From swarm
Provides rules for Claude plugin agents on swarm tool usage, model behaviors, file reservations, task coordination, and TDD. Useful in multi-agent Claude Code workflows.
How this skill is triggered — by the user, by Claude, or both
Slash command
/swarm:always-on-guidanceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- Follow instruction priority: system → developer → user → AGENTS.
hive_*, swarm_*, swarmmail_*, hivemind_*); avoid deprecated bd/cass references.ttl_seconds; release reservations on done; finish swarm work with swarm_complete.TaskCreate/TaskUpdate for visible progress in Claude Code UI alongside hive_* for git-backed persistence.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS is enabled, prefer TeammateTool for real-time coordination and swarmmail_* for persistence.swarmmail_release_all is coordinator-only for stale/orphaned reservations.Use model aliases (inherit, opus, sonnet, haiku) instead of version numbers.
EnterPlanMode for test-driven planning before implementation.npx claudepluginhub joelhooks/swarm-tools --plugin swarmCrafts effective prompts, CLAUDE.md instructions, rules, agent system prompts, and skill bodies for reliable Claude Code behavior.
Working with AI coding agents — User Sovereignty, agreement-as-signal, Karpathy/Willison framing, per-model overlays, and the rule to measure your prompt nudges.
Orchestrates AI coding workflows with self-correction loops, pre-flight discipline rules, and cross-agent support for Claude Code and other agents.