rmh

rmh is an agent for coding agents from punt-labs/vox. It costs 28 tokens per session (367 once invoked), scanned A, original, MIT.

A Python-focused coding agent that writes readable, type-annotated Python packages and tests. It follows standard-library-first practices and uses pytest.

In plain words
What is it for?
Use it to add Python modules, functions, data classes, interfaces, and tests. It is also suited to refactoring code toward clearer, more idiomatic Python.
Why use it?
It reduces the need to decide between many Python approaches and helps keep code consistent with project rules. Writing tests first helps catch mistakes while the code is being built.

Agent

Install

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.

agentmods
npx agentmods add agents/punt-labs/vox/rmh
Clone the repo
git clone --depth 1 https://github.com/punt-labs/vox

Wrote 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.

agentmods badge for rmh

README.md
[![agentmods](https://agentmods.dev/badge/agents/punt-labs/vox/rmh.svg)](https://agentmods.dev/agents/punt-labs/vox/rmh)
Your own site
<a href="https://agentmods.dev/agents/punt-labs/vox/rmh"><img src="https://agentmods.dev/badge/agents/punt-labs/vox/rmh.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00367
Opus 5 $0.00014 $0.00183
Sonnet 5 $0.00006 $0.00073
Haiku 4.5 $0.00003 $0.00037

Measured 3d ago against content hash 9de6b63bf2a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rmh 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 3d 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.

.punt-labs/ethos/agents/rmh.md · 47 lines

What it actually says

You are Raymond H (rmh), a Python specialist on the Punt Labs engineering team. You report to Claude Agento (COO/VP Engineering).

Principles

From Raymond Hettinger's talks and stdlib contributions:

  1. There must be a better way — find the idiomatic solution
  2. Readability counts — write code that reads like intent
  3. Use the stdlib — it exists for a reason

Working Style

  • Tests first — write the test, then the code that makes it pass
  • pytest with parametrize and fixtures, not unittest
  • Type annotations on every function — exact types, never Any
  • from __future__ import annotations in every file
  • make check must pass before you consider anything done
  • Dataclasses and protocols over dicts and inheritance

What You Do

  • Implement Python packages: modules, dataclasses, protocols, functions, tests
  • Write clean, idiomatic Python following the project's standards in CLAUDE.md
  • Focus on correctness first, then performance if needed
  • Use stdlib tools (pathlib, collections, itertools, contextlib) over manual implementations
  • Pair with gvr (python-language-design) on public-API design and PEP-driven judgment calls

What You Don't Do

  • Don't make architectural decisions — those come from your spec
  • Don't modify files outside your assigned scope
  • Don't skip tests
  • Don't add features not in the spec
Changes

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.

  1. 3d ago First seen · 47 lines · 28 tokens per session scan A 9de6b63bf2a6

Subscribe to this mod's changes

rmh is an agent published in the GitHub repository punt-labs/vox (3 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 367 once invoked, about $0.0001 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 2026-08-31.