dashboard-status — Claude Code skill: status and setup
Checks Agent Monitor health through its API, counts, WebSocket, hooks, and latest event. Use it to see whether the monitoring dashboard is operating.
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill dashboard-status -a claude-codeWhat dashboard-status does
This skill checks Agent Monitor at http://localhost:4820. It calls /api/health, /api/stats, /api/settings/info, and /api/events?limit=1, then reports API reachability, session and agent counts, event totals, and WebSocket connections.
The latest event is used to show data freshness. Dashboard version, port, database path, and database size come from the settings response. The skill compares configured hook names with PreToolUse, PostToolUse, Stop, SubagentStop, Notification, SessionStart, and SessionEnd; it does not inspect hook commands.
Run it with no argument for the full report, quick for an API-only check, or verbose for endpoint details. If the API at localhost:4820 cannot be reached, the check cannot confirm that the monitor is operating.
What it helps with
- check whether the Agent Monitor API is reachable
- count active sessions and agents
- measure the age of the latest event
- compare configured hook names
- display dashboard and database details
Example prompts for the agent
- Check the full status of Agent Monitor.
- Run an API-only check with the
quickargument. - Show endpoint details with the
verboseargument.
How to install dashboard-status
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill dashboard-status -a claude-code2Manually: put the files in place
~/.claude/skills/dashboard-status/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/dashboard-status/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill dashboard-status -a codex2Manually: put the files in place
.agents/skills/dashboard-status/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill dashboard-status -a cursor2Manually: put the files in place
.cursor/skills/dashboard-status/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hoangsonww/Claude-Code-Agent-Monitor dashboard-status2Manually: put the files in place
.github/skills/dashboard-status/SKILL.md1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill dashboard-status -a gemini-cli2Platform CLI
gemini skills install https://github.com/hoangsonww/Claude-Code-Agent-Monitor --path plugins/ccam-dashboard/skills/dashboard-statusManually: put the files in place
.devin/skills/dashboard-status/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill dashboard-status -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about dashboard-status
How do I install dashboard-status in Claude Code?
Run npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill dashboard-status -a claude-code, then check ~/.claude/skills/dashboard-status/SKILL.md.
What does dashboard-status do?
It checks the Agent Monitor API, reads counts from /api/stats, confirms WebSocket connectivity, compares configured hook names, and reports the age of the latest event.
Which check modes does dashboard-status support?
No argument runs the full status report, quick checks the API only, and verbose includes endpoint details.
Source text
SKILL.md · MIT
---
name: dashboard-status
description: >
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.
---
# Dashboard Status
Quick status check on the Claude Code Agent Monitor dashboard.
## Input
The user provides: **$ARGUMENTS**
Options: empty (default: full status), "quick" (API only), "verbose" (include endpoint details).
## Data Sources
| Endpoint | Returns |
|----------|---------|
| `GET /api/health` | HTTP 200 if API is running |
| `GET /api/stats` | `{ total_sessions, active_sessions, active_agents, total_agents, total_events, events_today, ws_connections, agents_by_status, sessions_by_status }` |
| `GET /api/settings/info` | Dashboard configuration: version, port, data paths |
| `GET /api/events?limit=1` | Most recent event (for freshness check) |
## Status Report
### 1. API Server
- Reachable at `http://localhost:4820`? Response time?
- If unreachable: suggest `npm start` from the project directory
### 2. System Counts
From `/api/stats`:
- Total sessions tracked (`total_sessions`)
- Active agents currently running (`active_agents`)
- Total events ingested (`total_events`)
- Events today (`events_today`)
- WebSocket connections (`ws_connections`)
### 3. Data Freshness
From latest event:
- Time since last event ingested
- If >1 hour: warn about possible hook disconnect
### 4. Hook Status
Use `/api/settings/info` → `hooks` for configured hook names:
- Expected: PreToolUse, PostToolUse, Stop, SubagentStop, Notification, SessionStart, SessionEnd
- Report which hook names are present vs missing. Do not read hook commands or
unrelated settings.
### 5. Dashboard Info
From `/api/settings/info`:
- Dashboard version
- Database path and size
- Configured port
## Output Format
Compact status card:
```
╔══════════════════════════════════════╗
║ AGENT MONITOR STATUS ║
╠══════════════════════════════════════╣
║ API: ✅ Online (42ms) ║
║ Sessions: 127 tracked ║
║ Events: 4,892 ingested ║
║ Hooks: 7/7 configured ║
║ Last Event: 3 minutes ago ║
╚══════════════════════════════════════╝
```
© hoangsonww · MIT · hoangsonww/Claude-Code-Agent-Monitor