Agent harness for complex codebases with project memory, planning, execution, and verified completion inside Codex.
LazyCodex is easy to set up with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
npx skills add code-yeongyu/lazycodexRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
LazyCodex is a tool that installs OmO's agent harness into Codex. It adds project memory, planning, and verified task completion. You can use commands like $ulw-loop to run tasks until they are verified done.
LazyCodex is the Codex distribution of OmO's agent harness. It provides project memory via /init-deep, planning via $ulw-plan, execution via $start-work, and verified completion via $ulw-loop. It also includes skills, hooks, model routing, and diagnostics. Install with one command: npx lazycodex-ai install. It is designed for complex codebases where agents need context and orchestration.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 2 days ago.
594 GitHub stars indicate community interest.
3 open issues signal maintenance load.
MIT license detected.
Install OmO agent harness into Codex with one command
Use $ulw-loop to iteratively refine a task until verified complete
Plan complex features with $ulw-plan before writing code
Execute multi-step plans with $start-work and track progress
Generate hierarchical project memory with /init-deep for large repos
Executes code on your machine; review plans before running $start-work
Uses third-party AI models; data sent to API providers
May modify files; ensure backups or version control
594
Stars
28
Forks
3
Issues
MIT
License
Vercel's official collection of packaged instructions and scripts that extend AI coding agent capabilities.
Official Supabase agent skills to help AI agents work accurately with Supabase products.
A best-practices skill for Terraform and OpenTofu AI agents, enabling testing, module structuring, CI/CD, and production infrastructure code.
3 security/trust notes recorded.
Setup difficulty is 2/5.