A catalogue of agentbundle primitives for building robust, review-driven AI coding workflows.
agent-ready-repo is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo clone eugenelim/agent-ready-repoOpen or clone the template repository.
Move the relevant AGENTS.md content into your project root.
Update project-specific commands, environment rules, and sensitive areas.
This repository provides a collection of reusable building blocks (called packs) that make AI coding agents more reliable. It includes a plan-execute-verify-review loop that forces agents to test and review their code before shipping, plus specialized reviewer subagents for adversarial, security, and quality checks. You can install packs for governance, documentation, monorepo management, and more.
agent-ready-repo is a catalogue of agentbundle primitives — skills, reviewer subagents, hooks, and governance scaffolding — that can be installed à la carte into any repository. Each pack delivers a coherent slice of functionality: a workflow you can run, a reviewer that pulls its weight, or the document shape that makes downstream agents work well. Skills follow the agentskills.io specification, making them self-contained and cleanly installable. The core pack introduces a plan → execute → verify → review loop that runs lint, typecheck, and tests as hard gates, then dispatches specialist reviewer subagents in a fresh session to read the diff adversarially before anything ships. Additional packs add governance ceremony (RFCs, ADRs), user-docs structure (Diátaxis), monorepo scaffolding, contract authoring, file conversion, Atlassian workflows, Figma file access, and solution architecture skills. The repository is stack-agnostic and scales from solo developers to teams of fifty.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 52 days ago.
7 GitHub stars indicate community interest.
1 open issues signal maintenance load.
Apache-2.0 license detected.
Set up a robust AI coding workflow that automatically reviews and tests generated code before merging.
Add governance documentation (RFCs, ADRs) to a project with minimal effort using pre-built skills.
Create a structured user guide following the Diátaxis framework for better documentation.
Automate file format conversions (PDF to Markdown, DOCX to Markdown, etc.) with agent skills.
Integrate Atlassian tools (Jira, Confluence) into your AI agent's workflow for project management.
The core loop runs code (lint, typecheck, tests) which could execute malicious code if the repository is compromised. Ensure you trust the source.
Some packs (e.g., Figma, Atlassian) require API tokens or credentials; handle them securely and avoid committing them to the repository.
The adversarial reviewer subagent may generate false positives or negatives; human oversight is still recommended for critical decisions.
7
Stars
3
Forks
1
Issues
Apache-2.0
License
A drop-in AGENTS.md file that makes coding agents behave like senior engineers, eliminating sycophancy and forcing verification.
Convert and sync AI coding-agent rule files between formats with zero dependencies.
Generate AGENTS.md from your codebase in one command. Free, instant, no API key.
A catalogue of agentbundle primitives for building robust, review-driven AI coding workflows.
AI agent developers who want to build reliable, self-reviewing coding workflows., Tech leads and architects setting up governance and documentation standards for their teams., Solo developers who want to leverage AI agents for code generation with built-in quality checks.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
The core loop runs code (lint, typecheck, tests) which could execute malicious code if the repository is compromised. Ensure you trust the source. Some packs (e.g., Figma, Atlassian) require API tokens or credentials; handle them securely and avoid committing them to the repository.
Similar or complementary options to evaluate include agents-md, agentsync, agentseed.
Jun 7, 2026
3 security/trust notes recorded.
Setup difficulty is 3/5.