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.
git clone --depth 1 https://github.com/Arthur742Ramos/ralph-wiggum-windowsWrote 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.
[](https://agentmods.dev/commands/arthur742ramos/ralph-wiggum-windows/help-ralph)<a href="https://agentmods.dev/commands/arthur742ramos/ralph-wiggum-windows/help-ralph"><img src="https://agentmods.dev/badge/commands/arthur742ramos/ralph-wiggum-windows/help-ralph/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/arthur742ramos/ralph-wiggum-windows/help-ralph"><img src="https://agentmods.dev/badge/commands/arthur742ramos/ralph-wiggum-windows/help-ralph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00009 | $0.00769 |
| Opus 5.5 | $0.00004 | $0.00308 |
| Sonnet 5.5 | $0.00002 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
help-ralph scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- help — 92% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Wiggum Plugin Help (Windows)
Please explain the following to the user:
What is the Ralph Wiggum Technique?
The Ralph Wiggum technique is an iterative development methodology based on continuous AI loops, pioneered by Geoffrey Huntley.
Core concept:
while ($true) {
Get-Content PROMPT.md | claude-code --continue
}
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:
- Claude receives the SAME prompt
- Works on the task, modifying files
- Tries to exit
- Stop hook intercepts and feeds the same prompt again
- Claude sees its previous work in the files
- Iteratively improves until completion
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:
- Creates
.claude/ralph-loop.local.mdstate file - You work on the task
- When you try to exit, stop hook intercepts
- Same prompt fed back
- You see your previous work
- Continues until promise detected or max iterations
/cancel-ralph
Cancel an active Ralph loop (removes the loop state file).
Usage:
/cancel-ralph
Windows-Specific Notes
This is a Windows-compatible implementation that uses PowerShell instead of bash/jq:
- Stop hook:
stop-hook.ps1(PowerShell) - Setup script:
setup-ralph-loop.ps1(PowerShell) - No jq dependency: Uses
ConvertFrom-Json - No bash dependency: Pure PowerShell
Key Concepts
Completion Promises
To signal completion, Claude must output a <promise> tag:
<promise>TASK COMPLETE</promise>
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.
- 2mo ago First seen · 119 lines · 9 tokens per session scan A ac804222807c
help-ralph is a command published in the GitHub repository Arthur742Ramos/ralph-wiggum-windows (6 stars, last pushed 10mo ago), licensed MIT. It adds 9 tokens to every session and 769 once invoked, about $0.0000 per session on Opus 5.5. 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.
help-ralph compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| help-ralphArthur742Ramos/ralph-wiggum-windows | Command | 6 | 10mo ago | MIT | A | 9 | Claude Code |
| checklistgithub/spec-kit | Command | 149k | today | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 149k | today | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 149k | today | MIT | A | 13 | Claude Code |
| convergegithub/spec-kit | Command | 149k | today | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 149k | today | MIT | A | 14 | Claude Code |
| speckit.bug.fixgithub/spec-kit | Command | 149k | today | MIT | A | 12 | Claude Code |