blakecyze/swarm

swarm-execute

Use when the user wants to run plans written by /swarm-improve, execute a plans/ backlog, or dispatch mechanical work to a cheaper model. The pair of /swarm-improve: it planned, this executes.

swarm-improve

Use when the user wants to audit a whole codebase for latent work (bugs, performance, tech debt, missing tests, what to build next) and capture it as self-contained plans a cheaper agent can execute later. Spends the capable model on judgement, not execution.…

swarm-principles

Use when orchestrating subagents, fanning work out in parallel, or running any /swarm-* skill. Sets standing rules for when to fan out, when not to, cost ceilings, and who judges. Auto-loads; not directly invoked by the user.

swarm-bulldoze

Use when the user wants to try several independent approaches to the same problem and keep the best one. Best-of-N generation. Expensive by design; respects the cost ceiling.

swarm-explore

Use when the user wants to map a large codebase, gather context from many files at once, or investigate a problem space in parallel. Read-only fan-out. Never writes.

swarm-plan

Use when the user wants to break a large task into parallel workstreams, plan a multi-agent job, or decide what can run concurrently. Produces an orchestration plan, does not execute it.

swarm-refine

Use when the user has one artefact (code, doc, design, plan) and wants it hardened by attacking it from several angles at once. Parallel critics, then merge. Not to be confused with bulldoze, which generates many solutions.