Launch or check the Claude Code monitoring dashboard. Use when: open dashboard, show dashboard, agent dashboard, monitoring, check agent activity, session stats, telemetry viewer.
From george-setupnpx claudepluginhub george11642/george-plugins --plugin george-setupThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Launch or check the agent activity dashboard.
bash ~/.claude/dashboard/start.sh
Then report: "Dashboard running at http://localhost:7860"
# Check if already running
lsof -ti :7860 >/dev/null 2>&1 && echo "Dashboard is running (PID: $(cat ~/.claude/dashboard/.pid 2>/dev/null || lsof -ti :7860))" || echo "Dashboard is not running"
kill $(cat ~/.claude/dashboard/.pid 2>/dev/null) 2>/dev/null || kill $(lsof -ti :7860) 2>/dev/null
echo "Dashboard stopped"
python3 -c "
import json; from pathlib import Path
b = json.loads((Path.home()/'.claude/behavior.json').read_text())
bg = json.loads((Path.home()/'.claude/budget.json').read_text())
print(f'Mode: {b.get(\"autonomy\",\"?\")} | Domain: {b.get(\"active_domain\",\"none\")} | Tools: {b.get(\"tool_call_count\",0)}/{bg.get(\"hard_limit\",200)}')
"