Skills for Real Engineers. Straight from my .agents directory.
dashboard-status
Agent skill fromhoangsonww/Claude-Code-Agent-Monitor
Quick dashboard health and status overview — checks the Agent Monitor API (port 4820), reports session/agent/event counts from /api/stats, confirms WebSocket connectivity, reads the redacted hook status returned by /api/settings/info, and shows data freshness (last event timestamp). Use to verify the monitoring system is operational.
How to install dashboard-status
npx skills add hoangsonww/Claude-Code-Agent-Monitor# or add only this skill to Claude Code: copy the folder
plugins/ccam-dashboard/skills/dashboard-status/
# into
~/.claude/skills/dashboard-status/ (all projects)
.claude/skills/dashboard-status/ (one project)
1# Dashboard Status23Quick status check on the Claude Code Agent Monitor dashboard.45## Input67The user provides: **$ARGUMENTS**89Options: empty (default: full status), "quick" (API only), "verbose" (include endpoint details).1011## Data Sources1213| Endpoint | Returns |14|----------|---------|15| `GET /api/health` | HTTP 200 if API is running |16| `GET /api/stats` | `{ total_sessions, active_sessions, active_agents, total_agents, total_events, events_today, ws_connections, agents_by_status, sessions_by_status }` |17| `GET /api/settings/info` | Dashboard configuration: version, port, data paths |18| `GET /api/events?limit=1` | Most recent event (for freshness check) |1920## Status Report2122### 1. API Server23- Reachable at `http://localhost:4820`? Response time?24- If unreachable: suggest `npm start` from the project directory2526### 2. System Counts27From `/api/stats`:28- Total sessions tracked (`total_sessions`)29- Active agents currently running (`active_agents`)30- Total events ingested (`total_events`)31- Events today (`events_today`)32- WebSocket connections (`ws_connections`)3334### 3. Data Freshness35From latest event:36- Time since last event ingested37- If >1 hour: warn about possible hook disconnect3839### 4. Hook Status40Use `/api/settings/info` → `hooks` for configured hook names:41- Expected: PreToolUse, PostToolUse, Stop, SubagentStop, Notification, SessionStart, SessionEnd42- Report which hook names are present vs missing. Do not read hook commands or43 unrelated settings.44…
Excerpt shown under the repository's MIT license.
More skills in Claude-Code-Agent-Monitor
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
