Displays summaries of recent Claude Code sessions including timestamps, durations, edited files, token usage, and waste percentages for quick context recovery. Useful after restarting sessions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-context-optimizer:cco-replay [N] (number of sessions to show, default 5)[N] (number of sessions to show, default 5)This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Show the user summaries of their recent sessions so they can quickly recover context.
Show the user summaries of their recent sessions so they can quickly recover context.
Parse $ARGUMENTS for the number of sessions to show (default: 5).
Run:
node ${CLAUDE_PLUGIN_ROOT}/src/replay.js $ARGUMENTS
Present the output to the user. It shows recent session summaries including:
If no summaries exist yet, tell the user: "No session summaries yet. They're generated automatically at the end of each session — just keep working!"
npx claudepluginhub egorfedorov/claude-context-optimizer --plugin claude-context-optimizerShow recent Claude Code sessions across all projects, so the user can re-enter work after a reboot or context switch. Lists per session the absolute project path, a short summary, last activity, turn count, git branch, model, and a ready-to-paste resume command, and can re-open all of them at once in new terminal tabs. Use when the user asks "what was I working on", "which projects did I touch recently", "where did I leave off", "list my recent sessions", "how do I get back into that session", "open all my sessions again", or invokes /recap. Reads only local files; the default run is instant and offline.
Query Claude Code session history for IDs, durations, tokens consumed, tool usage patterns, errors, permissions, and search past conversations by keyword or project. Use for usage introspection like 'tokens today' or 'find setup X'.
Analyzes Claude Code sessions in three modes: Handoff Document (exhaustive context extraction), Error Forensics (complete error/warning inventory), and Chronological Summary (dense technical timeline).