Cairn Help-76ca20 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Cairn Help-76ca20 (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.
On an explicit help request, explain this short reference without calling MCP tools:
| Request | Action |
|---|---|
| Cairn Handoff | Save a 7-bucket brief locally with handoff. |
| Cairn resume | Restore the latest state with decision_log view="current" and continue. |
| Cairn Help | Explain these commands. |
| Explicit context/host status request | Inspect context_status / host_status. |
Claude Code supports /cairn-handoff, /cairn-resume, /cairn-help; Codex supports the corresponding $cairn-handoff, $cairn-resume, $cairn-help invocations. Shell commands: cairn status, cairn list, cairn window, cairn tab, cairn stop.
Cairn runs only on explicit requests. There are no automatic task/session, threshold, or compaction actions. Each invocation covers only that action; resume does not enable a later handoff. Passive status displays are informational. Account mode is local with no model call or egress through Cairn. Do not add a status check, handoff, or resume to a help response.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.