session-memory

Run maintenance on working memory. Consolidates old log entries, detects stale threads, identifies orphaned nodes, and reports on memory health. Run periodically to keep memory sharp and within limits.

Archive or remove a project node from working memory. Use when a project is complete, abandoned, or no longer relevant. Supports full removal, archival (compress to a single summary), or merging two nodes together.

Capture standalone knowledge without a full session commit. Use when you've discovered something worth remembering — a gotcha, a mental model, a technique — and want to commit it directly. Faster and more focused than /remember.

Quick one-liner capture to a project node. Lighter than /remember (no extraction process) and lighter than /learn (no knowledge typing). Just append a timestamped note to the changelog. Use for quick facts, status updates, or things worth noting that don't need structure.

Surface working memory into the current conversation. Run /recall [project] to load context for a specific project, or /recall alone to see a dashboard of your entire working world — all active nodes, open threads, and pending next actions at a glance.

Commit this conversation to working memory. Extracts knowledge, decisions, insights, open threads, and next actions — then writes a living summary and changelog entry for the detected project node. Run at the end of any conversation worth remembering.

Generate a synthesized weekly review of activity and learning across all projects. Produces a shareable summary covering what moved forward, what was learned, what's stuck, and what's coming up. Different from /timeline (raw chronology) — this is an analytical digest.

Search across all working memory for knowledge, decisions, people, or topics. Supports "how does X work", "what did we learn about Y", "when did we decide Z", "any gotchas with X", and "what's my P0 list". Returns matching entries from any node.

Show a chronological timeline of activity across all projects or a single project. Useful for reviewing what happened over a time period, preparing weekly updates, or understanding the arc of a project.

Run maintenance on working memory. Auto-fires when a user says "clean up memory", "memory is getting cluttered", "consolidate my logs", "what's stale", "memory health check", or "run maintenance". Also triggers on "I'm running out of memory space" or "too many old entries".

Archive or remove a project node from working memory. Auto-fires when a user says "archive [project]", "we're done with [project]", "close out [project]", "remove [project] from memory", "merge [project] into [other project]", or "this project is finished". Also triggers on "clean up old projects" or "I don't need [project] anymore".

Capture standalone knowledge without a full session commit. Auto-fires when user says "remember that X works like Y", "good to know that...", "TIL", "I just realized...", "note to self about [technical thing]", "the trick is...", "gotcha:", "watch out for...", "the way X works is...", or "I was wrong about X". Also fires when the user discovers something mid-conversation and it sounds like knowledge worth preserving (a gotcha, mental model, technique, or corrected assumption) but a full /remember would be overkill.

Quick one-liner capture. Auto-fires when a user says "note that [fact]", "jot down that...", "quick note:", "FYI for the record:", "just happened:", or any brief factual statement the user clearly wants persisted but doesn't warrant a full /remember or typed /learn entry. Also fires if the user says "log this" followed by a short statement.

Surface project memory and knowledge into the current conversation. Auto-fires when a user says /recall, "what do we know about [topic/project]", "remind me where we left off", "how does [thing] work", "any gotchas with [thing]", "what's the status of [project]", "catch me up on [project]", or starts a conversation assuming shared context. Also fires on "what have we learned about [topic]" or when a user references a project/topic and seems to expect prior knowledge.

Commit a conversation to working memory — extracts both project state and knowledge (insights, lessons, mental models, gotchas, recipes, corrections). Auto-fires when a user says /remember, "save this conversation", "commit this to memory", "log this session", or signals they're wrapping up. Also triggers if the user asks Claude to "remember" something specific about a project, decision, or piece of knowledge.

Generate a synthesized weekly review. Auto-fires when a user says "weekly review", "what did I accomplish this week", "summarize my week", "weekly roundup", "what happened this week", "prep my status update", or "end of week review". Also fires on "what have I learned recently" or "give me a digest of recent activity".

Search across all working memory for knowledge, decisions, people, or topics. Auto-fires when a user asks "how does [X] work", "any gotchas with [X]", "what did we learn about [topic]", "when did we decide [X]", "what's the trick for [X]", "have we seen this before", "what's blocked right now", "what are my P0s", or "did we ever figure out [X]". Also fires on "what do we know about [person/topic/technology]".

Show a chronological timeline of activity across all projects or a single project. Auto-fires when a user asks "what have I been working on", "show me last week", "what happened this month", "give me a timeline of [project]", "weekly review", "what did we do on [project] recently", or "show my activity". Also triggers on "prep my weekly update" or "what's the arc of [project]".