exec-cockpit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited exec-cockpit (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.
Keeps a leadership role from crushing the person holding it. Four sub-deliverables — drafts only for anything external; the human sends (guardrail).
One page, agreed with the outgoing leader before they leave. Output: HTML styled with brand-assets/ (via tools/render_brand_html.py). Decision rights: what you decide alone vs. escalate (major spend, hiring/firing, board-level, anything structural).
Every thread the outgoing leader holds that could drop (key relationships, partner deals, board/investor threads). Status + next touch + owner. Refresh weekly.
Set the recurring update rhythm (e.g. weekly all-hands). Prep agenda + talking points so the team feels led; draft the async recap (internal send ok; nothing external without approval).
The periodic update you owe (board/investor/leadership). Pull live numbers at draft time; persist none to git; reproduce your branded layout. Draft only — never auto-send. See references/sops/wf-investor-update.md.
All of CLAUDE.md. Especially: no confidential figures in the repo, draft-never-send external, cite-don't-invent. Needs brand-assets/ filled for branded HTML output.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.