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-playbookgit 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-playbook)<a href="https://agentmods.dev/skills/ax-llm/ax/ax-cpp-playbook"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-cpp-playbook/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-playbook"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-cpp-playbook.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 | $0.00049 | $0.00516 |
| Opus 5.5 | $0.00020 | $0.00206 |
| Sonnet 5.5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
ax-cpp-playbook 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- ax-rust-playbook — 89% identical, 23 lines differ
- ax-go-playbook — 88% identical, 24 lines differ
- ax-python-playbook — 86% identical, 22 lines differ
- ax-cpp-refine — 81% identical, 20 lines differ
- ax-python-refine — 77% identical, 30 lines differ
- ax-java-playbook — 75% identical, 22 lines differ
- ax-go-agent-context — 73% identical, 33 lines differ
- ax-go-gepa — 72% identical, 31 lines differ
What it actually says
Ax Playbook 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
- Grow an evolving context playbook for a program or agent stage with playbook().
- Attach a seed playbook to an agent and learn bounded avoidance rules from run-end failure signals.
- Use the agent-bound playbook evolve method to mine grounded weaknesses with verification and exact rollback.
- Refine a playbook online from live feedback or offline from labeled examples.
- Render or persist a playbook and inject it into a program context.
Package Facts
- Language: C++.
- Package:
axllm. - Package API docs:
API.mdandaxir-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
auto program = axllm::ax("question:string -> answer:string");
auto pb = axllm::playbook(program, *llm);
pb.evolve(examples, metric_fn);
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-apiexamples only when the user explicitly has provider credentials available. - Use
no-keyexamples 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.
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 fd57065831c2
- 2d ago Changed 339f3645323a
- 4d ago Changed d32a473817ff
- 6d ago Changed f37f9e2b1b1d
- 8d ago Changed 0830f1f8227a
- 11d ago Changed 4c1d328ef90b
- 12d ago Changed 0df86a5cbfb3
- 13d ago Changed ebd476768e97
- 19d ago Changed ac58e3f5876e
- 22d ago First seen · 47 lines · 49 tokens per session scan A ce50ea6f5e88
ax-cpp-playbook is a skill published in the GitHub repository ax-llm/ax (2,967 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 516 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
output-dev-code-style
Code style conventions for Output SDK workflow projects. Use when writing or reviewing any TypeScript/JavaScript code. Discovers the project's own linting rules first; falls back to Output SDK conventions when no linter is configured.
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…
pn-godot-dev
Guides Godot Engine 4.x development: GDScript, GDExtension (C++), multiplayer, VisualShader/shader code, export/platform config, autoloads, Resource serialization, InputMap, headless CI, AnimationPlayer/Tree, 2D/3D workflows, physics, PCG, and Blender pipeline. Use when developing Godot 4.x projects.
pn-unreal-dev
Guides Unreal Engine development: C++, Blueprints, asset naming, build config, plugin development, programmatic asset creation, live uasset creation, Python automation, UAT/BuildGraph, Editor Utility Widgets, Data Validation, Materials, Niagara, PCG, and performance. Use when developing Unreal Engine projects.
typescript-expert
TypeScript best practices, advanced types, and patterns.
psl-ast-layers
How to use the PSL syntax tree layers (green tree, red tree, strongly-typed AST classes) correctly. Use for any PSL-related work: PSL interpreters (contract-psl), helpers inside the psl-parser package, the language server, formatters, or anything else that consumes parse() output from @internal/psl-parser.