context-switch — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited context-switch (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.
Quickly load context for a client or project. $ARGUMENTS should be the client or project name.
Use the LifeOS MCP tools:
If $ARGUMENTS looks like a client name:
If $ARGUMENTS looks like a project name/key:
get_belief_reframes with projectIds: [project._id] to load linked fears, inversions, and limiting-belief friction records.For graph context:
get_project_graph for project-centered context because it includes PPV relationships and belief_reframe friction nodes.falkor_graph_schema when the user specifically needs Falkor sidecar traversal or the Convex graph feels incomplete.falkor_graph_query to inspect related PPV pillars, projects, and agent-created links.falkor_graph_link only when you discover a durable relationship worth remembering and both endpoint nodes exist in Falkor; include reason and confidence.Present a quick context brief:
Keep it scannable - this is for fast context loading, not deep analysis.
If $ARGUMENTS is empty, ask which client or project to load.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.