Cairn Context Continuity-a66854 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Cairn Context Continuity-a66854 (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.
Use only the action the user requested. A mention in documentation, a quotation, or a question about Cairn is not a request to save, resume, or inspect context. One invocation does not enable automation for later turns. Do not call tools at startup, task completion, context thresholds, compaction, clearing, or a model/host switch. Do not add recurring reminders.
cairn-handoff to write and persist a 7-bucket brief with handoff.cairn-resume; decision_log view="current" restores prior state.cairn-help; explain commands without tool calls.context_status: pass the known model, tokenusage and surface cap. A yellow/red result is information, not permission to save a handoff.
host_status to inspect available host CLIs.Default account mode stores locally with no model call or egress. Optional bridge, sampling, and API modes need explicit configuration. No extra status calls are needed for handoff/resume.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.