Skip to main content
skill CX Codex

hook-diagnostics — Claude Code skill: what it does, how to install

Troubleshoots Claude Code hook registration, agent monitor reachability, and event ingestion. Useful when events stop appearing in the dashboard.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill hook-diagnostics -a claude-code
Open on GitHub

What hook-diagnostics does

Hook Diagnostics detects integration failures between Claude Code and the local Agent Monitor tool. It inspects ~/.claude/settings.json first. The tool checks for seven required hook types: PreToolUse, PostToolUse, Stop, SubagentStop, Notification, SessionStart, and SessionEnd. It also confirms that the configured handler script exists and has read permissions.

The second stage covers network and runtime checks. It pings http://localhost:4820/api/health, verifies JavaScript syntax using node --check, and posts a mock event payload. It then queries recent database entries to identify gaps in telemetry. Without the monitor service listening on port 4820, network checks fail immediately.

What it helps with

  • detect missing hook registrations in ~/.claude/settings.json
  • verify Agent Monitor connectivity on port 4820
  • validate hook handler script syntax with Node.js
  • send test events to confirm delivery and database writes

Example prompts for the agent

  • Run a full check using hook-diagnostics
  • Check dashboard connectivity using hook-diagnostics connectivity
  • Verify hook configuration in settings using hook-diagnostics install

How to install hook-diagnostics

1Skills CLI (Vercel)

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill hook-diagnostics -a claude-code

2Manually: put the files in place

~/.claude/skills/hook-diagnostics/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/hook-diagnostics/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about hook-diagnostics

How to install hook-diagnostics in Claude Code?

Install the skill by running npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill hook-diagnostics -a claude-code in your terminal.

What does hook-diagnostics do?

It evaluates hook configurations, dashboard reachability, handler script syntax, and database persistence. After checking each stage, it prints a status report with direct fix commands.

Which hook types does hook-diagnostics check?

It validates seven registrations: PreToolUse, PostToolUse, Stop, SubagentStop, Notification, SessionStart, and SessionEnd. Any missing hook or broken path triggers a warning.

Source text

SKILL.md · MIT
---
name: hook-diagnostics
description: >
  Diagnose Claude Code hook installation, delivery, and ingestion issues.
  Checks hook configuration, connectivity, event flow, and identifies
  common problems. Use when events are not appearing in the dashboard.
---

# 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:

```bash
# 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:

```bash
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:

```bash
# Verify handler exists and is executable
ls -la <handler-path>
# Syntax check
node --check <handler-path>
```

### 4. Event Delivery Test
Send a test event and verify it arrives:

```bash
echo '{"hook_type":"test","session_id":"diag-test","data":{}}' | \
  curl -sf -X POST http://localhost:4820/api/hooks/event \
  -H 'Content-Type: application/json' -d @-
```

### 5. Database Check
Verify the database is writable and events are persisted:

```bash
curl -sf http://localhost:4820/api/stats
curl -sf http://localhost:4820/api/events?limit=5
```

### 6. Recent Event Flow
Check if events are flowing:
- Time since last event received
- Events received in last hour
- Any gaps in event delivery

## Output Format

Present as a diagnostic report with:
```
Hook Diagnostics Report
━━━━━━━━━━━━━━━━━━━━━━
✅ Hook Installation .............. PASS
✅ Dashboard Connectivity ......... PASS
✅ Handler Script ................. PASS
⚠️ Event Delivery ................ WARN (slow)
✅ Database ....................... PASS
❌ Recent Event Flow .............. FAIL (no events in 2h)
━━━━━━━━━━━━━━━━━━━━━━
Overall: 5/6 checks passed
```

For each failed or warning check, include:
- What was expected vs what was found
- Specific remediation steps
- Commands to fix the issue

© hoangsonww · MIT · hoangsonww/Claude-Code-Agent-Monitor

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set60

benchmark The benchmark skill takes one session or a few recent ones and compares them with the rolling average from Agent Monitor data: cost, tokens, tool count and workflow complexity. Each metric comes back as a percentile of the population. CX Codex +1 ★ 1,121repo stars anomaly-alert Flags anomalous Claude Code sessions by checking spending spikes and tool execution errors via local Agent Monitor. CX Codex +1 ★ 1,121repo stars transcript-grep Search a session’s conversation for text or a regex and inspect each hit in context. Handy when you need to track down a prompt, tool call, or error. CX Codex +1 ★ 1,121repo stars session-debug Pulls a single Claude session out of Agent Monitor and reports its event chain, subagent tree, token spend and failures. CX Codex +1 ★ 1,121repo stars health-check This skill checks Agent Monitor’s API, database, WebSocket, endpoints, hooks, and data freshness. Use it to spot issues in a monitoring setup. CX Codex +1 ★ 1,121repo stars event-trace Turns one Claude session into an ordered timeline of its events, flagging gaps, failures and tool calls that never finished. CX Codex +1 ★ 1,121repo stars data-export Exports Claude Code sessions, events, costs, and analytics into JSON, CSV, or Markdown. Useful for backups, cost auditing, and custom reports. CX Codex +1 ★ 1,121repo stars quick-stats Get a compact Agent Monitor snapshot covering agent sessions, spending, daily events, and tool usage. Check the latest activity from your terminal. CX Codex +1 ★ 1,121repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor