context-memory-hygiene
100 / 100 · Low risk
Fine to try.
Invoke when deciding what to load into context, what to persist across turns or sessions, and what to drop — reads only what the task needs, writes durable handoffs, avoids context pollution, and chooses when to re-derive versus recall.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'context-memory-hygiene' ] || [ -L ~/.agents/skills/'context-memory-hygiene' ]; then echo 'A skill folder named context-memory-hygiene already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/rlaope/ultraprompt' "$d" && git -C "$d" checkout --quiet 'febbc08111b85bb31834218dce5361a4babbc696' -- 'skills/context-memory-hygiene' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/context-memory-hygiene' ~/.agents/skills/'context-memory-hygiene' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'context-memory-hygiene' ~/.claude/skills/'context-memory-hygiene' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/rlaope/ultraprompt/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | febbc08 | 100 |