification), and cancel-ralph functionality.
License
MIT
Instructions
63 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Ralph Loop

A self-referential development loop that runs until task completion.

## Variants

### Ralph Loop (Basic)

1. Work on the task continuously
2. When the task is FULLY complete, output: `<promise>DONE</promise>`
3. If you don't output the promise, continue working
4. Maximum iterations: 100 (configurable)

### ULW Loop (Ultrawork)

1. Work on the task continuously
2. When the work is complete, output: `<promise>DONE</promise>`
3. That does NOT finish the loop yet - Oracle verification is required
4. The loop only ends after Oracle verifies the result
5. There is no iteration limit

## Rules

- Focus on completing the task fully, not partially
- Don't output the completion promise until the task is truly done
- Each iteration should make meaningful progress toward the goal
- If stuck, try different approaches
- Use todos to track your progress

## Exit Conditions

### Ralph Loop
1. **Completion**: Output your completion promise tag when fully complete
2. **Max Iterations**: Loop stops automatically at limit
3. **Cancel**: User says "cancel ralph" or "stop"

### ULW Loop
1. **Verified Completion**: Oracle verifies the result
2. **Cancel**: User says "cancel ralph" or "stop"

## Usage

```
ralph-loop "task description" [--completion-promise=TEXT] [--max-iterations=N]
ulw-loop "task description" [--completion-promise=TEXT]
```

Default completion promise is "DONE" and default max iterations is 100.

## Cancel

To cancel an active loop:
1. Stop the loop from continuing
2. Clear the loop state
3. Allow the session to end normally

Check if a loop is active and cancel it. Inform the user of the result.

## Your Task

Parse the arguments and begin working. Work continuously until the task is fully complete, then output the completion promise.

From tainn03/oh-my-copilot, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 17, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from tainn03

Cite this page

ralph-loop skill. Agent Mart. https://agentmart.dev/skills/tainn03-ralph-loop (last updated 2026-10-24)