mcpField
R
ralph-loop

ralph-loop

github.com/cursorAgent workflows14.6k1.0k installsUpdated 1d ago
Repository

About ralph-loop

ralph-loop is an agent skill for running iterative development tasks by repeatedly feeding the original prompt back to the agent alongside its prior work. It stores loop state and supports an iteration limit and an optional completion condition.

Key features

  1. 01Repeats the task prompt each turn
  2. 02Records state in a scratchpad file
  3. 03Supports iteration limits
  4. 04Supports a completion condition

Use cases

  1. 01Iterating on a development task
  2. 02Capping an agent's work iterations
  3. 03Stopping after a defined completion condition

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cursor/plugins --skill ralph-loop

After installing, type/ralph-loopin Claude Code to confirm it loaded.

Details

From the project README

Ralph Loop

Trigger

The user wants to start a Ralph loop. An iterative development loop where the same prompt is fed back after every turn, and the agent sees its own previous work each iteration.

Workflow

  1. Gather the user's task prompt and optional parameters:

    • max_iterations (number, default 0 for unlimited)
    • completion_promise (text, or "null" if not set)

  2. Create the directory .cursor/ralph/ if it doesn't exist, then write the state file at .cursor/ralph/scratchpad.md with this exact format:

    ---
iteration: 1
max_iterations: <N or 0>
completion_promise: "<TEXT>" or null
---

<the user's task prompt goes here>

    Example:

    ---
iteration: 1
max_iterations: 20
completion_promise: "COMPLETE"
---

Build a REST API for todos with CRUD operations, input validation, and tests.

  3. Confirm to the user that the Ralph loop is active, then begin working on the task.

  4. The stop hook automatically intercepts each turn end and feeds the same prompt back as a followup message. You will see it prefixed with [Ralph loop iteration N.].

Guardrails

  • If a completion promise is set, you may ONLY output <promise>TEXT</promise> when the statement is completely and genuinely true.
  • Do not output false promises to escape the loop.
  • Always recommend setting max_iterations as a safety net.
  • Quote the completion_promise value in the YAML frontmatter if it contains special characters.

Output

Confirm the loop is active (prompt, iteration limit, promise if set), then start working on the task immediately.

Comments

Markdown supported