Monitor Stream
- 650 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
monitor-stream is a Claude Code skill that streams live swarm agent events over NDJSON so developers can observe multi-agent runs without writing custom polling loops.
About
monitor-stream is an observability skill in ruvnet/ruflo for real-time Claude Flow swarm monitoring. Instead of polling `swarm status` in a loop, it runs `npx @claude-flow/cli@latest swarm watch --stream` through the Monitor tool, emitting NDJSON lines for agent spawns, task completions, memory writes, and health checks where each stdout line triggers a notification. For one-shot snapshots it falls back to `mcp__claude-flow__swarm_status` or `mcp__claude-flow__swarm_health`. Developers reach for monitor-stream when debugging long-running agent workflows, watching swarm health during orchestration, or acting on live infrastructure and API event streams. ADR-091 documents the rationale for streaming over polling in agent operations.
- Real-time stream monitoring with configurable filters and handlers
- Integrates directly with agent workflows for live observation
- Lightweight CLI and programmatic API for embedding in any stack
- Supports multiple input sources including logs, events, and agent outputs
- Built-in alerting and transformation capabilities
Monitor Stream by the numbers
- 650 all-time installs (skills.sh)
- +10 installs in the week ending Jul 26, 2026 (Skillselion tracking)
- Ranked #367 of 2,715 Automation & Workflows skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill monitor-streamAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 650 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you stream live agent swarm events without polling?
Observe, filter, and act on real-time data streams from agents, APIs, or infrastructure without writing custom polling logic.
Who is it for?
Developers operating Claude Flow swarms who need continuous event visibility instead of status polling loops.
Skip if: Batch post-mortem log analysis or projects with no running agent swarm or streaming CLI infrastructure.
When should I use this skill?
A swarm is running, the user wants live agent observability, or polling `swarm status` in a loop is too slow or noisy.
What you get
Live NDJSON event stream, per-line notifications, and optional one-shot swarm status or health snapshots.
- live NDJSON event stream
- swarm health notifications
Files
Use the Monitor tool to stream swarm events in real time instead of polling:
Run via Monitor: npx @claude-flow/cli@latest swarm watch --stream
This streams NDJSON events for agent spawns, task completions, memory writes, and health checks. Each stdout line triggers a notification.
For one-shot status, use MCP: mcp__claude-flow__swarm_status or mcp__claude-flow__swarm_health.
Prefer Monitor over polling swarm status in a loop. See ADR-091 for rationale.
Related skills
Agent BrowserGive their coding agent reliable, high-fidelity control over any website or Electron desktop app.591k39.6k
Lark ApprovalLet their AI coding agent create, read, update, and approve items in Lark (Feishu) approval workflows without leaving the coding environment.494kLark EventHandle Feishu/Lark bot events, webhooks, and subscription callbacks in agent-driven backend code.493kLark Workflow Meeting SummaryAutomatically generate structured meeting summaries and action items from Lark/Feishu calls without manual note-taking.492kLark Workflow Standup ReportAutomatically generate and post daily standup reports in Lark/Feishu from their workflow and activity data.492k
Twitter AutomationAutomate X/Twitter posts, scheduling, and engagement via X API integration441k669FAQ
What events does monitor-stream capture?
monitor-stream captures NDJSON swarm events including agent spawns, task completions, memory writes, and health checks, with each stdout line surfaced as a notification during `swarm watch --stream`.
When should monitor-stream replace polling?
monitor-stream should replace polling when a Claude Flow swarm is actively running and continuous observability is needed; use `swarm_status` or `swarm_health` MCP calls only for one-shot status checks.