subagent-dashboard

Web dashboard for real-time monitoring and management of OpenClaw subagents. Use when monitoring or managing subagents.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "subagent-dashboard" with this command: npx skills add austindixson/subagent-dashboard

Subagent Dashboard Skill

Web dashboard for real-time monitoring and management of OpenClaw subagents.

Installation

cd workspace/skills/subagent-dashboard/scripts
./start_dashboard.sh

Or manually:

python3 -m venv venv
source venv/bin/activate
pip install -r ../requirements.txt
python3 dashboard.py

Usage

Start the dashboard and open http://localhost:8080 in your browser.

The dashboard shows:

  • All sessions from sessions.json: main (orchestrator), subagents, and optionally cron jobs
  • Real-time updates (auto-refresh every 3 seconds)
  • Agent details: model, age, tokens, task progress; role badges (Main / Subagent / Cron)
  • Transcript viewing for each agent
  • Stalled agent detection (>30 min inactive)

Purpose

Provides a web UI to:

  • Monitor active subagents in real-time
  • View agent transcripts and activity
  • Detect and manage stalled agents
  • Track task progress and token usage

Dependencies

  • Flask (web server)
  • flask-cors (CORS support)
  • Subagent-tracker skill (for data)

Configuration

Set PORT environment variable to change the server port (default: 8080).

Integration

The dashboard uses the subagent-tracker skill to fetch data. It reads:

  • ~/.openclaw/agents/main/sessions/sessions.json - Session list
  • ~/.openclaw/agents/main/sessions/*.jsonl - Transcript files
  • ~/.openclaw/agents/main/subagents/runs.json - Task mapping (and legacy ~/.openclaw/subagents/runs.json)

Completed column: For finished tasks to appear in the Completed column, the run in runs.json must have endedAt (timestamp) and outcome.status set to "ok", "completed", or "success" when the sub-agent finishes. The dashboard appends "recently completed" runs (within 24h) even if the session was removed from sessions.json.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

AANA Continuous Self-Improvement Skill

Enable continuous workflow improvement by observing outcomes, identifying issues, proposing low-risk changes, and verifying them without altering agent autho...

Registry SourceRecently Updated
Automation

Agentmfa

Request human approval via biometric auth before performing sensitive actions. Use this skill whenever an action is irreversible, destructive, or requires hu...

Registry SourceRecently Updated
Automation

Proviras Logger

Run on every heartbeat to summarize completed tasks and log them to your analytics dashboard. Triggers automatically during heartbeat cycles to track agent p...

Registry SourceRecently Updated
Automation

clawpage-skill

Router for Clawpage workflows. Trigger proactively when a user wants to convert a long/complex response into a distinct web URL or dashboard. Also use for al...

Registry SourceRecently Updated