agentleFS
cristobaltormocristobaltormo/cortex-md/skills/remember/SKILL.md

remember

Skill1 starsChanged 4 days agoMITView on GitHub

Save something to the brain right now. Use it when the user says "remember this", "note this down", "don't forget", "keep it for next time", or asks to see or correct what is already remembered.

70 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-context-isolation, agentica-infrastructure and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 62 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Before creating a note, grep memory/ in case one exists that should be updated.

    line 18
  2. Very specific:

    Write the note with complete frontmatter (verified set to today, status: current), add the line to the index of its area …

    line 20
  3. Very specific:

    Run bin/health.py to make sure the index is not out of step and no link is broken.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 62 edited versions of this file we could read. “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

Remember

The user wants something to survive this conversation. Do it before moving on: if the session is cut, it is lost.

If asked to save something

  1. Decide where it goes, using the rules of the memory-keeping skill:
    • a fact, a decision or a preference: a note in memory/
    • a repeatable procedure: a new skill in skills/
    • something half done or waiting for their decision: a line in PENDING.md
    • something the machine already knows (addresses, RAM, ports): do not save it, it is in inventory/
  2. Before creating a note, grep memory/ in case one exists that should be updated. Two notes that contradict each other are worse than one outdated note.
  3. Write the note with complete frontmatter (verified set to today, status: current), add the line to the index of its area (memory/index-*.md, never MEMORY.md), and link it from related notes with [[name]].
  4. Run bin/health.py to make sure the index is not out of step and no link is broken.
  5. Confirm in one line what was saved and where. Do not show the whole file.

If asked what is remembered

grep -i "<topic>" memory/index-*.md
grep -ril "<topic>" memory/

Summarise what you find in your own words; do not dump raw markdown.

If told that something remembered is wrong

Fix it at once. Edit the existing note (do not create a second one), move the old content to a ## Before section if it deserves keeping, and set verified to today. Having been corrected is the strongest sign that this had to be stored properly.

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.