菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
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.
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.
| name | claude-session-log |
| description | 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. |
Replay a Claude Code session as a human-readable transcript or structured JSON. Shows assistant text, tool calls, and tool results for every turn.
# Show log for a specific session
python3 .claude/skills/claude-session-log/scripts/session_log.py <session-id>
# Show log for the most recent session
python3 .claude/skills/claude-session-log/scripts/session_log.py --latest
# JSON output (always full content, no truncation)
python3 .claude/skills/claude-session-log/scripts/session_log.py --latest --json
# Show only tool calls and results (skip pure text)
python3 .claude/skills/claude-session-log/scripts/session_log.py --latest --tools-only
# Disable truncation on tool results (default: 500 chars)
python3 .claude/skills/claude-session-log/scripts/session_log.py --latest --full
# Use custom projects directory
python3 .claude/skills/claude-session-log/scripts/session_log.py --latest --dir /path/to/projects
Human-readable (default):
Session: 82c946c8-1eb8-4c70-9414-813fc0a278e4
Date: 2026-03-28 14:58
Model: claude-opus-4-6
Turns: 5
--- user (14:58:04) ---
Fix the bug in parser.py
--- assistant (14:58:06) ---
Let me read the file first.
> Read scripts/parser.py
[2847 chars, truncated]
def parse(input):
tokens = input.split()
...
> Edit scripts/parser.py
old: if t.startswith("--"):
new: if t.startswith("--") or t.startswith("-"):
Fixed the parser to handle single-dash flags.
--- user (14:58:12) ---
< tool_result (Read): [ok]
< tool_result (Edit): [ok]
--- assistant (14:58:15) ---
Done. The parser now handles both --flag and -f syntax.
JSON mode (--json):
{
"session_id": "82c946c8-...",
"model": "claude-opus-4-6",
"turns": 5,
"messages": [
{
"role": "user",
"timestamp": "2026-03-28T14:58:04Z",
"content": [{"type": "text", "text": "Fix the bug..."}]
},
{
"role": "assistant",
"timestamp": "2026-03-28T14:58:06Z",
"content": [
{"type": "text", "text": "Let me read the file first."},
{"type": "tool_use", "name": "Read", "input": {"file_path": "scripts/parser.py"}}
]
}
]
}