agentleFS
Sign inStart free
TheKontextCoTheKontextCo/kontext-claude-plugin/skills/kontext-memory/SKILL.md

kontext-memory

Skill1 starsChanged 3 months agoMITView on GitHub

Capture durable facts, decisions, and observations into Kontext as memories. Trigger when the user says to remember or save something, shares a fact with future value (a preference, price, deadline, credential-free detail), or asks what Kontext remembers. Do not trigger for secrets, incidental chat, or throwaway details.

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:

    Call save_to_kontext with a concise derived title when none is supplied.

    line 29
  2. Distinctive:

    After saving, return the tool's Markdown title link so the user can open the record in the Kontext Library.

    line 42

≈ “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

Kontext memory capture

save_to_kontext is the frictionless capture path: it stores a standalone document with kind: "memory" without forcing the user to pick a project first.

What to save

  • Facts with future value: decisions, preferences, constraints, prices, deadlines, links, names of things that recur.
  • The user explicitly says "save this", "remember this", or similar.
  • Observations worth keeping from the current conversation that will matter in another one.

What not to save

  • Passwords, verification codes, tokens, private keys, or any secret.
  • Incidental personal details without an explicit request.
  • Things already recorded — search first with search_context, and update the existing record instead of duplicating.

How to save

  • Call save_to_kontext with a concise derived title when none is supplied.
  • Include a source URL when the memory came from the web or a document.
  • Set an expiry timestamp when the memory is only valid until a date (a ticket price, a temporary state).
  • Supplying projectId is optional; memories can be organized later.

Recalling

  • For "what do you remember about X", use search_context first, then read_document on the best hit.
  • Memories appear in normal context/list/read tools; no special invocation is needed.

After saving, return the tool's Markdown title link so the user can open the record in the Kontext Library.

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