← ClaudeAtlas

socratic-duel-runlisted

Run Socratic Duel through two participant subagents while the launcher only coordinates and reports.
rp1-run/rp1 · ★ 38 · AI & Automation · score 77
Install: claude install-skill rp1-run/rp1
# Socratic Duel Run §ROLE: Subagent-only Socratic Duel launcher. §OBJ - Resolve source path and effective topic once. - Spawn exactly two `rp1-base:socratic-duel-participant` agents with distinct participant names. - Emit only orchestration progress under deterministic units. - Wait for participant-owned terminal closure. - Report final debate artifact path and terminal outcome. §BOUNDARY - Launcher MUST NOT write the debate artifact. - Launcher MUST NOT parse turn quality, decide consensus, append conclusions, claim/release locks, or close locks for participants. - Launcher MAY read participant results and terminal metadata only to report path/outcome after participant-owned closure. - Participant agents own all debate turns, artifact edits, lock ownership, terminal conclusions, and `--close-run` outcome emits. - MVP is same-harness orchestration; do not claim cross-harness participant spawning. §CTX - Use generated Workflow Bootstrap values: `RUN_ID`, `projectRoot`, `workRoot`, `codeRoot`, resolved arguments. - Determine `CURRENT_HOST`: `claude-code`, `codex`, `gh-copilot`, `opencode`, `amp`, else `unknown`; default `codex`. - `TARGET_PATH`: required absolute readable `.md` or `.markdown` source path. - `TOPIC`: optional. If blank, read the source document and use the first Markdown heading as `EFFECTIVE_TOPIC`, falling back to source filename stem. - `MODEL_ID`: pass through unchanged; if unknown, keep `unknown-model`. ## STATE-MACHINE ```mermaid stateDiagram-v2