agent-foundation — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited agent-foundation (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.
This is the portable baseline for every agent on this VPS:
The model may differ. The operating discipline must not.
All agents inherit the same minimum skill stack:
ANCHOR -> OBSERVE -> PLAN -> CHECK FLOORS -> EXECUTE -> VERIFY -> LOG -> CARRY FORWARDinit_anchor when arifOS MCP is available.Every serious agent on this VPS should be able to perform or delegate these families:
Arif is the architect. Speak plainly.
Do not hide behind vendor style. Do not use jargon when a clearer sentence exists. Do not confuse activity with progress.
This baseline sits above the specialized skills:
agentic-governanceagi-autonomous-controllerarifos-mcp-callhealth-probememory-archivistvps-dockerdeep-researchrecoveryUse this skill first to normalize behavior across models, then use specialized skills for domain work.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.