メニュー
Show token usage and estimated API cost for a Claude Code session. Use when the user asks about session cost, how much a session spent, token breakdown, API usage, or wants to analyze spend over a date range.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Sync the current git repo with remote — pull, auto-commit, push, and resolve conflicts. Use when user says "sync", "sync repo", "push changes", "save changes", or wants to commit and push all changes. Also use when user mentions conflicts during sync.
Send slash commands (like /context, /compact, /cost) to a Claude Code TUI session via tmux and capture the output. Use when the user wants to run TUI-only commands on a session programmatically.
Show a full action log (text, tool calls, tool results) for a Claude Code session. Use when the user wants to replay, debug, or inspect what happened in a session, especially after running claude -p.
Find the latest Claude Code session ID(s). Use when the user asks for the current or most recent session ID, wants to find a session, or needs to look up recent sessions to resume or inspect.
Manage personal tasks and daily plans. Use when the user wants to add, view, update, check off, or delete tasks. Also use when drafting or viewing a daily plan. Tasks are stored locally in my-data/tasks.jsonl (JSONL event log). Daily plans are freeform markdown files in my-data/daily-plans/YYYY-MM-DD.md.
Check context usage and session info for any Claude Code session. Use when the user asks about context usage, token count, session info, or wants to list/inspect Claude sessions.
SOC 職業分類に基づく
| name | claude-usage |
| description | Show token usage and estimated API cost for a Claude Code session. Use when the user asks about session cost, how much a session spent, token breakdown, API usage, or wants to analyze spend over a date range. |
Aggregates token usage and calculates estimated API cost from a session's .jsonl file.
# Show total usage for a session (falls back to $AGENT_SESSION_ID if no arg)
python3 .claude/skills/claude-usage/scripts/usage_summary.py <session-id>
# Filter by date range (ISO format, date-only or datetime)
python3 .claude/skills/claude-usage/scripts/usage_summary.py <session-id> --start 2026-03-01
python3 .claude/skills/claude-usage/scripts/usage_summary.py <session-id> --start 2026-03-01T09:00:00 --end 2026-03-16T23:59:59
# Use custom projects directory
python3 .claude/skills/claude-usage/scripts/usage_summary.py <session-id> --dir /path/to/projects
Session: <id>
Period: 2026-03-01 09:00 → 2026-03-16 18:42
Turns: 42
Tokens
Input: 1.2m
Cache write: 45.3k
Cache read: 890.1k
Output: 123.4k
Estimated cost: $1.2345
By model: (shown only if session used multiple models)
claude-sonnet-4-6 38 turns $1.10
claude-opus-4-6 4 turns $0.13
Each assistant turn's tokens are multiplied by the model's per-token price and summed:
| Token type | Billed as |
|---|---|
input_tokens | input price |
cache_creation | cache write |
cache_read | cache read |
output_tokens | output price |
Prices are estimates based on public Anthropic pricing. Actual billing may differ.