agentleFS
Sign inStart free
mnemoversemnemoverse/claude-plugin/skills/memory-catch-up/SKILL.md

memory-catch-up

Skill0 starsChanged 37 days agoMITView on GitHub

Catches up after a break by listing what was added to long-term Mnemoverse memory since a given time, newest first, in personal memory or in a shared room (beta). Use when the user returns to a project and asks \"where were we\", \"what happened since\", \"catch me up\", or \"any new messages in the room\", or at the start of a session that continues earlier work.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Look for the tool memory_list_recent.

    line 10
  2. Distinctive:

    If nothing came back, say "nothing new since <time> in <scope>", not just "nothing new".

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Catch up on what changed

Check first

Look for the tool memory_list_recent. If it is missing, memory is not connected: say so in one sentence and use the bundled setup skill if it is installed, otherwise https://mnemoverse.com/docs/api/install-by-host.

Why a list, not a search

A search answers "what do I know about X". Catching up asks "what happened lately", and that needs the newest entries in order, without a query. memory_list_recent returns them newest first, and within one scope it skips nothing.

How to catch up

  1. Choose the scope. Personal memory needs no domain. A shared room (beta) is a separate store: pass its address as domain, or a room is never covered. If the room's address is not at hand, memory_list_rooms lists the rooms the user owns or has joined, with their addresses.
  2. Set the starting point. Pass since with the time the user last looked, as an ISO 8601 instant. If the user does not know, use the start of the last working day and say so.
  3. Read to the end. A page can be shorter than limit when entries are long, and then it returns a cursor. Follow the cursor until the page says the feed has ended ("end of feed"); a short page that still carries a cursor is not the end, and neither is a page that says more entries exist but shows no cursor: then narrow the window with since and until and list again. Stopping at the first page reads as "nothing else happened" when it did.
  4. Several scopes. For personal memory and a room (beta), run one listing per scope. They are not merged.

How to report

  • Lead with what needs the user: questions addressed to them, decisions waiting for them, anything with a date that has passed.
  • Then what was decided or changed, one line each, with who wrote it and when if that is recorded.
  • Say which scopes and which time window were read, so the user knows what the summary covers.
  • If nothing came back, say "nothing new since <time> in <scope>", not just "nothing new".

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free