dag-fleet
Fleet
A skill for running parallel claude -p, codex exec, or pi -p workers in tmux with budgets and DAG dependencies. Supports Claude, Codex, and Pi providers — set per-fleet or per-worker. Operator owns all kill / steer / re-direction — there is no auto-restart, no auto-verify, no babysitter loop.
Prerequisites
- bash >= 4.0 — macOS ships bash 3.2 (from 2007). Install modern bash:
brew install bash - flock — Linux built-in. macOS:
brew install flock - tmux —
brew install tmuxorapt install tmux - jq —
brew install jqorapt install jq
macOS quick-start
brew install bash tmux jq flock
# Then invoke launch.sh explicitly with bash 4+:
/opt/homebrew/bin/bash /path/to/dag-fleet/scripts/launch.sh <fleet-root>
More from quickcall-dev/skills
doc
Create and manage structured documentation — experiments, plans, findings, checkpoints, research, learnings. Config-driven, parallel-safe.
30worktree-fleet
Independence-validated parallel fleet that runs each worker (claude -p, codex exec, or pi -p) in its own git worktree. Use when tasks touch non-overlapping files and you need merge-safe isolation (each worker on its own branch). For DAG-ordered one-shot workers with budgets, use dag-fleet. For headless iteration with a reviewer loop, use iterative-fleet.
30fleet-plan
Analyze a task, pick the right fleet type, and generate a ready-to-launch fleet (fleet.json + prompt.md files). Discovers available fleet skills dynamically. Use when the user wants to run work in parallel, asks to "plan a fleet", or says "fleet-plan".
29iterative-fleet
Reviewer-gated iterative fleet for headless `claude -p`, `codex exec`, or `pi -p` workers that run in cycles until a designated reviewer approves the output. Use when the work needs multiple rounds of iteration with a quality gate — a reviewer worker reads all worker logs, writes a verdict (lgtm | iterate | escalate), and the orchestrator decides whether to continue, pause, or stop. NEVER kills or restarts workers automatically; the operator owns all kill/pause decisions.
29autoresearch-fleet
Karpathy-inspired autonomous research loop. Agent edits one file, evals, keeps or discards, repeats. Plateau-triggered web search breaks through ceilings. Git as state machine. Runs until stopped or budget exhausted. Supports claude, codex, and pi providers.
29