cmd-help

cmd-help is a cursor rule for Cursor from nota-america/forgecat-agent-profiles. It costs 776 tokens per session, scanned A, original, Apache-2.0.

A help guide for the Ralph Wiggum technique, an iterative coding method that repeatedly gives the same prompt to an AI coding tool while it builds on changes already saved in the project.

In plain words
What is it for?
It is for starting Ralph loops, setting iteration limits, defining completion messages, and explaining how the technique improves work across repeated runs.
Why use it?
It explains how repeated work loops operate and which commands and stopping options are available.

Cursor rule for Cursor

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 rules/nota-america/forgecat-agent-profiles/cmd-help
Clone the repo
git clone --depth 1 https://github.com/nota-america/forgecat-agent-profiles

Made for: Cursor.

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.

agentmods badge for cmd-help

README.md
[![agentmods](https://agentmods.dev/badge/rules/nota-america/forgecat-agent-profiles/cmd-help.svg)](https://agentmods.dev/rules/nota-america/forgecat-agent-profiles/cmd-help)
Your own site
<a href="https://agentmods.dev/rules/nota-america/forgecat-agent-profiles/cmd-help"><img src="https://agentmods.dev/badge/rules/nota-america/forgecat-agent-profiles/cmd-help.svg" alt="Measured on agentmods" height="20"></a>
Per session 776 This file is loaded in full into every session.
When invoked 776 The same file — it is already loaded in full.
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 $0.00776 $0.00776
Opus 5 $0.00388 $0.00388
Sonnet 5 $0.00155 $0.00155
Haiku 4.5 $0.00078 $0.00078

Measured 4d ago against content hash d446fdbc99ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cmd-help 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 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.

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.

profiles/anthropics/claude-code/anthropics_claude-code_ralph-wiggum/for-cursor/.cursor/rules/cmd-help.mdc · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ralph Wiggum Plugin Help

Please explain the following to the user:

What is the Ralph Wiggum Technique?

The Ralph Wiggum technique is an iterative development methodology based on continuous AI loops, pioneered by Geoffrey Huntley.

Core concept:

while :; do
  cat PROMPT.md | claude-code --continue
done

The same prompt is fed to Claude repeatedly. The "self-referential" aspect comes from Claude seeing its own previous work in the files and git history, not from feeding output back as input.

Each iteration:

  1. Claude receives the SAME prompt
  2. Works on the task, modifying files
  3. Tries to exit
  4. Stop hook intercepts and feeds the same prompt again
  5. Claude sees its previous work in the files
  6. Iteratively improves until completion

The technique is described as "deterministically bad in an undeterministic world" - failures are predictable, enabling systematic improvement through prompt tuning.

Available Commands

/ralph-loop [OPTIONS]

Start a Ralph loop in your current session.

Usage:

/ralph-loop "Refactor the cache layer" --max-iterations 20
/ralph-loop "Add tests" --completion-promise "TESTS COMPLETE"

Options:

  • --max-iterations <n> - Max iterations before auto-stop
  • --completion-promise <text> - Promise phrase to signal completion

How it works:

  1. Creates .claude/.ralph-loop.local.md state file
  2. You work on the task
  3. When you try to exit, stop hook intercepts
  4. Same prompt fed back
  5. You see your previous work
  6. Continues until promise detected or max iterations

/cancel-ralph

Cancel an active Ralph loop (removes the loop state file).

Usage:

/cancel-ralph

How it works:

  • Checks for active loop state file
  • Removes .claude/.ralph-loop.local.md
  • Reports cancellation with iteration count

Key Concepts

Completion Promises

To signal completion, Claude must output a <promise> tag:

<promise>TASK COMPLETE</promise>

The stop hook looks for this specific tag. Without it (or --max-iterations), Ralph runs infinitely.

Read the full file on GitHub · 128 lines

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. 4d ago First seen · 128 lines · 776 tokens per session scan A d446fdbc99ba

Subscribe to this mod's changes

cmd-help is a cursor rule published in the GitHub repository nota-america/forgecat-agent-profiles (63 stars, last pushed today), licensed Apache-2.0. It adds 776 tokens to every session, about $0.0039 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 2026-08-30.