← ClaudeAtlas

swarmlisted

Ad-hoc parallel task executor. Pass natural language tasks directly (or --tasks-file); independent tasks use concurrent host-native volume/execution/judgment roles and dependent tasks run serially. No spec directory required; use feature-implement for full-feature work.
austinmao/feature-fix-swarm · ★ 3 · AI & Automation · score 75
Install: claude install-skill austinmao/feature-fix-swarm
# /swarm — Ad-hoc parallel task executor ## Host dispatch contract - Codex: `$skill`, Codex collaboration roles, and GPT-5.6 tiers. - Claude: `/skill`, Agent/Skill tools, and Claude aliases. - A bare `/skill` in this shared source denotes the Claude form; Codex dispatches the same named skill as `$skill`. ## Init gate Before any other step, run the advisory init guard and relay its output verbatim: ```bash bash "$(git rev-parse --show-toplevel)/scripts/gsd/init-guard.sh" || true ``` If it printed `INIT-GUARD:` warnings, offer `/ffs-init` before proceeding in interactive sessions (declining proceeds anyway); headless, spawned, and autonomous runs relay the warnings once and continue. Advisory only — never a block, never an exit-code change. At entry, make one opportunistic, fail-soft `bash scripts/gsd/reconcile.sh` pass; never block on its result. One command. Pass task descriptions, get model classification, parallel execution, and a structured result. No spec pipeline, no `.planning/` prerequisite. ## When to invoke - "swarm these tasks", "run these in parallel", "do all of these" - Multi-task batch execution without the full spec pipeline - Quick automation: lint + test + docs + cleanup at once For anything that IS a feature (multi-phase, TDD, ship tail): use `/feature-implement` — the gsd loop owns that shape. ## Invocation ``` /swarm "task1" "task2" "task3" # classify + execute /swarm --tasks-file PATH # md checklist or one-per-line /swarm ... -