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 axir-language-backendgit 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/axir-language-backend)<a href="https://agentmods.dev/skills/ax-llm/ax/axir-language-backend"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/axir-language-backend/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/axir-language-backend"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/axir-language-backend.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 | $0.00057 | $0.01646 |
| Opus 5 | $0.00028 | $0.00823 |
| Sonnet 5 | $0.00011 | $0.00329 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
axir-language-backend 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AxIR Language Backend
Use this for work on generated Ax libraries such as Python, Java, C++, Go, or future Rust. This is not an Ax product skill from src/ax/skills/; it is repo-local guidance for compiler/backend implementation.
First Checks
- Confirm the target is a generated Ax user library, not a public AxIR API.
- Inspect current target seams before editing:
tools/axir/internal/axir/codegen.go,verify.go,runtime_model.go, the existing*_core_emit.gofiles, and target templates. - Check user-facing package names in docs before choosing names. Do not expose
axir,ax-go, or compiler-internal branding in generated library metadata.
Backend Implementation Rules
- Keep semantics Core-owned. Provider mapping, Agent context/runtime behavior, Flow graph semantics, optimizer/GEPA behavior, envelopes, state, logs, and traces should come from Core helpers/descriptors.
- Keep target code idiomatic but thin. Target templates own language wrappers, dynamic value representation, transports, error boundary shape, package metadata, and examples.
- Prefer standard-library dependencies for base packages. Optional runtime profiles may remain dependency-bearing and opt-in.
- Use deterministic ordering for generated output, JSON/string rendering, prompt fields, snapshots, catalogs, action logs, and conformance output.
- Public APIs should feel native in the target language while preserving Ax concepts. Document unavoidable naming differences in generated README/examples.
- Capability manifests must be truthful. Do not list
unsupported_capabilitiesfor a generated package that is included in default verification; either implement the surface or remove the public/manifest claim. - Concrete public generated methods must never be placeholder-only bodies such as
pass,return None,return null,return nil,Value::Null, empty vectors, or generic "not implemented"/"unsupported" fallbacks. Validation errors remain acceptable for invalid inputs, unknown provider names, and unknown runtime protocol ops. - Abstract/base interfaces may describe fallible boundaries, but every concrete generated class/struct that is advertised by the manifest must implement claimed provider, router, balancer, runtime session, AxGen, AxAgent, AxFlow, and optimizer operations.
- Conformance dispatch must be explicit for all claimed feature groups. Do not add a silent catch-all that makes unsupported fixture kinds pass without executing an implementation path.
- Conformance coverage must be semantic, not just dispatch-shaped. Every generated package must emit
conformance-coverage.jsonwith each claimed fixture kind/operation classified assemantic,validation-error,transport-boundary, orexplicitly-not-claimed; default-verified targets must not usepresence-only. - Runner code must reject guard-only shortcuts: no broad expectation helpers, empty fixture arms, suite-name-only dispatch, self-comparisons, or checks that only prove an expected key exists. If a fixture expects a validation error, tie the generated error to the fixture expectation and keep the implementation path explicit.
- Provider API and no-key examples must cover every claimed public surface class: chat, stream, embeddings, audio/realtime mapping helpers when claimed, routers/balancers, runtime protocol, AxGen, AxAgent, AxFlow, and optimizer artifacts.
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 · +14 lines f91e019fd1ea
- 7d ago First seen · 60 lines · 57 tokens per session scan A 0fbf95c5410e
axir-language-backend is a skill published in the GitHub repository ax-llm/ax (2,894 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 1,646 once invoked, about $0.0003 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-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…
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.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
migrate-oxfmt
Guide for migrating a project from Prettier or Biome to Oxfmt. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's formatter from Prettier or Biome to Oxfmt.