From cc-harness
Splits large tasks into research, synthesis, implementation, and verification phases, assigning ownership to bounded workers while the coordinator focuses on integration.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cc-harness:swarm-coordinatorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when a task is large enough that one coordinator and several bounded workers are more reliable than one monolithic agent loop.
Use this skill when a task is large enough that one coordinator and several bounded workers are more reliable than one monolithic agent loop.
Generate a task-board skeleton:
python3 {baseDir}/scripts/task_board.py --goal "Investigate flaky CI failure" --worker research --worker implementation --worker verification
Then use the coordinator prompt in references/prompt-template.md.
The coordinator should own planning, routing, and synthesis. Workers should own bounded execution.
python3 {baseDir}/scripts/task_board.py ...npx claudepluginhub learnprompt/cc-harness-skills --plugin cc-harnessOrchestrates multi-agent work at scale: research swarms, parallel feature builds, wave dispatch, and build-review-fix pipelines. Activates on mentions of swarm, parallel agents, multi-agent, or fan-out.
Patterns and principles for orchestrating parallel subagent execution: work decomposition (fan-out/fan-in, map-reduce), isolation, result synthesis, and failure handling. Use when a task splits into independent subtasks.
Coordinates multi-agent work across plan/implement/test/review phases, fanning out 3+ independent workstreams in parallel. Includes a GO/NO-GO gate to assess whether parallelization is appropriate.