What is ax-cpp-agent-optimize?

A guide for improving C++ agents built with axllm by testing them, studying failures, and refining reusable instructions. GEPA and BootstrapFewShot are methods for automatically improving an agent from examples and evaluations.

Use it to create evaluators, optimize an AxAgent, build reusable playbooks, and save the results of bounded improvement runs.

It provides a structured way to find weak results and keep only improvements that pass checks. This reduces guesswork when tuning an agent or its instructions.

ax-cpp-agent-optimize — Skill by ax-llm

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-agent-optimize

Any agent

npx skills add ax-llm/ax --skill ax-cpp-agent-optimize

Clone the repo

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

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 481 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.

Model	Per session	Once invoked
Fable 5	$0.00045	$0.00481
Opus 5	$0.00023	$0.00241
Sonnet 5	$0.00009	$0.00096
Haiku 4.5	$0.00005	$0.00048

Measured today against content hash 9f3a44f36818, 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-agent-optimize 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

Copies of this mod

1 near-identical copy found in the catalogue:

ax-python-agent-optimize — 89% identical, 22 lines differ

packages/cpp/skills/ax-cpp-agent-optimize/SKILL.md · 46 lines

What it actually says

AxAgent Optimize 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

Optimize an AxAgent or reusable program component.
Mine grounded weaknesses from failed agent tasks and keep only playbook proposals that pass the verification gate.
Create evaluator callbacks and persist optimizer artifacts.
Keep optimization runs bounded by explicit budgets and dataset rows.

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

Agents And RLM: axllm::agent, axllm::AxAgent
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.

today Changed 9f3a44f36818
2d ago First seen · 46 lines · 45 tokens per session scan A 1fd1dfb57dc3

Subscribe to this mod's changes

ax-cpp-agent-optimize is a skill published in the GitHub repository ax-llm/ax (2,890 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 481 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.

LLM Writing and docs ai cohere javascript openai typescript

fmt

Format all code in the repository. Run before opening a PR or committing changes.

denoland/deno · 18 tokens

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, services, or HTTP communication, or for best practices on reactivity (signals, linkedSignal, resource, httpResource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component…

angular/angular · 77 tokens

ax-cpp-agent-optimize