Claude Skill

session-debug

Debug a specific session by inspecting its full event chain (PreToolUse, PostToolUse, Stop, SubagentStop, Compaction, APIError, TurnDuration, Notification events), agent hierarchy (recursive parent/child tree with subagent_type and depth), token usage with compaction baselines, w

LLM Mart · 0 points · 8 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download hoangsonww-claude-code-agent-monitor-plugins_ccam-devtools_skills_session-debug-83d4df5.zip · 1 KB

hoangsonww/claude-code-agent-monitor 1014 238 forks MIT Updated 21h ago

Part of hoangsonww/claude-code-agent-monitor — 86 skills

Install

skills CLI

npx skills add https://github.com/hoangsonww/Claude-Code-Agent-Monitor/tree/master/plugins/ccam-devtools/skills/session-debug

Claude Code

claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install hoangsonww-claude-code-agent-monitor@llmmart

Git git clone https://github.com/hoangsonww/Claude-Code-Agent-Monitor.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole hoangsonww/claude-code-agent-monitor collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Session Debug

Debug and inspect a Claude Code session from Agent Monitor data.

Input

The user provides: $ARGUMENTS

This may be:

A session ID to debug
"latest" or "last" for the most recent session
"errors" to find and debug the most recent errored session

Procedure

Identify the target session:
- If session ID given: GET /api/sessions/{id} from http://localhost:4820
- If "latest": GET /api/sessions?limit=1 (default sort: most recently updated first)
- If "errors": GET /api/sessions?limit=10&status=error
Collect full session data:
- Session metadata: status, model, cwd, timestamps, duration
- Events: GET /api/events?session_id={session_id} — full event timeline
- Agents: GET /api/agents?session_id={session_id} — all agents in session
- Cost: GET /api/pricing/cost/{session_id}
Analyze the session:

Session Lifecycle
- Start time → first event → last event → end time
- Status transitions (active → working → completed/error)
- Total duration and active-vs-idle time
Event Chain Analysis
- Chronological event list with timestamps and durations
- Identify the critical path (longest chain of dependent events)
- Flag events that took unusually long
- Highlight error events with full error context
Agent Inspection
- List all agents: type, task, status, duration
- Subagent tree visualization (parent → children)
- Agents that failed and their last known state
- Agent switching patterns (when and why new agents spawned)
Tool Execution Trace
- Every tool invocation in order with: tool name, duration, success/failure
- Failed tool calls with error messages
- Tool retry patterns (same tool called multiple times)
Anomaly Detection
- Events out of expected order
- Gaps in event timeline (>30s with no events)
- Duplicate events or agent states
- Token usage spikes (compaction indicators)
Diagnosis:
- Root cause hypothesis (if errors present)
- Contributing factors
- Remediation suggestions

Output Format

Present as a debug report with:

Session summary header (ID, status, model, duration, cost)
Color-coded timeline (✅ success, ❌ error, ⚠️ warning, ℹ️ info)
Agent tree diagram
Diagnosis section with numbered findings

Files (claude-code-agent-monitor)

agents

openai.yaml 266 B

interface:
  display_name: "Session Debug"
  short_description: "Debug a specific session by inspecting its full event chain..."
  default_prompt: "Use $session-debug to inspect CCAM data and complete this workflow safely."
policy:
  allow_implicit_invocation: true

SKILL.md 2.8 KB

---
name: session-debug
description: >
  Debug a specific session by inspecting its full event chain (PreToolUse,
  PostToolUse, Stop, SubagentStop, Compaction, APIError, TurnDuration,
  Notification events), agent hierarchy (recursive parent/child tree with
  subagent_type and depth), token usage with compaction baselines, workflow
  intelligence data (orchestration DAG, error propagation by depth), and
  session metadata (thinking_blocks, turn_count, total_turn_duration_ms).
---

# Session Debug

Debug and inspect a Claude Code session from Agent Monitor data.

## Input

The user provides: **$ARGUMENTS**

This may be:
- A session ID to debug
- "latest" or "last" for the most recent session
- "errors" to find and debug the most recent errored session

## Procedure

1. **Identify the target session**:
   - If session ID given: `GET /api/sessions/{id}` from `http://localhost:4820`
   - If "latest": `GET /api/sessions?limit=1` (default sort: most recently updated first)
   - If "errors": `GET /api/sessions?limit=10&status=error`

2. **Collect full session data**:
   - Session metadata: status, model, cwd, timestamps, duration
   - Events: `GET /api/events?session_id={session_id}` — full event timeline
   - Agents: `GET /api/agents?session_id={session_id}` — all agents in session
   - Cost: `GET /api/pricing/cost/{session_id}`

3. **Analyze the session**:

   ### Session Lifecycle
   - Start time → first event → last event → end time
   - Status transitions (active → working → completed/error)
   - Total duration and active-vs-idle time

   ### Event Chain Analysis
   - Chronological event list with timestamps and durations
   - Identify the **critical path** (longest chain of dependent events)
   - Flag events that took unusually long
   - Highlight error events with full error context

   ### Agent Inspection
   - List all agents: type, task, status, duration
   - Subagent tree visualization (parent → children)
   - Agents that failed and their last known state
   - Agent switching patterns (when and why new agents spawned)

   ### Tool Execution Trace
   - Every tool invocation in order with: tool name, duration, success/failure
   - Failed tool calls with error messages
   - Tool retry patterns (same tool called multiple times)

   ### Anomaly Detection
   - Events out of expected order
   - Gaps in event timeline (>30s with no events)
   - Duplicate events or agent states
   - Token usage spikes (compaction indicators)

4. **Diagnosis**:
   - Root cause hypothesis (if errors present)
   - Contributing factors
   - Remediation suggestions

## Output Format

Present as a debug report with:
- Session summary header (ID, status, model, duration, cost)
- Color-coded timeline (✅ success, ❌ error, ⚠️ warning, ℹ️ info)
- Agent tree diagram
- Diagnosis section with numbered findings