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.
Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/ax-llm/ax/ax-gepa)<a href="https://agentmods.dev/skills/ax-llm/ax/ax-gepa"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-gepa/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.
<a href="https://agentmods.dev/skills/ax-llm/ax/ax-gepa"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-gepa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00071 | $0.02526 |
| Opus 5 | $0.00036 | $0.01263 |
| Sonnet 5 | $0.00014 | $0.00505 |
| Haiku 4.5 | $0.00007 | $0.00253 |
Grade A, and why
ax-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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ax-gepa — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEPA Optimization Codegen Rules (@ax-llm/ax)
Use this skill to generate GEPA optimization code. Prefer the top-level optimize(...) helper for normal code, and use direct AxGEPA / AxBootstrapFewShot only when the user needs low-level optimizer control.
Use These Defaults
- Use
optimize(program, train, metric, { studentAI, teacherAI, ... })for normal generator and flow tuning. - Prefer
ai(),ax(), andflow()for new code. - Use a strong
teacherAIand a cheaperstudentAI. - Pass
validationExampleswhen you have a holdout set. - Set
maxMetricCallsto bound optimizer cost;optimize(...)defaults it to100. - Use scalar metrics for one objective and object metrics for Pareto optimization.
- Apply results with
program.applyOptimization(result.optimizedProgram!). - For tree-wide runs, expect
optimizedProgram.componentMap. - Persist artifacts with
axSerializeOptimizedProgram(...)and restore them withaxDeserializeOptimizedProgram(...)so the same flow works in browsers and Node. optimize(...)runsAxBootstrapFewShot -> AxGEPAfor small starter sets by default, preserving the demos inresult.optimizedProgram.demos.
Critical Rules
optimize(...)andAxGEPA.compile()work for a single generator and for tree-aware roots such as flows or agents with registered optimizable descendants.- There is no separate flow-only GEPA optimizer. Use
AxGEPAfor flows too. - The metric may return either
numberorRecord<string, number>. - Keep metrics deterministic and cheap by default.
- Avoid extra LLM calls inside the metric unless the user explicitly wants judge-based evaluation.
- If the user needs LLM-as-judge scoring for a non-agent GEPA run, prefer a plain typed
AxGenevaluator instead of writing a custom judge abstraction. maxMetricCallsmust be large enough to cover the initial validation pass overvalidationExamples.- GEPA optimizes generic string components exposed by
getOptimizableComponents(). If a tree exposes no components, optimization will fail. - Use held-out validation examples for selection. Do not reuse the training set as
validationExamples. result.optimizedProgramis the easy-to-apply best candidate.result.paretoFrontis the full trade-off set for multi-objective runs.- Direct
AxGEPAstill has its ownbootstrapoption, but top-leveloptimize(...)composes the existingAxBootstrapFewShotoptimizer before GEPA instead.
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.
- 3d ago Changed 51dba55208cb
- 6d ago First seen · 265 lines · 71 tokens per session scan A 3918cd644aa4
ax-gepa is a skill published in the GitHub repository ax-llm/ax (2,894 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 2,526 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
output-dev-prompt-file
Create .prompt files for LLM operations in Output SDK workflows. Use when designing prompts, configuring LLM providers, or using Liquid.js templating.
output-dev-eval-testing
Create offline evaluation tests for Output SDK workflows using @outputai/evals. Use when implementing test evaluators with verify(), creating dataset YAML files, building eval workflows, or running workflow tests via CLI.
output-dev-step-function
Create step functions in steps.ts for Output SDK workflows. Use when implementing I/O operations, error handling, HTTP requests, or LLM calls.
output-meta-project-context
Comprehensive guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal. Covers project structure, workflow patterns, steps, LLM integration, HTTP clients, CLI commands, and the full inventory of available agents and skills.
output-eval-dataset-design
Design diverse eval datasets using dimension-based variation. Use when bootstrapping eval datasets, when real traces are sparse, or when existing datasets miss edge cases.
output-eval-judge-prompt
Design effective LLM judge .prompt files for evaluators. Use when creating judgeVerdict/judgeScore/judgeLabel prompts, or when existing judges produce unreliable results.