memory-hygiene

aaaaqwq/claude-code-skills · updated Apr 8, 2026

$npx skills add https://github.com/aaaaqwq/claude-code-skills --skill memory-hygiene
0 commentsdiscussion
summary

Keep vector memory lean. Prevent token waste from junk memories.

skill.md

Memory Hygiene

Keep vector memory lean. Prevent token waste from junk memories.

Quick Commands

Audit: Check what's in memory

memory_recall query="*" limit=50

Wipe: Clear all vector memory

rm -rf ~/.clawdbot/memory/lancedb/

Then restart gateway: clawdbot gateway restart

Reseed: After wipe, store key facts from MEMORY.md

memory_store text="<fact>" category="preference|fact|decision" importance=0.9

Config: Disable Auto-Capture

The main source of junk is autoCapture: true. Disable it:

{
  "plugins": {
    "entries": {
      "memory-lancedb": {
        "config": {
          "autoCapture": false,
          "autoRecall": true
        }
      }
    }
  }
}

Use gateway action=config.patch to apply.

What to Store (Intentionally)

✅ Store:

  • User preferences (tools, workflows, communication style)
  • Key decisions (project choices, architecture)
  • Important facts (accounts, credentials locations, contacts)
  • Lessons learned

❌ Never store:

  • Heartbeat status ("HEARTBEAT_OK", "No new messages")
  • Transient info (current time, temp states)
  • Raw message logs (already in files)
  • OAuth URLs or tokens

Monthly Maintenance Cron

Set up a monthly wipe + reseed:

cron action=add job={
  "name": "memory-maintenance",
  "schedule": "0 4 1 * *",
  "text": "Monthly memory maintenance: 1) Wipe ~/.clawdbot/memory/lancedb/ 2) Parse MEMORY.md 3) Store key facts to fresh LanceDB 4) Report completion"
}

Storage Guidelines

When using memory_store:

  • Keep text concise (<100 words)
  • Use appropriate category
  • Set importance 0.7-1.0 for valuable info
  • One concept per memory entry

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.437 reviews
  • Aisha Menon· Dec 24, 2024

    Useful defaults in memory-hygiene — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Meera Kim· Dec 4, 2024

    memory-hygiene is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Chen Ramirez· Nov 27, 2024

    memory-hygiene reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Meera Li· Nov 23, 2024

    memory-hygiene fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Aisha Iyer· Nov 15, 2024

    memory-hygiene has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Advait Park· Oct 18, 2024

    Registry listing for memory-hygiene matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Yusuf Menon· Oct 14, 2024

    We added memory-hygiene from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Amelia Sanchez· Oct 6, 2024

    Solid pick for teams standardizing on skills: memory-hygiene is focused, and the summary matches what you get after install.

  • Daniel Gupta· Sep 25, 2024

    We added memory-hygiene from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Piyush G· Sep 1, 2024

    I recommend memory-hygiene for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

showing 1-10 of 37

1 / 4