What is ax-python-refine?

A Python workflow for improving text or other generated results with AxLLM, an AI-generation package, by using evaluators and optimization tools.

Use it to write Python code that evaluates generated candidates, runs AxLLM optimizers such as GEPA, and ports refinement ideas from TypeScript to Python.

It helps when a first generated result is not good enough and you need a repeatable way to use feedback to improve it.

ax-python-refine — Skill for Claude Code and Codex by ax-llm/ax

About the project

Ax is a TypeScript-first programming framework for building applications with large language models through typed generation, agents, workflows, and optimization tools. It is intended for developers who want one model for LLM programs across TypeScript, Python, Java, C++, Go, Rust, and other runtimes.

ax-llm/ax · 2,967 stars · on GitHub · axllm.dev

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.

Any agent

npx skills add ax-llm/ax --skill ax-python-refine

Clone the repo

git clone --depth 1 https://github.com/ax-llm/ax

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ax-llm/ax/ax-python-refine/github.svg)](https://agentmods.dev/skills/ax-llm/ax/ax-python-refine)

Your own site

<a href="https://agentmods.dev/skills/ax-llm/ax/ax-python-refine"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-python-refine/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ax-llm/ax/ax-python-refine"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-python-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 458 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin 77% 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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.00458
Opus 5.5	$0.00014	$0.00183
Sonnet 5.5	$0.00007	$0.00092
Haiku 4.5	$0.00003	$0.00046

Measured yesterday against content hash 8165b232cc0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ax-python-refine 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 yesterday.

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

77% identical to ax-cpp-playbook — 30 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-refine/SKILL.md · 47 lines

What it actually says

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

Improve generated outputs with evaluator feedback or optimizer artifacts.
Port TypeScript refinement intent into generated-language surfaces without assuming TypeScript-only helpers.
Use generated optimizer APIs when the target package does not expose a standalone refine helper.

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 AxGEPA

engine = AxGEPA(reflection_client)
result = engine.optimize(request, evaluator)

Relevant API Surface

AxGen: ax, AxGen, run_control, AxRunControl, Callable[[str, dict | None], dict | None], set_caching_function
Optimizers: optimize, playbook, AxPlaybook, AxBootstrapFewShot, AxGEPA, OptimizerEngine, OptimizerEvaluator

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.

yesterday Changed 8165b232cc0b
3d ago Changed d6e79f14e555
5d ago Changed 91835ff84aeb
8d ago Changed 03b0d405013e
9d ago Changed 7d02090c3db9
10d ago Changed a49b5a9ea786
16d ago Changed 22f13953ccff
19d ago Changed 1e2242715b06
21d ago Changed b88914d46c79
24d ago First seen · 47 lines · 35 tokens per session scan A 654486ef3de5

Subscribe to this mod's changes

ax-python-refine is a skill published in the GitHub repository ax-llm/ax (2,967 stars, last pushed 2d ago), licensed Apache-2.0. It adds 35 tokens to every session and 458 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 77% identical to ax-cpp-playbook, differing in 30 lines, and is treated as a copy.

Data and AI LLM Languages Python TypeScript ai cohere javascript openai

claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

hashgraph-online/awesome-codex-plugins · 53 tokens

migrating-llm-gateway-callers

Migrates an LLM caller from services/llm-gateway to PostHog/ai-gateway. Use when adding a gateway caller, converting an existing Python gateway integration, adopting shared Go-capable client builders, changing gateway URLs or headers for a caller, or removing a Python fallback. Inventories the caller's contract…

PostHog/posthog · 102 tokens

migrate-from-ai-sdk

Use when porting an app from the Vercel AI SDK (ai, @ai-sdk/) to @deuz-sdk/core. Triggers include "migrate from the AI SDK", "replace ai with @deuz-sdk/core", "we use streamText/generateText/useChat and want to switch", removing @ai-sdk/openai or @ai-sdk/anthropic, porting a toUIMessageStreamResponse route, converting…

Deuz-AI/Deuz-SDK · 118 tokens

ax-python-refine