Monitor a swarm, a group of agents, and receive notifications when its status or agent count changes. A watcher script checks status periodically and streams changes through Monitor; separate tools provide one-time status and health checks.
Stream live swarm events using the Monitor tool for real-time observability
Run score Not tested
See how to installMonitor the status of a swarm, a group of agents, and receive notifications through Monitor when its status or agent count changes. The swarm-watch.mjs script periodically runs swarm status --format json. It outputs the initial state, changes, and errors as NDJSON: JSON records written one per line. Each output line triggers a notification.
Use this skill while multiple agents are running and you want to keep track of changes in their status or participation count. You can specify the monitoring interval. If you only need a single check, the skill also directs you to MCP tools for a one-time status or health check, without continuing to monitor the swarm.
Continuous monitoring uses Monitor and a Node.js environment to run the bundled scripts/swarm-watch.mjs. The ruflo CLI has no swarm watch command; the script checks periodically. The minimum interval is two seconds. Monitoring covers status and agent-count changes, without displaying individual task or memory events.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 21, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Use the Monitor tool to stream swarm events in real time instead of polling:
Run via Monitor: node "${CLAUDE_PLUGIN_ROOT}/scripts/swarm-watch.mjs" (add --interval 5 for faster updates; minimum 2 s)
There is no swarm watch in the ruflo CLI, so this script polls swarm status --format json and prints one NDJSON line when it changes (swarm.snapshot, swarm.changed, swarm.error). It shows status and agent-count changes, not individual task or memory events. Each stdout line triggers a notification.
For one-shot status, use MCP: mcp__plugin_ruflo-core_ruflo__swarm_status or mcp__plugin_ruflo-core_ruflo__swarm_health.
Prefer Monitor over polling swarm status in a loop. See ADR-091 for rationale.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.
Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.
Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.
Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.
Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.