메뉴
Query Claude Code session analytics from ccrecall database. Use when user asks about token usage, session history, or wants to analyze their Claude Code usage patterns.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Setup guide for essential MCP servers. Use when configuring MCP servers or when user asks about search, SQLite, or MCP management.
High-leverage prompts that challenge Claude's defaults. Use for "grill me", "prove it works", "scrap this", "what would 10x engineer do", "find ways this fails".
Maintain CLAUDE.md files effectively. Use when adding lessons learned, updating conventions, or restructuring project instructions.
Multi-agent orchestration patterns for Claude Code team mode. Use when coordinating teammates, decomposing complex tasks, or managing shared task lists.
Enhanced Research-Plan-Implement workflow with structured phase gates. Use when tackling complex tasks that benefit from a phased approach with user checkpoints.
Terminal setup for Claude Code. Use for Ghostty config, statusline customization, voice dictation, tmux worktrees.
| name | analytics |
| description | Query Claude Code session analytics from ccrecall database. Use when user asks about token usage, session history, or wants to analyze their Claude Code usage patterns. |
Query your Claude Code usage data from the ccrecall SQLite database.
# Sync transcripts to SQLite (requires bun)
bun x ccrecall sync
Database location: ~/.claude/ccrecall.db
bun x ccrecall sync # Import transcripts (incremental)
bun x ccrecall stats # Show session/message/token counts
bun x ccrecall sessions # List recent sessions
bun x ccrecall search # Full-text search across messages
bun x ccrecall tools # Show most-used tools
bun x ccrecall query # Execute raw SQL
SELECT model,
COUNT(*) as messages,
SUM(input_tokens) as input_tok,
SUM(output_tokens) as output_tok
FROM messages
WHERE model IS NOT NULL
GROUP BY model;
SELECT date(timestamp/1000, 'unixepoch') as day,
COUNT(*) as msgs,
SUM(output_tokens) as tokens
FROM messages
GROUP BY day
ORDER BY day DESC
LIMIT 7;
SELECT s.project_path,
COUNT(m.uuid) as messages,
SUM(m.output_tokens) as tokens
FROM sessions s
JOIN messages m ON m.session_id = s.id
GROUP BY s.project_path
ORDER BY tokens DESC
LIMIT 10;
SELECT tool_name, COUNT(*) as count
FROM tool_calls
GROUP BY tool_name
ORDER BY count DESC;
SELECT substr(thinking, 1, 200) as preview,
datetime(timestamp/1000, 'unixepoch') as time
FROM messages
WHERE thinking LIKE '%your search term%'
ORDER BY timestamp DESC
LIMIT 10;
If you have mcp-sqlite-tools configured, Claude can query directly:
open_database ~/.claude/ccrecall.dbsessions, messages, tool_calls, tool_results, teams, team_members, team_tasks