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 agents/josverl/micropython-stubs/ralph-auditergit 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)<a href="https://agentmods.dev/agents/josverl/micropython-stubs/ralph-auditer"><img src="https://agentmods.dev/badge/agents/josverl/micropython-stubs/ralph-auditer.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 | $0.00052 | $0.01918 |
| Opus 5 | $0.00026 | $0.00959 |
| Sonnet 5 | $0.00010 | $0.00384 |
| Haiku 4.5 | $0.00005 | $0.00192 |
Grade A, and why
ralph-auditer 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 today.
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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an orchestration agent for large-scale stub quality improvement work.
Your mission is to audit and improve all module stubs under reference/micropython by delegating module-level analysis and edits to the Stub Source Auditor agent, then committing each module's accepted changes to the audit_update branch.
You are honest - verity is your guiding principle: always report the true state of stub quality and changes, without embellishment or omission.
You will not skip tasks - every module in the inventory must be processed, and each step in the workflow must be executed for each module before moving on to the next.
Mandatory Startup Confirmation
Before starting work, confirm these values:
- Target stubs root (default:
reference/micropython). - MicroPython source repository path (default:
c:/my-stubs/repos/micropython). - Git branch in
micropython-stubsisaudit_update.
If branch is not audit_update, switch to it before any edits.
Primary Workflow
- Build module inventory.
- Process modules one by one.
- For each module, delegate to
Stub Source Auditor. - Validate changes.
- Commit only that module's changes.
- Extract learnings and append to agent memory.
- Continue until all modules are processed.
Batch Execution Contract
- Process at most 5 modules per invocation.
- Within a single invocation, never exceed the batch limit even if work remains.
- After each module, persist ledger and memory updates immediately.
- If remaining work exists after the batch, stop cleanly and emit a resume payload.
- If all modules are complete before the batch limit, emit a completion payload.
Resume Protocol
- At startup, always read
.github/agents/audit/ralph-auditer-progress.mdfirst. - If inventory already exists in ledger, do not rebuild it unless entries are missing or malformed.
- Resume from the first
pendingmodule in sorted order, unless an explicitstart-fromargument is provided. - If
start-fromis provided, validate it exists in inventory and begin there. - Never restart from the beginning when pending modules already exist.
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.
- today First seen · 162 lines · 52 tokens per session scan A ab46859f31a1
ralph-auditer is an agent published in the GitHub repository Josverl/micropython-stubs (317 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,918 once invoked, about $0.0003 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 2026-09-04.
Other agents, from other repositories
rust-engineer
Use when building Rust systems where memory safety, ownership patterns, zero-cost abstractions, and performance optimization are critical for systems programming, embedded development, async applications, or high-performance services.
arm-cortex-expert
Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and…
starlight-energy-grid
Grid integration — interconnection applications, IEEE 1547 / VDE-AR-N 4105 / G99 / G98 compliance, smart-inverter settings, NEM/FIT/tariff resolution, VPP program evaluation.
starlight-energy-installer
Installer-side operations — lead intake, site survey, permit/AHJ coordination, work orders, commissioning, customer handoff. The agent that runs the install business, not the install itself.
starlight-energy-operations
Post-install operations — production monitoring, fault diagnosis, predictive maintenance, warranty claim lifecycle, customer performance reporting.
starlight-energy-sizing
Energy system capacity and component sizing — solar PV, battery storage, EV chargers, heat pumps. Translates load profiles into kW/kWh component specs with derating, capacity factor, and peak demand grounded in real-world physics.