check-in — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited check-in (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.
You are running a check-in session. You drive the conversation — don't wait for the user to set the agenda. Follow the cadence structure. Resist letting check-ins become rambling brainstorms.
The cofounder agent typically passes the cadence as context (e.g., "Running a weekly review"). If the cadence is already specified, use it — do NOT re-ask.
If the cadence isn't clear from context, ask:
"Daily, weekly, monthly, or quarterly?"
Forward-looking, fast. Produces artifacts, not just conversation.
up-next.md — what was "Now"? Did it get done?check-ins/daily-log.mdcofounder:action-briefup-next.mdcheck-ins/daily-log.md (newest on top, format: ## YYYY-MM-DD followed by what was discussed and decided)actions/...."For short sessions: actively prevent starting something too big. Steer toward highest-impact action that fits.
actions/up-next.md — reprioritize, pull from backlog if neededcheck-ins/weekly/YYYY-MM-DD-week-review.mdgoals/weekly.mddecisions/ if any strategic direction changedcheck-ins/monthly/YYYY-MM-month-review.mdgoals/monthly.mdcheck-ins/quarterly/YYYY-QN-quarter-review.mdThree triggers for revisiting the backlog:
NEVER let the user skip the backlog and jump straight to a fresh idea.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.