Tooluck logoTooluck
SKILL.md

hook-diagnostics

Agent skill fromhoangsonww/Claude-Code-Agent-Monitor

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.

How to install hook-diagnostics

install hook-diagnostics
# install the Claude-Code-Agent-Monitor pack with the skills CLI
npx skills add hoangsonww/Claude-Code-Agent-Monitor

# or add only this skill to Claude Code: copy the folder

plugins/ccam-devtools/skills/hook-diagnostics/

# into

~/.claude/skills/hook-diagnostics/ (all projects)

.claude/skills/hook-diagnostics/ (one project)

plugins/ccam-devtools/skills/hook-diagnostics/SKILL.md

MITFull file
1# Hook Diagnostics
2
3Diagnose hook integration issues between Claude Code and the Agent Monitor.
4
5## Input
6
7The user provides: **$ARGUMENTS**
8
9This may be:
10- "full" or empty (default: run all diagnostics)
11- "install" to check hook installation only
12- "connectivity" to check dashboard connectivity only
13- "events" to check event delivery only
14
15## Procedure
16
17Run diagnostic checks in this order:
18
19### 1. Hook Installation Check
20Verify hooks are installed in Claude Code settings:
21
22```bash
23# Check if hooks exist in Claude Code settings
24cat ~/.claude/settings.json | jq '.hooks // empty'
25```
26
27Verify:
28- All 7 expected hook types are registered: `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStop`, `Notification`, `SessionStart`, `SessionEnd`
29- Hook commands point to the correct handler script path
30- Handler script exists and is readable at the configured path
31
32### 2. Dashboard Connectivity
33Test that the dashboard API is reachable:
34
35```bash
36curl -sf http://localhost:4820/api/health
37```
38
39Verify:
40- Dashboard responds with 200 OK
41- Response includes expected health fields
42- WebSocket endpoint is accessible
43
44### 3. Hook Handler Validation
45Check the hook handler script:
46
47```bash
48# Verify handler exists and is executable
49ls -la <handler-path>
50# Syntax check
51node --check <handler-path>
52```
53
54### 4. Event Delivery Test
55Send a test event and verify it arrives:
56
57```bash
58echo '{"hook_type":"test","session_id":"diag-test","data":{}}' | \
59 curl -sf -X POST http://localhost:4820/api/hooks/event \
60…

Excerpt shown under the repository's MIT license.

More skills in Claude-Code-Agent-Monitor

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

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

CCCXGHGM+135 skills

nexu-io /

open-design
107k

The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate together in one workspace.

40 skills

tt-a1i /

archify
95k

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

CCCXOC1 skill

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates