swarm-coordinator
Swarm Coordinator
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 It For
- broad codebase exploration
- cross-file bug hunts
- parallel review or research passes
- tasks that benefit from explicit synthesis before implementation
Avoid It For
- trivial edits
- urgent blocking steps that are faster to do locally
- delegation with no ownership boundaries
Quick Start
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.
Core Rule
The coordinator should own planning, routing, and synthesis. Workers should own bounded execution.
Supporting Files
- Prompt template: references/prompt-template.md
- Source notes: references/source-notes.md
- Helper script:
python3 {baseDir}/scripts/task_board.py ...
More from learnprompt/cc-harness-skills
dream-memory
Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.
26memory-extractor
Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.
23verification-gate
Run a read-only verification pass after implementation to check whether completion claims are real, validation actually ran, and obvious edge cases or regressions were missed.
23structured-context-compressor
Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step.
19kairos-lite
Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon.
13