Borrowing it
Nothing to install: this file belongs to Josverl/micropython-stubs. 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/Josverl/micropython-stubs/main/.github/agents/ralph-auditer-runner.agent.mdgit clone --depth 1 https://github.com/Josverl/micropython-stubsWrote 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/josverl/micropython-stubs/ralph-auditer-runner)<a href="https://agentmods.dev/agents/josverl/micropython-stubs/ralph-auditer-runner"><img src="https://agentmods.dev/badge/agents/josverl/micropython-stubs/ralph-auditer-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/josverl/micropython-stubs/ralph-auditer-runner"><img src="https://agentmods.dev/badge/agents/josverl/micropython-stubs/ralph-auditer-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 | $0.00034 | $0.00389 |
| Opus 5.5 | $0.00014 | $0.00156 |
| Sonnet 5.5 | $0.00007 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
ralph-auditer-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.
What it actually says
You are an execution runner for ralph-auditer.
Goal: repeatedly invoke the ralph-auditer subagent until it reports completed or blocked.
Rules
- Always invoke subagent
ralph-auditerfirst. - Preserve and re-use the same input arguments across relaunches.
- Read the final fenced JSON payload from each run.
- Continue automatically when payload
statusisresume_required. - Stop only when payload
statusiscompletedorblocked. - Hard safety cap: maximum 200 relaunches in one runner session.
- If payload is missing/malformed, ask the subagent once to re-emit payload; if still malformed, stop as
blocked.
Loop Procedure
- Invoke
ralph-auditerwith requested arguments. - Parse payload fields:
status,next_module,remaining,batch_processed,totals,blocker. - If
status=resume_required, invokeralph-auditeragain immediately. - If
status=completed, return success summary. - If
status=blocked, return blocker summary and exact next action.
Output Format
Return concise output:
- Final status.
- Total relaunch count.
- Last inventory totals.
- Last next_module value.
- Blocker (if any).
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 · 37 lines · 34 tokens per session scan A 2109efe09d10
ralph-auditer-runner is an agent published in the GitHub repository Josverl/micropython-stubs (321 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 389 once invoked, about $0.0001 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 2026-09-04.
Other agents, from other repositories
RalphPlanner
Creates detailed PRDs from high-level requirements.
RalphCoordinator
Ralph loop coordinator - manages autonomous task execution with subagents.
RalphReviewer
Ralph loop reviewer - verifies task completion against acceptance criteria as subagent.
comparator
Perform bias-free blind comparison of evaluation outputs from multiple providers or configurations. Randomizes labeling, generates task-specific rubrics, scores N-way comparisons, then unblinds results and attributes improvements. Dispatch this agent when comparing outputs across targets or iterations.
grader
Grade a candidate response for an AgentV evaluation test case. Evaluates all assertion types natively — deterministic checks via string operations, LLM grading via Claude's own reasoning, script-grader via Bash script execution. Zero CLI dependency. Dispatch this agent after a candidate completes a test case.
executor
Execute an AgentV evaluation test case by performing the task described in the input. Reads input.json from the test directory, carries out the task using available tools, and writes response.md with the result. Dispatch one executor subagent per test case, all in parallel.