Skills for Real Engineers. Straight from my .agents directory.
session-debug
Agent skill fromhoangsonww/Claude-Code-Agent-Monitor
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).
How to install session-debug
npx skills add hoangsonww/Claude-Code-Agent-Monitor# or add only this skill to Claude Code: copy the folder
plugins/ccam-devtools/skills/session-debug/
# into
~/.claude/skills/session-debug/ (all projects)
.claude/skills/session-debug/ (one project)
1# Session Debug23Debug and inspect a Claude Code session from Agent Monitor data.45## Input67The user provides: **$ARGUMENTS**89This may be:10- A session ID to debug11- "latest" or "last" for the most recent session12- "errors" to find and debug the most recent errored session1314## Procedure15161. **Identify the target session**:17 - If session ID given: `GET /api/sessions/{id}` from `http://localhost:4820`18 - If "latest": `GET /api/sessions?limit=1` (default sort: most recently updated first)19 - If "errors": `GET /api/sessions?limit=10&status=error`20212. **Collect full session data**:22 - Session metadata: status, model, cwd, timestamps, duration23 - Events: `GET /api/events?session_id={session_id}` — full event timeline24 - Agents: `GET /api/agents?session_id={session_id}` — all agents in session25 - Cost: `GET /api/pricing/cost/{session_id}`26273. **Analyze the session**:2829 ### Session Lifecycle30 - Start time → first event → last event → end time31 - Status transitions (active → working → completed/error)32 - Total duration and active-vs-idle time3334 ### Event Chain Analysis35 - Chronological event list with timestamps and durations36 - Identify the **critical path** (longest chain of dependent events)37 - Flag events that took unusually long38 - Highlight error events with full error context3940 ### Agent Inspection41 - List all agents: type, task, status, duration42 - Subagent tree visualization (parent → children)43…
Excerpt shown under the repository's MIT license.
More skills in Claude-Code-Agent-Monitor
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
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
