sessions

Load a context primer for the current repo before starting work. Use when the user says "what was I doing here", "catch me up on this repo", "context primer", "what's the open thread", "where did I/we leave off" — and PROACTIVELY when a session opens on work that clearly continues something ("keep going on the refactor", "finish the migration") or when resuming a codebase after a break. Past sessions carry the open thread, prior decisions, and abandoned approaches that code and git history don't show.

Triage context-memory candidates mined from past AI coding sessions. Use when the user says "triage memory", "review memory", "mine memory", "/memory", or asks what durable facts their session history contains. Runs the mine, clusters paraphrased candidates, judges which facts generalize beyond the session they came from, and walks approve / reject / snooze, including marking standing constraints always-on and assigning project groups.

Recall what was done on a specific project or topic from past AI coding sessions. Use when the user says "what did I do on [project]", "recall [topic]", "history of [project]", "when did I last work on [thing]" — but also when they reference prior work without asking for history explicitly: "didn't we already fix this", "what was that approach we tried", "why did we do it this way", "what happened to [file/feature]". Use PROACTIVELY before re-deriving a decision or re-solving a problem a past session likely settled — past conversations hold rationale and dead ends that never made it into git.

Show usage metrics and analytics for AI coding sessions. Use when the user asks "how much have I been coding", "session stats", "show me metrics", "tool usage", "which tool do I use most", "active hours", or wants analytics about their AI coding tool usage.

Reflect on how you work with AI coding agents using sessions history. Use when the user says "reflect on my workflow", "why do I keep correcting the agent", or asks about prompting habits, supervision, workflow friction, or what makes delegation succeed. Produces sourced observations and experiments, not an activity recap or automatic memory updates.

Generate a quick standup summary of yesterday and today's AI coding sessions. Use when the user says "standup", "what did I do yesterday", "daily summary", "what have I been working on", or needs a quick recap for a standup meeting.

Generate a comprehensive summary of AI coding sessions from the past week. Use when the user says "weekly summary", "what did I do this week", "summarize my week", "weekly recap", "week in review", or asks for a summary of recent work across projects.

Explain why a piece of code exists by correlating it to the AI coding sessions behind it. Use when the user asks "why does this exist", "why did we write it this way", "what was the reasoning behind this line/file/commit", "who changed this and why", or points at a file, line, or commit and wants the rationale that git alone does not carry. Use PROACTIVELY before rewriting or removing code whose purpose is unclear — the deciding conversation may still be recoverable.