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 agentmods add instructions/kubb-labs/kubb/agents-mdgit clone --depth 1 https://github.com/kubb-labs/kubbWrote 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/instructions/kubb-labs/kubb/agents-md)<a href="https://agentmods.dev/instructions/kubb-labs/kubb/agents-md"><img src="https://agentmods.dev/badge/instructions/kubb-labs/kubb/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01025 | $0.01025 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
kubb AGENTS.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Kubb is a code-generation toolkit for generating TypeScript, React-Query, Zod, Faker.js, MSW and more from OpenAPI specifications. It uses a plugin-based architecture with an Abstract Syntax Tree (AST) layer.
High-level architecture
Kubb is built from:
- Core engine (
@kubb/core) runs the plugin system and orchestrates code generation - Authoring kit (
@kubb/kit, reached through thekubb/kitsubpath) bundles the helpers for building plugins, generators, adapters, resolvers, and renderers - Adapters (
@kubb/adapter-oas) transform OpenAPI specs into an AST - Renderers and utilities turn the AST into code
- The CLI is the entry point for code generation
- MCP server adds Model Context Protocol integration for AI assistants
Project structure and commands
The full folder structure, repository setup, and commands live in CONTRIBUTING.md.
Repository setup
| Aspect | Choice |
|---|---|
| Monorepo | pnpm workspaces + Turborepo |
| Module system | ESM-only (type: "module") |
| Node version | 22 |
| Package manager | pnpm 11+ |
| Linter | oxlint |
| Formatter | oxfmt |
| Bundler | tsdown |
| Tests | Vitest |
| Versioning | Changesets |
| CI/CD | GitHub Actions |
Plugin ecosystem
Plugins are maintained in a separate monorepo at kubb-labs/plugins. Extension metadata and the docs pages live in the platform repo (kubb-labs/platform, apps/kubb.dev/extensions/ and apps/kubb.dev/plugins/), published on kubb.dev. When an extension's options change here, update its kubb.dev docs page there.
Token optimized CLI (rtk)
rtk is a CLI proxy that filters and compresses command output to cut token usage. Prefix shell
commands with it so their output stays small:
rtk git status
rtk git log -10
rtk pnpm test
Run these meta commands directly:
rtk gain # Token savings dashboard
rtk gain --history # Per-command savings history
rtk discover # Find missed rtk opportunities
rtk proxy <cmd> # Run raw without filtering but still track usage
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.
- 4d ago First seen · 80 lines · 1,025 tokens per session scan A 15802634657e
kubb AGENTS.md is an instructions file published in the GitHub repository kubb-labs/kubb (1,791 stars, last pushed today), licensed MIT. It adds 1,025 tokens to every session, about $0.0051 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.
Other instructions, from other repositories
react-seed AGENTS.md
Instructions for guokaigdg/react-seed, covering agents.md, 目录, 1. 项目概览, 2. 技术栈 and 3. 目录结构.
lathe CLAUDE.md
Claude Code instructions for lathe-cli/lathe, covering claude.md, project intent, product positioning, source of truth and project structure.
prisma-class-generator CLAUDE.md
Claude Code instructions for kimjbstar/prisma-class-generator, covering claude.md, what this is, architecture, commands and testing approach.
lathe AGENTS.md
AGENTS.md instructions for lathe-cli/lathe, a project described as: Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.