Clean Room Resume

Resume an existing clean-room run from durable artifacts. Never use prior chat history as the source of truth.

Use the canonical clean-room skill workflow and references in this plugin. Read skills/clean-room/references/CONTROLLER-LOOP.md when the manifest records loop_context or unattended mode. Preserve the same clean-room boundary, role separation, artifact schemas, leakage rules, implementation-root rules, and hook expectations.

If task-manifest.json records controller_policy.mode: "unattended" in Claude Code, prefer launching clean-room-skill run --task-manifest <path> --agent-runtime claude only when loop_context exists and names approved pending or gap units. For ccsilo/OpenRouter sessions, use clean-room-skill run --task-manifest <path> --ccsilo [variant] instead of manual --agent-runtime claude, --agent-config-dir, or CLEAN_ROOM_CLAUDE_EXECUTABLE wiring. Never write ANTHROPIC_AUTH_TOKEN or API keys into ccsilo or Claude settings files. If an unattended manifest lacks loop_context, treat it as incomplete outer-loop state: finish decomposition or selected-slice approval first, or stop with the missing outer-loop fields instead of launching the runner. If clean-room-skill is not on PATH, immediately use npx clean-room-skill@latest run --task-manifest <path> --agent-runtime claude instead of searching for the installed package. Do not search plugin cache paths for schema files, and do not pass --schema-dir /dev/null. The runner uses bundled schemas by default; pass --schema-dir only when the user provides a real schema directory. The main conversation must not perform Agent 1, Agent 2, Agent 3, or Agent 4 work once runner-ready unattended state exists. Do not edit task-manifest.json unit statuses in the main conversation; unit completion must come from runner-managed role artifacts and contaminated-side coverage verification. Do not ask to continue while unattended policy, iteration budget, and approved pending or gap units still permit progress. If the runner or Claude role-agent dispatch is unavailable, stop with BLOCKERS: Claude role-agent dispatch unavailable rather than silently continuing in the main chat.

Discovery Before Load

Before saying no clean-room run exists, perform the canonical clean-room "Run State Discovery Before Wizard" rules. Resolve explicit artifact paths first, then inspect the current working directory and ancestors for .clean-room/local-state.json, then configured clean-room roots, then bounded ~/Documents/CleanRoom/task-* and ~/Documents/CleanRoom/*/tasks/task-* candidates. If the repo-local pointer identifies an external project, scan that project's tasks/ directory before any global fallback.

Treat target-repository .clean-room/tasks/ as noncanonical unless the user explicitly provided that path or .clean-room/local-state.json identifies it as the external task root. Active artifacts belong under the external task root, not under the target repo stub.

If a candidate task-manifest.json is present but invalid, legacy-shaped, or schema-incompatible, report the exact path and validation errors. Do not say no artifacts exist. If no runnable task remains but a valid project is found, report the project root and make the next safe action "create a new task in this project" when the user wants to add more work.

Load Order

Load these artifacts from the paths recorded in task-manifest.json and the configured root environment. Treat missing optional artifacts as blockers only when the current gate requires them. A task may live at <base>/<project>/tasks/<task-id>/ with a shared project-level implementation root; trust the absolute paths recorded in task-manifest.json artifact_paths and never re-derive the layout from folder positions.