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
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.
npx skills add ax-llm/ax --skill ax-cpp-llmgit clone --depth 1 https://github.com/ax-llm/axWrote 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-cpp-llm)<a href="https://agentmods.dev/skills/ax-llm/ax/ax-cpp-llm"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-cpp-llm/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-cpp-llm"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-cpp-llm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.00626 |
| Opus 5.5 | $0.00015 | $0.00250 |
| Sonnet 5.5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
ax-cpp-llm 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ax For C++
Use this entry point when working with axllm. Read the guides relevant to the task before writing code. The guides are bundled locally; no additional skill installation is needed. Load more guides when a task crosses into another area.
Choose A Guide
| Task | Read |
|---|---|
| Start a program, choose native factories, or find package docs and examples | Quick reference |
| provider clients and model routing | AxAI Providers |
| decision signatures and native questions | Typesafe / Jev |
| audio and realtime provider mappings | Ax Audio And Realtime |
| signatures, fields, schemas, and validation | Ax Signatures |
| structured generation and tools | AxGen Structured Generation |
| RLM agents and tools | AxAgent |
| runtime sessions and actor-code execution | AxAgent RLM Runtime |
| memory, recall, and dynamic skill loading | AxAgent Memory And Skills |
| traces, logs, usage, and diagnostics | AxAgent Observability |
| agent evaluation and optimization artifacts | AxAgent Optimize |
| choosing context maps, policy, optimization, and recall | AxAgent Context Selection |
| workflow graphs and orchestration | AxFlow |
| Pareto optimization and prompt evolution | Ax GEPA |
| evolving context playbooks | Ax Playbook |
| candidate improvement and evaluation feedback | Ax Refinement Patterns |
For an agent with persistent recall, read the agent and memory guides. For a provider-backed workflow, read the AI, generation, and flow guides.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ax-cpp-agent-context.md 1.9 KB
- references/ax-cpp-agent-memory-skills.md 4.0 KB
- references/ax-cpp-agent-observability.md 4.6 KB
- references/ax-cpp-agent-optimize.md 1.8 KB
- references/ax-cpp-agent-rlm.md 1.8 KB
- references/ax-cpp-agent.md 13 KB
- references/ax-cpp-ai.md 30 KB
- references/ax-cpp-audio.md 4.3 KB
- references/ax-cpp-flow.md 12 KB
- references/ax-cpp-gen.md 27 KB
- references/ax-cpp-gepa.md 1.6 KB
- references/ax-cpp-playbook.md 1.8 KB
- references/ax-cpp-refine.md 1.8 KB
- references/ax-cpp-signature.md 11 KB
- references/ax-cpp-typesafe.md 8.4 KB
- references/quickstart.md 3.2 KB
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 bc9b73114dda
- 2d ago Changed 272e53dda338
- 3d ago Changed · -13 lines 6a645a7cf5a7
- 5d ago Changed 78bacfd8ff2a
- 7d ago Changed 3157c36d5588
- 9d ago Changed 4d855de62353
- 12d ago Changed fdd9f239f65e
- 13d ago Changed a536c6e28c9f
- 14d ago Changed fcc82c3f2647
- 20d ago First seen · 51 lines · 38 tokens per session scan A aa7bc62434e1
ax-cpp-llm is a skill published in the GitHub repository ax-llm/ax (2,968 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 626 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
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…
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.
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.