agentleFS
TheElephantCoderTheElephantCoder/agent-harness/skills/memory-sync/SKILL.md

memory-sync

Skill3 starsChanged 53 days agoMITView on GitHub

Keep memory warm and small. Hydrate at start, append notes at end.

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. ramboz/jig★ 7same name
    2. TransitionMatrix/godot-dap-mcp-server★ 4same 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 repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 3

    Very specific

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

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

    Start: read MEMORY.md and tiers/hot.md.

    line 35
  2. Very specific:

    End: run harness memory sync "..." with what you learned (it appends + re-prunes to budget).

    line 37
  3. Very specific:

    If you considered 2+ approaches and picked one, write a short decisions/ADR-###.md.

    line 42
  4. Distinctive:

    No secrets in memory, it gets redacted anyway.

    line 43

≈ “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 sync

Keeps sessions from starting cold.

Layout

memory/
  MEMORY.md        # curated, always loaded, keep under 2k
  SOUL.md          # who the agent is
  USER.md          # who you are
  sessions/        # raw per-session notes, cleaned up after ~30d
  decisions/       # short ADRs
  tiers/
    hot.md         # always loaded
    warm.md        # loaded on keyword
    cold/          # explicit read only

Lifecycle

Start: read MEMORY.md and tiers/hot.md. Maybe warm.md if the task matches. Don't read sessions/ unless you're digging into history. Should be under 15s total.

End: run harness memory sync "..." with what you learned (it appends + re-prunes to budget).

Tips

  • MEMORY.md is curated, not append only. Keep it under 2k tokens, edit surgically.
  • If you considered 2+ approaches and picked one, write a short decisions/ADR-###.md.
  • No secrets in memory, it gets redacted anyway.

Commands:

harness memory show
harness memory edit
harness memory prune
harness memory sync "note"

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.