agentleFS
Sign inStart free
cukascukas/remembrall/skills/obliviate/SKILL.md

obliviate

Skill6 starsChanged 8 months agoMITView on GitHub

Guided pruning of stale memories with user confirmation

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Run the memory staleness analyzer:

    line 12
  2. Distinctive:

    Read the analysis report:

    line 21
  3. Distinctive:

    If the report exists, present findings to the user:

    line 27
  4. Very specific:

    Ask: "Would you like to archive these N stale memories?

    line 36
  5. Distinctive:

    If the user confirms:

    line 40
  6. Distinctive:

    If the user says no or wants to skip some:

    line 46

≈ “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

Obliviate — Guided Memory Pruning

You are running the Obliviate memory pruning skill. Follow these steps:

Step 1: Analyze

Run the memory staleness analyzer:

SESSION_ID="${CLAUDE_SESSION_ID:-default}"
echo "{\"session_id\":\"$SESSION_ID\",\"cwd\":\"$(pwd)\"}" | bash "$CLAUDE_PLUGIN_ROOT/hooks/obliviate-analyze.sh"

Step 2: Review

Read the analysis report:

REPORT="/tmp/remembrall-obliviate/${SESSION_ID}.json"

If the report exists, present findings to the user:

  • Total memories analyzed
  • Number flagged as stale
  • For each stale memory: filename, age, and reason

Step 3: Confirm

NEVER archive without explicit user confirmation.

Ask: "Would you like to archive these N stale memories? They'll be moved to .archive/ and can be restored later."

Step 4: Execute

If the user confirms:

bash "$CLAUDE_PLUGIN_ROOT/scripts/obliviate-archive.sh" "$SESSION_ID"

If the user says no or wants to skip some:

  • Respect their choice
  • They can run /obliviate again later

Notes

  • Archived memories go to memory/.archive/ — they are NOT deleted
  • The MEMORY.md index is updated automatically
  • Stale = not updated in more sessions than obliviate_stale_sessions (default: 5)
  • Pensieve activity is cross-referenced: if a TT agent recently accessed related files, the memory is NOT stale

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