What problem does it solve? Repeated manual workflows and recurring friction across AI coding sessions go unnoticed, so users keep re-explaining the same processes instead of turning them into reusable skills, commands, or agent instructions. ## Core Features & Use Cases - Workflow Pattern Detection: Reviews recent sessions, project notes, and existing agent assets to find repeated friction with frequency, confidence, and impact scoring. - Session Archaeology Mode: Queries the OpenCode SQLite database directly to analyze historical sessions across all repos, with per-session summaries cached as JSON to save tokens. - Conservative Recommendations: Proposes the smallest useful improvement (prompt rule, skill, command, agent, config change, or playbook) and asks for approval before changing anything. - Use Case: Run /reflect --sessions --last 100 after weeks of coding to discover that you repeatedly grep for test files before editing, then get a concrete proposal for a reusable command that eliminates that friction. ## Quick Start Ask the agent to run /reflect --sessions to analyze your recent OpenCode sessions and suggest reusable workflow improvements.