ax-cpp-gepa

ax-cpp-gepa is a skill for Claude Code, Codex from ax-llm/ax. It costs 39 tokens per session (447 once invoked), scanned A, original, Apache-2.0.

A C++ guide for using the axllm package to optimize prompts or agent instructions with GEPA. GEPA compares candidates using an evaluator and keeps useful trade-offs and optimization results.

In plain words
What is it for?
Use it when writing C++ code for GEPA optimization, BootstrapFewShot setup, reflection clients, metric budgets, Pareto fronts, or saved optimization artifacts.
Why use it?
It helps choose the package's optimization patterns and track evaluation limits, reflection calls, candidate states, and result files correctly.

Skill for Claude CodeCodex

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 · 2,891 stars · on GitHub

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-cpp-gepa
Any agent
npx skills add ax-llm/ax --skill ax-cpp-gepa
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.

agentmods badge for ax-cpp-gepa

README.md
[![agentmods](https://agentmods.dev/badge/skills/ax-llm/ax/ax-cpp-gepa.svg)](https://agentmods.dev/skills/ax-llm/ax/ax-cpp-gepa)
Your own site
<a href="https://agentmods.dev/skills/ax-llm/ax/ax-cpp-gepa"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-cpp-gepa.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 447 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 $0.00039 $0.00447
Opus 5 $0.00019 $0.00224
Sonnet 5 $0.00008 $0.00089
Haiku 4.5 $0.00004 $0.00045

Measured 2d ago against content hash 134dbd689928, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ax-cpp-gepa 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 2d 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.

packages/cpp/skills/ax-cpp-gepa/SKILL.md · 44 lines

What it actually says

Ax GEPA For C++

This skill helps an agent write C++ 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

  • Run the generated GEPA optimizer or inspect a GEPA artifact.
  • Use BootstrapFewShot before GEPA when demonstrations should seed optimization.
  • Track metric budgets, reflection calls, candidate state, and Pareto fronts.

Package Facts

  • Language: C++.
  • 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

axllm::AxGEPA engine(reflection_client, options);
auto result = engine.optimize(request, evaluator);

Relevant API Surface

  • Optimizers: axllm::optimize, axllm::playbook, axllm::AxPlaybook, axllm::AxBootstrapFewShot, axllm::AxGEPA, axllm::OptimizerEngine, axllm::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.

  1. 2d ago Changed 134dbd689928
  2. 5d ago First seen · 44 lines · 39 tokens per session scan A 2b456dd64b4f

Subscribe to this mod's changes

ax-cpp-gepa is a skill published in the GitHub repository ax-llm/ax (2,891 stars, last pushed 3d ago), licensed Apache-2.0. It adds 39 tokens to every session and 447 once invoked, about $0.0002 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 2026-08-30.