agentleFS
t1mericksont1merickson/skills/cut-memory/SKILL.md

cut-memory

Skill1 starsChanged 2 months agoMITView on GitHub

Audit Claude's project-scoped memory, preserve the few non-reconstructable facts, and quarantine redundant or stale entries with an auditable undo.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Use this skill only when invoked.

    line 8
  2. Very specific:

    Read MEMORY.md and every file it references.

    line 14
  3. Distinctive:

    Verify the supposed duplicate or stale source before classifying it.

    line 26

≈ “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

Cut memory

Use this skill only when invoked. Treat memory skeptically, not as disposable: its job is to preserve behavior-changing facts that are neither durable elsewhere nor cheaply reconstructable.

Claude project memory normally lives under ~/.claude/projects/<encoded-cwd>/memory/. Confirm the active location and schema before operating; host layouts drift.

Inventory

Read MEMORY.md and every file it references. Record file count, total bytes, inbound links, and any unindexed files. Do not inspect another project's memory merely because it is adjacent on disk.

Classify

A memory earns retention only when all three hold:

  1. It changes future behavior or prevents a likely mistake.
  2. The fact is absent from project instructions, code, durable docs, skills, and agent configuration.
  3. Reconstructing it is meaningfully harder than reading one file or running one command.

Typical cuts are task reports, duplicated project facts, stale tool state, motives already preserved beside a rule, and command-derived inventories. Typical keeps are silent runtime traps, user context with no appropriate durable home, and facts whose default inference would be confidently wrong.

Verify the supposed duplicate or stale source before classifying it. Do not move global preferences into another agent's configuration as a side effect; report the routing question instead.

Apply reversibly

Move cut files to a dated sibling quarantine. Write a manifest containing original path, quarantine path, size, reason, and the durable source that supersedes it. Rebuild MEMORY.md with one concise pointer per survivor; do not summarize removed material back into the index.

Report before/after file and byte counts, every classification, the quarantine path, and the exact undo. Cutting nothing—or cutting everything—is valid when the evidence supports it.

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.