Agent Memory skill
SaferSkills independently audited agent-memory (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.
Purpose: This repository provides a reliable way to keep track of long‑running work and the decisions behind it.
This repository implements:
The system behaves as a state machine over repository files.
No host discovery. No silent repair. No implicit authority.
Run:
python bootstrap.py
Expected output:
{"message": "bootstrap complete", "stage": "bootstrap", "status": "ok"}
If bootstrap fails:
Do not modify files.
Follow:
references/RECOVERY.md
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.