When your Agent Monitor dashboard is empty and you're wondering if Claude Code hooks are even firing, this runs through the checklist: checks if all seven hook types are registered in settings.json, verifies the handler script exists and is executable, tests dashboard connectivity on port 4820, sends a test event to confirm delivery, and checks if events are actually making it into the database. You get a pass/fail report with specific fixes for whatever's broken. It's basically the troubleshooting runbook you'd write yourself after debugging hook integration issues three times, now automated so you don't have to manually curl endpoints and grep config files.

GitHub stars
455
last updated
Jun 11, 2026

Install

$ npx -y skills add hoangsonww/claude-code-agent-monitor --skill hook-diagnostics --agent claude-code

Installs into .claude/skills of the current project.

Files

Hook Diagnostics

Diagnose hook integration issues between Claude Code and the Agent Monitor.

Input

The user provides: $ARGUMENTS

This may be:

  • "full" or empty (default: run all diagnostics)
  • "install" to check hook installation only
  • "connectivity" to check dashboard connectivity only
  • "events" to check event delivery only

Procedure

Run diagnostic checks in this order:

1. Hook Installation Check

Verify hooks are installed in Claude Code settings:

# Check if hooks exist in Claude Code settings
cat ~/.claude/settings.json | jq '.hooks // empty'

Verify:

  • All 7 expected hook types are registered: PreToolUse, PostToolUse, Stop, SubagentStop, Notification, SessionStart, SessionEnd
  • Hook commands point to the correct handler script path
  • Handler script exists and is readable at the configured path

2. Dashboard Connectivity

Test that the dashboard API is reachable:

curl -sf http://localhost:4820/api/health

Verify:

  • Dashboard responds with 200 OK
  • Response includes expected health fields
  • WebSocket endpoint is accessible

3. Hook Handler Validation

Check the hook handler script:

Sponsors

Details

Repository
github.com/hoangsonww/claude-code-agent-monitor
Categories
DevOps & CI/CD, AI & Agent Building
License
MIT
First seen
Jun 11, 2026

More from hoangsonww/claude-code-agent-monitor

All 24
1hoangsonww avataroptimization-suggesthoangsonww/claude-code-agent-monitor>0skills.sh installs
2hoangsonww avatarpattern-detecthoangsonww/claude-code-agent-monitor>0skills.sh installs
3hoangsonww avatarproductivity-scorehoangsonww/claude-code-agent-monitor>0skills.sh installs
4hoangsonww avatarquick-statshoangsonww/claude-code-agent-monitor>0skills.sh installs
5hoangsonww avatarrelease-guardhoangsonww/claude-code-agent-monitorRun release-readiness checks for this repository. Use when validating docs, scripts, verification coverage, and operational safety before merge or release.0skills.sh installs
6hoangsonww avatarrepo-onboardinghoangsonww/claude-code-agent-monitorUnderstand this repository quickly before making changes. Use for architecture discovery, ownership mapping, command selection, and initial implementation plann0skills.sh installs