claude-history
Skill9 starsChanged 9 months agoMITView on GitHub
Claude CLIの過去の会話を検索・以前話した内容を調べる・search_sessions.pyを使う・rate_limit後に記憶を復元する・restore_session_memory.pyを使う → このスキルを読む
1 other project uses a version of this.
Adopted by
Most recently taken up by
- raine/claude-historytheir own version, first seen Oct 17, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- raine/claude-history★ 538same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .claude/skills/latest-apis/CLAUDE.mdCLAUDE.md
- ayumu-emailSkill
- browserSkill
- calendarSkill
- cameraSkill
- creationSkill
- discordSkill
- feedsSkill
- identitySkill
- latest-apisSkill
- lifeSkill
- maintenanceSkill
- project-structureSkill
- readingSkill
- recallSkill
- security-reviewSkill
- smart-homeSkill
- speakSkill
- twitterSkill
- voice-chatSkill
- websiteSkill
The file
Files
Session スキル
Claude CLIの会話履歴とセッション管理。
関連スキル
/recall- 記憶システム全般の検索
1. セッション検索(search_sessions.py)
基本検索
# テキスト検索
uv run tools/search_sessions.py "検索ワード"
# コンテキスト付き(前後3件表示)
uv run tools/search_sessions.py "検索ワード" -C 3
# 今日の会話
uv run tools/search_sessions.py --today --current
# 統計情報
uv run tools/search_sessions.py --stats高度な検索
# 日付範囲
uv run tools/search_sessions.py "キーワード" --after 2026-01-25
# ツール使用箇所を検索
uv run tools/search_sessions.py --tool Edit --current -C 3 --show-tools
# 正規表現
uv run tools/search_sessions.py "パターン" --regex
# 特定セッションを表示
uv run tools/search_sessions.py --session-id <セッションID>2. セッションデータの保存場所
メイン会話履歴(完全版)
~/.claude/projects/<project-path>/<session-id>.jsonlサブエージェント履歴
~/.claude/projects/<project-path>/<session-id>/subagents/*.jsonl簡易履歴(全セッション要約)
~/.claude/history.jsonl3. 記憶復元(restore_session_memory.py)
rate_limitエラー後に記憶が飛んだ場合:
# compact以降の全会話を表示
uv run .claude/skills/claude-history/restore_session_memory.py --from-compact
# 最後のN件だけ
uv run .claude/skills/claude-history/restore_session_memory.py --last 100
# 全メッセージ
uv run .claude/skills/claude-history/restore_session_memory.py --all出力をClaudeに読ませることで記憶を復元。
4. トラブルシューティング
問題: rate_limitエラー後に記憶がない
解決: restore_session_memory.py で復元
5. 便利なコマンド
# 最近のセッション一覧
jq -r '[.sessionId, .timestamp] | @tsv' ~/.claude/history.jsonl | sort -k2 -r | head -20
# 特定セッションの最初のメッセージ
head -1 ~/.claude/projects/<path>/<id>.jsonl | jq -r '.snapshot.text'
# compact境界の検出
grep -n "This session is being continued" <session-file>.jsonl関連ファイル
tools/search_sessions.py- 検索ツール.claude/skills/claude-history/restore_session_memory.py- 記憶復元ツール
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

