Agent
Part of clean-room
Plans clean implementation from approved clean behavioral specs and the clean destination foundation without reading contaminated source or chat history.
A skill for claude/codex to take source code and implement a clean-room of agents to generate specs
Agent
Part of clean-room
Plans clean implementation from approved clean behavioral specs and the clean destination foundation without reading contaminated source or chat history.
Agent
Part of clean-room
Shell-capable Agent 3 profile for isolated clean implementation verification homes.
Agent
Part of clean-room
Performs final source-denied clean code polish, repository hygiene, verification review, and constrained implementation-root commit after Agent 3 completes.
Agent
Part of clean-room
Implements the clean implementation plan, verifies the clean destination code, records implementation status, and emits one terminal report for Agent 0.
Agent
Part of clean-room
Reviews Agent 1 draft specs from a fresh source-denied contaminated context, removes identifying material, and approves only scrubbed artifacts for clean handoff.
Agent
Part of clean-room
Consumes contaminated source indexes, decomposes authorized source scope, tracks clean-room coverage, and verifies clean specs against source without sending source expression across the wall.
Agent
Part of clean-room
Reads authorized source in a contaminated workspace and produces neutral draft task slices plus behavioral specs with evidence references, not replacement code.
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: