Collective intelligence runtime for AI agents. Knowledge graph + persistent memory.
SaferSkills independently audited sibyl (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 stub points at the version-matched workflow shipped by the installed CLI.
Load the core pack before knowledge work:
sibyl skill get coreYou get the full recall -> act -> remember -> reflect loop, every CLI verb with the flags that actually exist on this machine, context pack usage, error patterns to avoid, and lock-conflict handling. Don't guess the verbs from training data; the CLI schema changes between releases.
Quick triggers (intent -> verb):
sibyl task list --status doing,blockedsibyl recall "<goal>"sibyl search "<topic>"sibyl remember "<title>" "<body>"sibyl reflect "<notes>" --persistLive status: sibyl context shows project link and auth; sibyl health shows server reachability.
Useful follow-ups:
sibyl skill list
sibyl skill get workflows
sibyl skill get examplesHooks are separate from skills. Install or update hooks only when the user explicitly wants automatic prompt/session integration.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.