Inspectable engineering workflows for OpenAI Codex.
This repository also configures its own agents. See what rootloom tells them →
Skill Codex
Initialize, retrieve, and explicitly update the separate Rootloom Memory plugin's repository-owned architecture, risk, decision, and failure lessons. Use only when explicitly requested. Memory is experimental, advisory, and outside Rootloom Core.
Skill Codex
Review without editing; report evidence-backed defects by severity and disclose material verification gaps.
Skill Codex
Complete scoped code changes with proportional verification; load governed, Evidence, and external-action procedures only when needed.
Skill Claude CodeCodex
Create, refine, or validate repository guidance on explicit user request; preserve real-path scope, managed ownership, and unrelated content.
Skill Codex
Plan, install, inspect, update, or roll back Rootloom Personal Core in a user's Codex home. Supports Skills-only, guidance, and the recommended personal preset. Use when the user explicitly asks for a Rootloom setup plan, installation, configuration, bootstrap, repair, audit, status, update, reduction, rollback, or…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: