Agent skill · daymade
read-claude-code-history
Reads, searches and exports local Claude Code and Kimi CLI history without resuming work: timelines, verbatim user input, keyword or fuzzy recall, file recovery from transcripts, and which session ran a given command in a known time window. Use when the user asks what was said, wants a session ID or original context, needs proof of what a session contained, or needs past-session runtime evidence about commands, tool calls and hook runs — query this index instead of raw-scanning transcript files. Not for Codex (use read-codex-history); with no platform or several named, start at local-conversation-history.
What it needs
About 11k tokens when loaded.
What this skill does
Read Claude Code History Read Claude Code evidence only. Do not resume the old process, edit its project, or turn a read request into a continuation task. When the user later asks to act, hand the verified evidence to daymade-claude-code:continue-claude-code-work. Route by the requested result User wants Use --- --- Recent Claude Code sessions, titles, dates, or IDs Indexed metadata only; the bundled listlocalhistory.py currently reads all candidate bodies before date/limit filtering, so do not use it for a broad inventory One known Session reconstructed as a chronological evidence briefing scripts/readclaudesession.py --session <ID> Original tool input and paired result from one exact Session, selected by tool name, literal text, ordinal or time scripts/readclaudesession.py --session <ID> --tool-evidence --contains '<literal>'; see Original tool call/result evidence below The exact command behind a hook audit row that records a Session ID and a command SHA-256 instead of the text scripts/readclaudesession.py --session <ID> --find-command-sha256 <HEX>; see Command behind a hook audit row below Every Agent/Task tooluse in one Session, quoted verbatim (e.g. the exact prompt handed to an independent reviewer agent) scripts/readclaudesession.py --session <ID> --agent-prompts (optionally --agent-description-prefix TEXT); a prompt dispatched twice is listed twice Which session launched a program in a known time window, across sessions scripts/analyzesessions.py tool-calls --from <ISO> --to <ISO> --pattern <REGEX> [--tool NAME]; candidates are selected by filesystem metadata before any body is read, then grouped by session; Codex rollouts are out of scope and the gap is stated in the output When hook runs happened across sessions — outcome, duration, exit code per run (e.g. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills daymade/read-claude-code-history