client-brief — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited client-brief (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.
Get a full client briefing. $ARGUMENTS should be the client name or ID.
Use the LifeOS MCP tools:
get_belief_reframes with projectIds: [project._id] to surface linked fears, inversions, and limiting-belief friction records.get_project_graph for the relevant project because it includes PPV context and belief_reframe friction nodes. Use FalkorDB only for sidecar traversal or agent-owned relationship links.For each active project, also call get_phases to see phase breakdown.
Use falkor_graph_link only when you find a durable PPV/project relationship that should be remembered but should not mutate Convex canonical records. Always include reason and confidence.
Present as a client brief:
If no client is specified in $ARGUMENTS, list all active clients and ask which one.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.