{"id":"3464040f-d17f-469e-94b0-ac928ca640f5","slug":"agent-ready-repo","kind":"skill","name":"agent-ready-repo","summary":"The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release) over a catalogue of curated packs: skills, subagents, and","owner":"eugenelim","repoUrl":"https://github.com/eugenelim/agent-ready-repo","license":"Apache-2.0","licenseTier":"permissive","trust":"community","stars":24,"match":null,"fewStars":false,"format":"skill","createdAt":null,"addedAt":"2026-10-14T06:06:28.062Z","logoUrl":"https://avatars.githubusercontent.com/u/473231?u=cb7ca82fae4d5bce28e1b0501c9b284b8961e342&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["developer-tools","communication","memory-knowledge"],"tags":["agentic-ai","agentic-coding","ai-agents","ai-code-review","ai-workflows","claude-code","code-review","coding-agents"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-14T06:46:06.753Z","sample":false,"url":"https://conduits.dev/tools/agent-ready-repo","language":"Python","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# agent-ready-repo\n\n**The supervised agentic build loop—and the catalogue of workflows around it.**\n\nDecide what to build, design the product and system, implement and review software, plan infrastructure, validate releases, document what ships, and govern the catalogue your organization owns.\n\n```text\nReversible agent work → mechanical checks → independent review → human decision\n```\n\n[![PyPI](https://img.shields.io/pypi/v/agentbundle)](https://pypi.org/project/agentbundle/) [![License](https://img.shields.io/badge/license-MIT%2FApache--2.0-blue)](#license) [![OWASP Agentic Skills Top 10](https://img.shields.io/badge/OWASP-Agentic%20Skills%20Top%2010%20v1.0-blue)](https://owasp.org/www-project-agentic-skills-top-10/)\n\n[Build with `core`](#build-with-core) · [Explore use cases](https://eugenelim.github.io/agent-ready-repo/#use-cases) · [Get started](https://eugenelim.github.io/agent-ready-repo/docs/getting-started/) · [Browse the catalogue](https://eugenelim.github.io/agent-ready-repo/catalogue/) · [Contribute](CONTRIBUTING.md)\n\n## Choose a use case\n\n- **Product managers and strategists:** move from strategy and evidence to a bounded decision brief with `product-strategy`, `desk-research`, and `product-engineering`.\n- **Platform, infrastructure, and SRE teams:** design the boundary, author contracts, produce reviewable Terraform, and validate the deployed result with `architect`, `contracts`, `iac-terraform`, and `release-engineering`.\n- **Software teams:** take a brief or spec through implementation, hard gates, independent review, and a human merge decision with `core`.\n- **Design, research, documentation, and enablement teams:** [explore the use cases](https://eugenelim.github.io/agent-ready-repo/#use-cases) that map your work to the relevant packs.\n\nPacks are composable units, not departments. Install only what you need, or use a profile when a curated starting set fits. The [complete catalogue](https://eugenelim.github.io/agent-ready-repo/catalogue/) remains the source for current pack inventory and install commands.\n\n## Build with `core`\n\n`core` is the catalogue's flagship and its strongest reason to start. It is a complete build system for coding agents: spec and plan before code, mechanical gates before claims, a cold independent review before handoff, and a human decision before merge.\n\n```bash\npython -m pip install agentbundle\nagentbundle install --pack core\n```\n\nThen ask your coding agent:\n\n```text\nImplement <small, testable feature> with the work-loop.\n```\n\nThe loop keeps fixing until the checks and review are clean. If it repeats the same failure, crosses a boundary, or reaches an irreversible decision, it stops and surfaces the choice instead of self-certifying. [See how `core` compares with prompt-and-approve coding, Spec Kit, and Kiro](guides/core/explanation/core-pack.md).\n\nUsing Claude? You can also [add this catalogue as a plugin marketplace](https://eugenelim.github.io/agent-ready-repo/docs/getting-started/install/#route-2-claude-plugins) and install any user-scope pack directly. Repo-scoped packs such as `core` install with `agentbundle` so the whole team shares the same loop.\n\n## Own the system\n\n`agentbundle` projects portable skills, subagents, hooks, commands, and seeds into the layout each supported agent expects. Installed files remain readable and editable; upgrades preserve local changes as explicit companions instead of silently clobbering them.\n\nCreate an organization-owned catalogue without forking this repository:\n\n```bash\nagentbundle catalogue init my-catalogue --name my-catalogue\nagentbundle catalogue verify --root my-catalogue\n```\n\n[Understand packs, profiles, adapters, composition, and self-hosting](guides/_shared/explanation/pack-catalogue.md) · [Create a catalogue](guides/_shared/how-to/create-a-catalogue.md) · [Read the authoring standards](guides/_shared/reference/catalogue-authoring-standards.md)\n\n## Go deeper\n\n- **Use the catalogue:** [technical docs](https://eugenelim.github.io/agent-ready-repo/docs/) · [install routes](guides/_shared/explanation/install-routes.md) · [adapter support](guides/_shared/reference/adapter-support.md) · [`agentbundle` reference](guides/_shared/reference/agentbundle.md)\n- **Understand the operating model:** [how work flows from idea to production](guides/_shared/explanation/the-operating-model.md) · [file safety](guides/_shared/explanation/file-safety-contract.md)\n- **Inspect the implementation:** [architecture](docs/architecture/) · [machine contracts](contracts/) · [security model](docs/architecture/security.md)\n- **Contribute:** [contribution lanes and gates](CONTRIBUTING.md) · [pack authoring](packs/) · [repository conventions](AGENTS.md)\n\n## License\n\nLicensed under either [Apache 2.0](LICENSE-APACHE) or [MIT](LICENSE-MIT) at your option. Contributions are dual-licensed under the same terms unless you state otherwise.\n"}