Skill Claude CodeCodex
Ro's coding loop. Use on $awesomeharness or any build, refactor, audit.
A drop-in harness that makes Claude Code cheaper, sharper, and forgetful-proof: persistent memory, token savings, anti-drift, a code-map RAG, disciplined cheap-model coding.
Skill Claude CodeCodex
Ro's coding loop. Use on $awesomeharness or any build, refactor, audit.
Skill Claude CodeCodex
Decompose a code change into small verifiable units before writing it, then build and self-audit each. Use for any change beyond one line.
Skill Claude CodeCodex
Prove what the repo already provides before adding code: evidence-backed REUSE/ADAPT/REJECT + STOP/PLAN/BUILD gate, before code-decompose.
Skill Claude CodeCodex
Every-turn close: commit, record the lesson, update STATE resume point + .now.md, push, emit CONTINUE. Run each substantive turn and before compaction.
Skill Claude CodeCodex
Proposal-only: AUDIT a repo harness for drift, or SCOUT transcripts and outside ideas worth stealing. Use on "audit/scout the harness". Never edits.
Skill Claude Code
Find credible creators and mine YouTube/Instagram content (transcripts, reels, comments) via the ytintel CLI. Use for niche or competitor research.
Skill Claude CodeCodex
Use for awesome-harness Codex sessions, or whenever the user asks for Caveman discipline, terse progress, delegated code changes, or evidence-led implementation.
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: