Back to directory

agent-ready-repo

A package manager and catalogue of installable skills, subagents and hooks that structure how an AI coding agent moves from an idea through implementation, review and release.

agent-ready-repo

agent-ready-repo is a catalogue of composable packs, covering product strategy, research, software architecture, infrastructure, release engineering and documentation, that install into an AI coding agent in one line. Its flagship pack, core, is a build system for coding agents that puts a spec and plan before code, runs mechanical checks before any claim of completion, requires an independent review before handoff, and leaves the merge decision to a person.

Packs are installed selectively with the project's own package manager, agentbundle, or through a Claude Code plugin marketplace for user-scoped packs, and installed files remain plain, readable and editable rather than hidden behind the tool. It supports Claude Code, Codex, Cursor, GitHub Copilot, Gemini and Kiro.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.