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 skills add vcz-Gray/loophaus --skill ralph-claude-loopgit clone --depth 1 https://github.com/vcz-Gray/loophausWrote 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/skills/vcz-gray/loophaus/ralph-claude-loop)<a href="https://agentmods.dev/skills/vcz-gray/loophaus/ralph-claude-loop"><img src="https://agentmods.dev/badge/skills/vcz-gray/loophaus/ralph-claude-loop/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/skills/vcz-gray/loophaus/ralph-claude-loop"><img src="https://agentmods.dev/badge/skills/vcz-gray/loophaus/ralph-claude-loop.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 | $0.00034 | $0.01163 |
| Opus 5 | $0.00017 | $0.00581 |
| Sonnet 5 | $0.00007 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
ralph-claude-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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop (Claude Code)
Start a Loop optimized for Claude Code. This skill sets up the loop state, activates the official stop hook, and begins working on the first pending story from prd.json.
Prerequisites
- The
loophausplugin must be installed - A
prd.jsonfile must exist in the project root (generate one with/loop-plan)
How It Works
- This skill writes
.loophaus/state.json(the state file) - loophaus's stop hook reads this file and intercepts session exits
- Each iteration follows the Implement → Discover → Plan → Continue cycle
- When all stories pass: output
<promise>COMPLETE</promise>
Iteration Cycle (per story)
┌─ IMPLEMENT ─────────────────────────────┐
│ Pick next story → implement → verify │
└─────────────────────┬───────────────────┘
▼
┌─ DISCOVER ──────────────────────────────┐
│ Review what you just built. │
│ Did you find: │
│ - Hidden complexity? │
│ - Missing edge cases? │
│ - New dependencies? │
│ - Broken assumptions from the PRD? │
└─────────────────────┬───────────────────┘
▼
┌─ UPDATE PRD ────────────────────────────┐
│ If discoveries found: │
│ 1. Add new stories to prd.json │
│ 2. Log discoveries in progress.txt │
│ 3. Adjust max_iterations if needed │
│ If nothing new: skip │
└─────────────────────┬───────────────────┘
▼
┌─ CONTINUE ──────────────────────────────┐
│ Mark current story done → next story │
└─────────────────────────────────────────┘
Activation
Run the setup script to create the state file:
mkdir -p .loophaus && cat > .loophaus/state.json << 'LOOP_STATE'
{
"active": true,
"prompt": "Read prd.json for the task plan. Read progress.txt for current status (check Codebase Patterns section first). Pick the highest priority user story where passes is false. Implement that ONE story. Run verification: $VERIFY_CMD. On failure: read error, fix, retry up to 3 times. On success: commit with message feat: [Story ID] - [Story Title]. Update prd.json: set passes to true for the completed story. DISCOVERY PHASE — After completing the story, review what you just built: did implementation reveal hidden complexity not covered by existing stories? Are there missing edge cases, error handling, or integration points? Did you discover new dependencies or broken assumptions? Are there follow-up tasks needed for what you just built? If YES to any: add new user stories to prd.json with the next available ID (e.g. US-010), set passes: false, and set priority appropriately. Log the discovery in progress.txt under Discoveries section with rationale. If NO: skip, just append progress to progress.txt with learnings. If ALL stories (including newly added ones) have passes true, output <promise>COMPLETE</promise>. When stuck after 3 retries: set notes field in prd.json with error details, move to next story.",
"completionPromise": "COMPLETE",
"maxIterations": $MAX_ITERATIONS,
"currentIteration": 0,
"sessionId": ""
}
LOOP_STATE
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.
- 9d ago First seen · 102 lines · 34 tokens per session scan A e2b5304ae62d
ralph-claude-loop is a skill published in the GitHub repository vcz-Gray/loophaus (23 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,163 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…