ax-cpp-flow

A C++ guide for composing axllm programs into workflow graphs, where nodes read and write shared values.

In plain words
What is it for?
Use it to build C++ workflows with dependent steps, typed inputs and outputs, nested programs, dynamic options, caching, or optimizer components.
Why use it?
It explains how to connect generators, agents, and nested workflows while handling state, returns, caching, and errors. This makes multi-step AI workflows easier to define consistently.

Skill for Claude CodeCodex

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-flow
Any agent
npx skills add ax-llm/ax --skill ax-cpp-flow
Clone the repo
git clone --depth 1 https://github.com/ax-llm/ax

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,208 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.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.01208
Opus 5 $0.00018 $0.00604
Sonnet 5 $0.00007 $0.00242
Haiku 4.5 $0.00004 $0.00121

Measured today against content hash dd55674f0262, 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-flow 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

2 near-identical copies found in the catalogue:

packages/cpp/skills/ax-cpp-flow/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AxFlow 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

  • Compose generators, agents, and nested flows into a workflow graph.
  • Reason about flow state, node inputs, returns, caching, and errors.
  • Use generated package examples for flow graphs and provider-backed flows.

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

auto draft = axllm::ax("topicText:string -> draftText:string");
auto wf = axllm::flow(axllm::object({{"id", "docs.coreFlow"}}))
    .execute("draft", draft, axllm::object({
      {"reads", axllm::array({"topicText"})},
      {"writes", axllm::array({"draftResult", "draftText"})}
    }))
    .returns(axllm::object({{"draftText", "draftText"}}));

More Patterns

Typed programs

Build each flow node from its own input/output contract.

auto classifier = axllm::ax("requestText:string -> route:class \"support, sales, engineering\"");
auto responder = axllm::ax("requestText:string, route:string -> responseText:string");

Class decision

Declare reads and writes so the responder waits for the typed route.

auto branch_flow = axllm::flow(axllm::object({{"id", "docs.branchFlow"}}))
    .execute("classifier", classifier, axllm::object({{"reads", axllm::array({"requestText"})}, {"writes", axllm::array({"classifierResult", "route"})}}))
    .execute("responder", responder, axllm::object({{"reads", axllm::array({"requestText", "route"})}, {"writes", axllm::array({"responderResult", "responseText"})}}))
    .returns(axllm::object({{"route", "route"}, {"responseText", "responseText"}}));

Read the full file on GitHub · 107 lines

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.

  1. today Changed dd55674f0262
  2. 2d ago First seen · 107 lines · 37 tokens per session scan A f699dcd51415

Subscribe to this mod's changes

ax-cpp-flow is a skill published in the GitHub repository ax-llm/ax (2,890 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 1,208 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.