agentleFS
Sign inStart free
enckequityenckequity/samebrain/skills/memory-gc/SKILL.md

memory-gc

Skill0 starsChanged 5 months agoMITView on GitHub

Compact the shared memory index when /memory-gc is invoked or the recall hook reports that memory/MEMORY.md exceeds its size cap.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. yangwhale/CloseCrab★ 5same name
    2. AlvaroBalbin/claude-memory★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are 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.

  • 2

    Very specific

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

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

    Keep {{REPO}}/memory/MEMORY.md cheap: it is injected into every session of every agent, so every line is a recurring token tax.

    line 8
  2. Very specific:

    Read {{REPO}}/memory/MEMORY.md and list the files in {{REPO}}/memory/topics/.

    line 16
  3. Distinctive:

    When adding a date, never invent one — only record a confirmation that actually happened.

    line 29

≈ “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

memory-gc

Keep {{REPO}}/memory/MEMORY.md cheap: it is injected into every session of every agent, so every line is a recurring token tax. Target: under 120 non-blank lines and 12KB, one line per fact. Detail belongs in memory/topics/ (which Hindsight ingests and bin/memory-search.mjs searches, when that optional backend is enabled).

Procedure

  1. Read {{REPO}}/memory/MEMORY.md and list the files in {{REPO}}/memory/topics/.
  2. Dedupe. Merge lines stating the same fact; keep the most recent, most specific wording.
  3. Roll up. Facts that are detail rather than index material move into the matching memory/topics/<topic>.md (create the topic file if needed), leaving at most a one-line pointer in the index.
  4. Prune by decay. Facts may carry a last-confirmed date — (confirmed: YYYY-MM-DD) — refreshed by any agent that re-verifies the fact. Delete facts that are stale, superseded, or machine-specific to a machine that no longer exists. Flag facts whose confirmed date (or, absent one, best-guess age) is past 90 days with (verify) rather than deleting outright; a fact still flagged on the next gc pass gets pruned. When adding a date, never invent one — only record a confirmation that actually happened.
  5. Show, don't commit. Present the resulting diff of MEMORY.md (and any topic files) for approval. Never commit or push the change yourself — the session-end sync hook commits memory once the user accepts the edit.

Hard rules: never invent facts; never delete the index wholesale; preserve the existing section structure; keep each fact to a single line.

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