ax-python-agent-rlm

A Python coding aid for axllm, a package for building language-model agents that can run code through runtime sessions. RLM means a loop where an agent reasons and executes code repeatedly.

In plain words
What is it for?
Setting up code-execution sessions, using process or JavaScript/Python runtimes, and working with runtime state and capability details.
Why use it?
It helps connect agents to code runtimes and manage the information passed between the agent and those runtimes.

Skill for Claude CodeCodex

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 skills/ax-llm/ax/ax-python-agent-rlm
Any agent
npx skills add ax-llm/ax --skill ax-python-agent-rlm
Clone the repo
git clone --depth 1 https://github.com/ax-llm/ax

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00041 $0.00441
Opus 5 $0.00020 $0.00220
Sonnet 5 $0.00008 $0.00088
Haiku 4.5 $0.00004 $0.00044

Measured today against content hash 552728bc5445, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ax-python-agent-rlm 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.

Origin

This is a copy

89% identical to ax-cpp-agent-rlm — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

packages/python/skills/ax-python-agent-rlm/SKILL.md · 47 lines

What it actually says

AxAgent RLM Runtime For Python

This skill helps an agent write Python code with the generated Ax package axllm. Use the generated package API, examples, and manifests; do not import TypeScript-only APIs unless you are editing the TypeScript package.

When To Use

  • Wire an AxCodeRuntime or AxCodeSession implementation.
  • Use ProcessCodeRuntime or an optional runtime profile for actor-code sessions.
  • Explain that generated packages are not TypeScript transpilers; they adapt the Ax runtime contract.

Package Facts

  • Language: Python.
  • Package: axllm.
  • Package API docs: API.md and axir-api.json.
  • Capability manifest: axir-capabilities.json.
  • Runnable examples: examples/.
  • Real network support: yes.
  • Scripted no-key transport support: yes.
  • Runtime profiles: javascript-quickjs, python-pyodide.

Core Pattern

from axllm import agent

helper = agent("question:string -> answer:string")
out = helper.forward(llm, {"question": "How should I proceed?"})

Relevant API Surface

  • Agents And RLM: agent, AxAgent
  • Runtime Profiles: ProcessCodeRuntime, RuntimeCapabilities, RuntimeEnvelope, javascript-quickjs, python-pyodide

Guardrails

  • Start from package examples for exact native syntax before inventing a new call shape.
  • Use provider-api examples only when the user explicitly has provider credentials available.
  • Use no-key examples for deterministic local checks and provider request mapping.
  • Treat AxIR as the source of generated package truth: if package docs disagree with source code, update the compiler and regenerate packages.
  • Do not copy repo-maintainer skills from tools/*/skills/ into user packages.
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. today Changed 552728bc5445
  2. 3d ago First seen · 47 lines · 41 tokens per session scan A 5abd5cd6f544

Subscribe to this mod's changes

ax-python-agent-rlm is a skill published in the GitHub repository ax-llm/ax (2,890 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 441 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to ax-cpp-agent-rlm, differing in 22 lines, and is treated as a copy.

Related

Other skills, from other repositories

add-harness-package

Guide for adding new AI SDK harness packages. Use when creating a new @ai-sdk/harness- package that adapts a coding-agent runtime to HarnessV1.

vercel/ai · 41 tokens

cubepi

Use when building, extending, or debugging agents with the CubePi framework. Covers the Agent API, providers, tools, middleware, checkpointing, MCP integration, and HITL. References the cubepi-trace skill for run debugging.

cubeplexai/cubepi · 50 tokens

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

nodetool-ai/nodetool · 22 tokens

nodetool-chat-cli

Use NodeTool chat CLI commands, interactive terminal, agent mode, workspace management, and Global Chat features. Use when user asks about chat commands, interactive terminal, chat features, agent mode in chat, or the Global Chat interface.

nodetool-ai/nodetool · 52 tokens

nodetool-browser-agent

Create browser automation agents that navigate websites, extract data, fill forms, and perform multi-step web tasks using natural language instructions. Use when user asks to automate browsing, scrape websites with AI, build a web agent, or perform complex browser interactions.

nodetool-ai/nodetool · 55 tokens

maintain-model-list

Maintain the supported LLM model list: add a new model, or run routine maintenance to verify availability and discover new models worth adding. Use when the user asks to add/support a model, update the model list, or check model availability.

alibaba/page-agent · 53 tokens