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.
npx agentmods add commands/ronmkr/promptbook/ralph-loopgit clone --depth 1 https://github.com/ronmkr/PromptBookWrote 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/ronmkr/promptbook/ralph-loop)<a href="https://agentmods.dev/commands/ronmkr/promptbook/ralph-loop"><img src="https://agentmods.dev/badge/commands/ronmkr/promptbook/ralph-loop.svg" alt="Measured on agentmods" 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 | $0.00006 | $0.00212 |
| Opus 5 | $0.00003 | $0.00106 |
| Sonnet 5 | $0.00001 | $0.00042 |
| Haiku 4.5 | $0.00001 | $0.00021 |
Grade A, and why
ralph-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
95% identical to ralph-loop — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Ralph Loop Command
Execute the setup script to initialize the Ralph loop:
"${GEMINI_PLUGIN_ROOT}/scripts/setup-ralph-loop.sh" $ARGUMENTS
Please work on the task. When you try to exit, the Ralph loop will feed the SAME PROMPT back to you for the next iteration. You'll see your previous work in files and git history, allowing you to iterate and improve.
CRITICAL RULE: If a completion promise is set, you may ONLY output it when the statement is completely and unequivocally TRUE. Do not output false promises to escape the loop, even if you think you're stuck or should exit for other reasons. The loop is designed to continue until genuine completion.
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.
- yesterday First seen · 19 lines · 6 tokens per session scan A 94ddc1f97d5b
ralph-loop is a command published in the GitHub repository ronmkr/PromptBook (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 6 tokens to every session and 212 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to ralph-loop, differing in 4 lines, and is treated as a copy.
Other commands, from other repositories
new-collection
Author a new Operator issuetype collection — a shareable AI workflow.
shortreply
Keep replies short — AI sends only changed lines.
mem-worklog
Turn a week of session archives into a worklog — daily hours table prorated over a fixed daily amplitude, plus an activity report and next-week objectives.
plan
Create implementation plan with risk assessment.
restart
Prepare for a fresh session by saving all current context, progress, and decisions.
caveman-compress
Compress a markdown/text file into caveman format to save tokens.