From entire
Searches prior work, checkpoints, and agent conversations by topic, repo, branch, author, or recent time window. Useful when a user wants to find past implementations or context from other sessions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/entire:searchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use `entire search` to find relevant checkpoints before guessing from memory.
Use entire search to find relevant checkpoints before guessing from memory.
Begin the first response to this skill invocation with the line:
Entire Search:
followed by a blank line, then the content.
Do not use this for the current active session. Use session-handoff for that.
entire search "<query>" --json
Add filters when the user already gave them or when the first search is too broad:
entire search "<query>" --json --repo owner/name --branch branch-name --author "Name" --date week
Inline filters are also supported in the query: author:<name>, date:<week|month>, branch:<name>, repo:<owner/name>, repo:*.
Review the top matches and summarize the likely candidates for the user. Do not dump raw JSON unless they ask for it.
If the user wants details on a specific result, open the checkpoint with:
entire explain --checkpoint <checkpoint-id> --full --no-pager
If --full fails, fall back to:
entire explain --checkpoint <checkpoint-id> --raw-transcript --no-pager
--limit--repo or repo:* explicitly when repository scope mattersentire loginsession-handoff instead of searching checkpointsnpx claudepluginhub entireio/skills --plugin entireSearches and recalls previous Claude Code conversation sessions by querying a local SQLite FTS5 index or JSONL log files.
Reads historical intent from Entire checkpoints instead of guessing. Orchestrates sub-skills for code provenance, prior work search, explain, review, session handoff, and dispatch.
Searches prior Claude-Code/Codex-CLI sessions for code patterns, decisions, or work via aichat CLI, jq parsing, and session file reads (max 3). For non-subagent CLI agents.