transcript-analyzer

# Transcript Analyzer Skill

Use this skill when you need to analyze Claude Code session transcripts for:
- Debugging plugin behavior
- Understanding context/token usage patterns
- Tracing tool execution flow
- Finding sources of context bloat
- Investigating errors or unexpected behavior

## Transcript Location

Claude Code stores session transcripts at:
```
~/.claude/projects/-PATH-TO-PROJECT/*.jsonl
```

The path uses dashes instead of slashes. For example:
- Project: `/Users/bfreis/dev/myproject`
- Transcripts: `~/.claude/projects/-Users-bfreis-dev-myproject/*.jsonl`

## Transcript Structure

Transcripts use **JSONL format** (one JSON object per line).

### Record Types

| Type | Description |
|------|-------------|
| `summary` | Session metadata |
| `file-history-snapshot` | File change tracking |
| `user` | User messages (includes tool results) |
| `assistant` | Assistant messages (includes tool calls) |

### Message Structure

```json
{
  "type": "user" | "assistant",
  "uuid": "message-uuid",
  "parentUuid": "parent-message-uuid",
  "sessionId": "session-uuid",
  "isSidechain": false,
  "timestamp": "2025-12-06T...",
  "message": {
    "role": "user" | "assistant",
    "content": [...],
    "usage": { "input_tokens": N, "output_tokens": N }
  }
}
```

### Content Block Types

**In assistant messages:**
- `text` - Regular text response
- `tool_use` - Tool invocation with `.id`, `.name`, `.input`
- `thinking` - Extended thinking blocks

**In user messages:**
- `text` - User input
- `tool_result` - Tool output with `.tool_use_id`, `.content`

### Critical Gotchas

1. **Content is ALWAYS an array** - Even single text blocks
2. **Tool result `.content` can be string OR array** - Handle both:
   ```jq
   if .content | type == "array" then
     (.content | map(.text // "") | add)
   else
     .content
   end
   ```
3. **Use `[]?` not `[]`** - Handles missing fields gracefully
4. **Sub-agents have `isSidechain: true`** - Filter these for main conversation only
5. **