Auto swarm
Distributed agent swarm orchestrator — spawns parallel subagent clusters for any task with configurable depth, swarm size, and convergence criteriaFrom its SKILL.md
npx -y skills add ShaheerKhawaja/ProductionOS --skill auto-swarmAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.4 KB, as published. Nobody here has run it
auto-swarm
Overview
Use this as the Codex-first swarm workflow. In Codex it should preserve the decomposition and convergence ideas from ProductionOS while defaulting to practical execution: decompose clearly, parallelize only when the user wants it, and keep a visible coverage map.
Source references:
.claude/commands/auto-swarm.mdagents/swarm-orchestrator.mdagents/worktree-orchestrator.md
Inputs
- required
task - optional
mode - optional
depth - optional
swarm_size - optional
iterations
Codex Workflow
- Analyze the task and choose the mode.
- Decompose the work into independent slices.
- Build a coverage map before execution starts.
- Execute serially by default in Codex unless the user explicitly wants sub-agents or parallel work.
- After each wave, synthesize:
- what was covered
- what remains
- whether another wave is justified
- Stop when coverage is sufficient or returns diminish.
Expected Output
- task decomposition
- coverage map
- per-wave synthesis
- final compiled result
Guardrails
- do not parallelize by reflex
- keep subtask boundaries explicit
- stop when additional waves are not producing meaningful coverage gains