note-taker — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited note-taker (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this skill when a task has enough moving parts that losing intermediate facts, decisions, files, or TODOs would make later steps less reliable.
The bundled script is scripts/notes.py, relative to this SKILL.md. Run it with Python 3.
python <skill-dir>/scripts/notes.py resumeNOTES.md: mutable working understanding, findings, decisions, relevant files, open questions, and corrected assumptions.TODO.md: mutable task tracking with current, blocked, and done sections.NOTES.md and TODO.md directly when the task state changes. Keep both files compact and accurate. Replace stale notes instead of accumulating contradictions.resume again and/or use rg over the session files.python <skill-dir>/scripts/notes.py init
python <skill-dir>/scripts/notes.py where
python <skill-dir>/scripts/notes.py resume
python <skill-dir>/scripts/notes.py search "query"
python <skill-dir>/scripts/notes.py gcSession resolution is strict. The script uses NOTE_TAKER_SESSION_ID first, then CODEX_THREAD_ID. If neither exists, set NOTE_TAKER_SESSION_ID before using the skill.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.