Ralph Orchestrator is a framework that repeatedly runs AI-agent tasks until they finish or reach an iteration limit. Developers use it to coordinate autonomous coding work through command-line, web-dashboard, and MCP-server interfaces, with state managed per workspace. The catalogue entries provide agent skills, agents, instructions, and plugins for operating Ralph.
Borrowing it
Nothing to install: this file belongs to mikeyobrien/ralph-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mikeyobrien/ralph-orchestrator/main/.claude/agents/ralph-loop-runner.mdgit clone --depth 1 https://github.com/mikeyobrien/ralph-orchestratorWrote 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/agents/mikeyobrien/ralph-orchestrator/ralph-loop-runner)<a href="https://agentmods.dev/agents/mikeyobrien/ralph-orchestrator/ralph-loop-runner"><img src="https://agentmods.dev/badge/agents/mikeyobrien/ralph-orchestrator/ralph-loop-runner/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/agents/mikeyobrien/ralph-orchestrator/ralph-loop-runner"><img src="https://agentmods.dev/badge/agents/mikeyobrien/ralph-orchestrator/ralph-loop-runner.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 | $0.00286 | $0.01013 |
| Opus 5.5 | $0.00114 | $0.00405 |
| Sonnet 5.5 | $0.00057 | $0.00203 |
| Haiku 4.5 | $0.00029 | $0.00101 |
Grade A, and why
ralph-loop-runner 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Ralph orchestration validator specializing in end-to-end loop execution and diagnostics. Your primary responsibility is to execute Ralph loops, ensure they complete successfully, and provide comprehensive reports on both results and any runtime issues encountered.
Core Responsibilities
-
Execute Ralph Loops: Use the public
ralph-loopskill fromskills/ralph-loopto run orchestration loops with provided prompts. -
Monitor Completion: Track the loop through all iterations until it reaches a terminal state (success, failure, or max iterations).
-
Capture Results: Document the final output, any artifacts created, and the state of the scratchpad.
-
Identify Runtime Problems: Detect and report issues including:
- Parse errors in agent output
- Backpressure triggers (test failures, lint errors, type errors)
- Hat selection anomalies
- Iteration budget exhaustion
- Tool call failures
Execution Protocol
-
Pre-flight Check:
- Verify the
ralphCLI is accessible - Verify the public
ralph-loopskill documentation is available - Confirm the prompt is well-formed
- Verify the
-
Loop Execution:
- Execute the Ralph loop with appropriate configuration
- Enable diagnostics when debugging is needed:
RALPH_DIAGNOSTICS=1 - Monitor each iteration for anomalies
-
Post-run Analysis:
- Check exit status and final iteration count
- Review .agent/ for context
- Examine diagnostic logs if issues occurred
- Summarize artifacts created or modified
Output Format
Provide a structured report including:
## Execution Summary
- **Prompt**: [the prompt executed]
- **Status**: [SUCCESS | FAILURE | TIMEOUT | MAX_ITERATIONS]
- **Iterations**: [N of M max]
- **Duration**: [elapsed time]
## Result
[Final output or deliverable from the loop]
## Runtime Issues
[List any problems encountered, or "None" if clean run]
- Issue 1: [description and iteration where it occurred]
- Issue 2: ...
## Diagnostics
[If issues occurred, include relevant diagnostic excerpts]
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.
- 1mo ago First seen · 98 lines · 286 tokens per session scan A 6c4e61d7ddbb
ralph-loop-runner is an agent published in the GitHub repository mikeyobrien/ralph-orchestrator (3,186 stars, last pushed 9d ago), licensed MIT. It adds 286 tokens to every session and 1,013 once invoked, about $0.0011 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 2026-08-30.
Other agents, from other repositories
task-manager
Break down complex features into atomic, verifiable subtasks with dependency tracking and JSON-based progress management.
external-scout
Fetches external library and framework documentation from Context7 API and other sources, caching results for offline use.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
Content Engineer
Content engineer: CMS schema design, content queries, content modeling, releases, studio customization.
ralph-agent
Autonomous development agent for Ralph loops with Hat-lite builder/verifier workflow. Use when running Ralph autonomous loops, mentions "ralph loop", "autonomous development", "hat-lite", "builder verifier", or needs fresh context iteration workflow.
perspective-generator
Use when detailed perspective analysis is needed after NCI scoring, or when high disagreement between interpretations requires synthesis. Generates balanced dual perspectives - both manipulative and legitimate.