multi-agent-repolisted

## Live context !`git rev-parse --show-toplevel 2>/dev/null && echo "cwd repo: $(basename "$(git rev-parse --show-toplevel)")" || echo "not a git repo"` !`gh auth status 2>&1 | head -1 || echo "gh: not available"` # multi-agent-repo Audit, plan, and implement canonical multi-agent repository setup: **one `AGENTS.md` source of truth**, thin adapters per tool, portable skills, and CI-enforced validation. ## Why this skill exists Teams running Claude Code, Cursor, and Codex in parallel often maintain three diverging instruction files. Policies drift, context bloats past Codex's 32 KiB limit, and agents ignore duplicated rules. This skill runs **review → plan → dev** so you know what's missing, what order to fix it, and can land the full setup via PR. For quick file generation without a prior audit, use **dev** mode directly. ## Supporting files | Path | When to read | |------|----------------| | `references/mode-contracts.md` | Parse arguments; know stop conditions per mode | | `references/target-layouts.md` | Classify app vs claude-plugin vs hybrid | | `references/audit-rubric.md` | Full checklist for review mode | | `references/gap-scoring.md` | Auto vs manual rubric mapping | | `references/platform-setup.md` | Fetch docs + generate AGENTS.md and thin adapters (phases 0–1) | | `references/platform-specs.md` | Schema fallback when live doc fetch fails | | `scripts/parse-mode-args.sh` | Deterministic mode/target parsing | | `scripts/inventory-agent-setup.sh` | Re-export →