Loading...
Loading...
Reference documentation for analyzing Claude Code conversation history files
npx skill4agent add akiselev/qt-llm-template cc-history~/.claude/projects/{encoded-path}/
|-- {session-uuid}.jsonl # Main conversation
|-- {session-uuid}/
|-- subagents/
| |-- agent-{hash}.jsonl # Subagent conversations
|-- tool-results/ # Large tool outputsPROJECT_DIR="~/.claude/projects/$(echo "$PWD" | sed 's|^/|-|; s|/\.|--|g; s|/|-|g')"/-/-/.--/Users/bill/.claude-Users-bill--claude/Users/bill/git/myproject-Users-bill-git-myproject| Type | Description |
|---|---|
| User input messages |
| Model responses (thinking, tool_use, text) |
| System messages |
| Background task notifications (subagent done) |
{
"type": "assistant",
"uuid": "abc123",
"parentUuid": "xyz789",
"timestamp": "2025-01-15T19:39:16.000Z",
"sessionId": "session-uuid",
"message": {
"role": "assistant",
"content": [...],
"usage": {
"input_tokens": 20000,
"output_tokens": 500,
"cache_read_input_tokens": 15000,
"cache_creation_input_tokens": 5000
}
}
}type: "thinking"thinkingtype: "tool_use"nameinputtype: "text"text# List by modification time (most recent first)
ls -lt "$PROJECT_DIR"/*.jsonl
# Find by date
ls -la "$PROJECT_DIR"/*.jsonl | grep "Jan 15"
# Find by content
grep -l "search term" "$PROJECT_DIR"/*.jsonl# Get message by line number (1-indexed)
sed -n '42p' file.jsonl | jq .
# Get message by uuid
jq -c 'select(.uuid=="abc123")' file.jsonl
# All user messages
jq -c 'select(.type=="user")' file.jsonl
# All assistant messages
jq -c 'select(.type=="assistant")' file.jsonl# List all tool calls
jq -c 'select(.type=="assistant") | .message.content[]? | select(.type=="tool_use") | {name, input}' file.jsonl
# Count tool calls by name
jq -c 'select(.type=="assistant") | .message.content[]? | select(.type=="tool_use") | .name' file.jsonl | sort | uniq -c | sort -rn
# Find specific tool calls
jq -c 'select(.type=="assistant") | .message.content[]? | select(.type=="tool_use" and .name=="Bash")' file.jsonlpython3 -m skills\.([a-z_]+)\.# Find all skill invocations
grep -oE "python3 -m skills\.[a-z_]+" file.jsonl | sort -u
# Find conversations using a specific skill
grep -l "python3 -m skills\.planner\." "$PROJECT_DIR"/*.jsonl# Total tokens in conversation
jq -s '[.[].message.usage? | select(.) | .input_tokens + .output_tokens] | add' file.jsonl
# Token breakdown
jq -s '[.[].message.usage? | select(.)] | {
input: (map(.input_tokens) | add),
output: (map(.output_tokens) | add),
cached: (map(.cache_read_input_tokens // 0) | add)
}' file.jsonl
# Token progression over time
jq -c 'select(.type=="assistant") | {ts: .timestamp[11:19], inp: .message.usage.input_tokens, out: .message.usage.output_tokens}' file.jsonl# Count messages by type
jq -s 'group_by(.type) | map({type: .[0].type, count: length})' file.jsonl
# Character count in user messages
jq -s '[.[] | select(.type=="user") | .message.content | length] | add' file.jsonl
# Thinking block character count
jq -s '[.[] | select(.type=="assistant") | .message.content[]? | select(.type=="thinking") | .thinking | length] | add' file.jsonl# List subagents for a session
ls "${SESSION_DIR}/subagents/"
# Get subagent task description (first user message)
jq -c 'select(.type=="user") | .message.content' agent-*.jsonl | head -1
# Find Task tool calls in parent (these spawn subagents)
jq -c 'select(.type=="assistant") | .message.content[]? | select(.type=="tool_use" and .name=="Task") | .input' file.jsonlagent-{hash}.jsonl{session}/subagents/