health-check · hoangsonww — Claude Code skill: checks and install
This skill checks Agent Monitor’s API, database, WebSocket, endpoints, hooks, and data freshness. Use it to spot issues in a monitoring setup.
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill health-check -a claude-codeWhat health-check does
In full mode, the skill queries the local API and stats endpoints at localhost:4820, tests WebSocket support and key API endpoints, then checks hook integration. It also checks when the latest event arrived and the latest session was created, and flags active sessions with no events for more than an hour.
quick is for a connectivity check. deep adds database integrity and resource checks: database and log sizes, free disk space, and Node.js process memory when accessible. Hook checks cover the handler script and ~/.claude/settings.json. The local API checks require Agent Monitor to be running.
The skill formats its findings as a system health dashboard. For failed checks, it provides an explanation and remediation steps.
What it helps with
- check whether the Agent Monitor API responds
- find database or WebSocket issues
- test the main API endpoints
- inspect hook configuration
- identify stale active sessions
Example prompts for the agent
- Run
health-checkinfullmode and show the Agent Monitor status dashboard. - Run a quick connectivity check with
health-check quick. - Run
health-check deepand include database integrity and resource usage.
How to install health-check
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill health-check -a claude-code2Manually: put the files in place
~/.claude/skills/health-check/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/health-check/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill health-check -a codex2Manually: put the files in place
.agents/skills/health-check/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill health-check -a cursor2Manually: put the files in place
.cursor/skills/health-check/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hoangsonww/Claude-Code-Agent-Monitor health-check2Manually: put the files in place
.github/skills/health-check/SKILL.md1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill health-check -a gemini-cli2Platform CLI
gemini skills install https://github.com/hoangsonww/Claude-Code-Agent-Monitor --path plugins/ccam-devtools/skills/health-checkManually: put the files in place
.devin/skills/health-check/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill health-check -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 health-check
How do I install health-check in Claude Code?
Run npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill health-check -a claude-code. The skill file is at ~/.claude/skills/health-check/SKILL.md.
What does health-check do?
It checks Agent Monitor’s API, database, WebSocket, endpoints, hooks, and data freshness. Deep mode also checks database integrity and resource usage.
How do quick and deep modes differ?
quick performs a connectivity check. deep adds database integrity checks, file sizes, available disk space, and Node.js process memory when accessible.
Source text
SKILL.md · MIT
--- name: health-check description: > Run comprehensive health checks on the Claude Code Agent Monitor system. Validates dashboard API, database, WebSocket, hooks, and disk usage. Use to verify the monitoring setup is working correctly. --- # Health Check Run a comprehensive health check on the Agent Monitor system. ## Input The user provides: **$ARGUMENTS** This may be: - "full" or empty (default: run all checks) - "quick" for a fast connectivity check - "deep" for extended checks including database integrity ## Procedure Run health checks in this order: ### 1. API Health ```bash curl -sf http://localhost:4820/api/health ``` - Verify HTTP 200 response - Check response time (<500ms expected, <1000ms acceptable) - Confirm JSON response body ### 2. Database Health ```bash curl -sf http://localhost:4820/api/stats ``` - Verify stats endpoint returns valid data - Check that counts are non-negative integers - Verify database file exists and has reasonable size ### 3. WebSocket Health - Check that the WebSocket server is listening - Verify WebSocket upgrade is supported on the dashboard port ### 4. API Endpoint Validation Test each major endpoint: ```bash curl -sf http://localhost:4820/api/sessions?limit=1 curl -sf http://localhost:4820/api/events?limit=1 curl -sf http://localhost:4820/api/analytics curl -sf http://localhost:4820/api/pricing curl -sf http://localhost:4820/api/settings/info ``` ### 5. Hook Integration - Verify hook handler script exists - Check hooks are configured in `~/.claude/settings.json` - Verify the handler script targets the correct dashboard URL ### 6. Disk & Resource Usage (deep mode only) - Database file size - Log file sizes (if any) - Available disk space - Node.js process memory usage (if accessible) ### 7. Data Freshness - Time since last event ingested - Time since last session created - Check for stale active sessions (active but no events in >1 hour) ## Output Format Present as a system health dashboard: ``` ╔══════════════════════════════════════════════╗ ║ AGENT MONITOR HEALTH CHECK ║ ║ Timestamp: 2025-04-11 12:00:00 UTC ║ ╠══════════════════════════════════════════════╣ ║ ║ ║ API Server ............ ✅ OK (45ms) ║ ║ Database .............. ✅ OK (2.4 MB) ║ ║ WebSocket ............. ✅ OK ║ ║ API Endpoints ......... ✅ 6/6 passing ║ ║ Hook Integration ...... ⚠️ 5/7 hooks ║ ║ Data Freshness ........ ✅ 3m ago ║ ║ ║ ║ Overall: HEALTHY (5/6 checks passed) ║ ║ ║ ╚══════════════════════════════════════════════╝ ``` For any non-passing check, include detailed explanation and remediation steps below the dashboard.
© hoangsonww · MIT · hoangsonww/Claude-Code-Agent-Monitor
Similar skills
All skills for DevOps and infrastructure →health-check by other authors comes first.