init

A project setup command for Kubb, a tool that generates code from an OpenAPI description of an API.

In plain words
What is it for?
It helps start Kubb projects with options such as TypeScript, API clients, query hooks, validation schemas, test data, or mock servers.
Why use it?
It removes the manual work of creating Kubb's configuration and installing the packages needed for selected outputs.

Command

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 commands/kubb-labs/kubb/init
Clone the repo
git clone --depth 1 https://github.com/kubb-labs/kubb
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 352 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 $0.00018 $0.00352
Opus 5 $0.00009 $0.00176
Sonnet 5 $0.00004 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 2d ago against content hash ba821df468f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 2d 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.

tools/claude/commands/init.md · 26 lines

What it actually says

Scaffold Kubb in the current project by running the kubb init CLI in the terminal. The arguments map to its flags: an OpenAPI spec (--input), an output directory (--output), and a comma-separated plugin list (--plugins). Read the config skill before choosing plugins.

Parsed from $ARGUMENTS (ask only for what is missing):

  1. Choose plugins. Map the requested outputs to @kubb/plugin-* packages with the config skill. Valid values: plugin-ts, plugin-axios, plugin-fetch, plugin-react-query, plugin-vue-query, plugin-zod, plugin-faker, plugin-msw, plugin-cypress, plugin-mcp, plugin-redoc. Default to plugin-ts when the user is unsure.

  2. Run init with --yes and the chosen values so it never prompts:

    npx kubb init --yes --input <input> --output <output> --plugins <comma,separated,list>
    

    This writes kubb.config.ts and installs kubb plus the selected packages (--yes also creates a package.json if the project has none). For a default setup, npx kubb init --yes works without flags. If a config already exists, edit it by hand rather than rerunning init.

  3. Suggest running /kubb:generate next.

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. 2d ago First seen · 26 lines · 18 tokens per session scan A ba821df468f0

Subscribe to this mod's changes

init is a command published in the GitHub repository kubb-labs/kubb (1,788 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 352 once invoked, about $0.0001 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.