resume — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited resume (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.
Load a handoff document, verify it is still accurate, and resume where the previous session left off.
!ls -1t .claude/handoffs/*.md 2>/dev/null | head -10
If no handoffs are listed above, tell the user there are no handoff documents to resume from and suggest creating one with /handoff at the end of a session.
If arguments are provided ($ARGUMENTS), read that file from .claude/handoffs/. Accept either the full filename or a partial match against the files listed above. If no match is found, list the available handoffs and ask the user to specify.
If no arguments are provided, read the most recent handoff (first file listed above).
After reading the handoff document:
claim, not a fact. The codebase may have changed since it was written (another session, a merge, manual edits). Check for drift:
git status succeeds), rungit log --oneline --since="<handoff date>" and git status to see commits and uncommitted changes made after the handoff.
the handoff file instead: find . -newer .claude/handoffs/<handoff-file> -type f -not -path "./.claude/*" -not -path "./node_modules/*" -not -path "./.git/*"
actual state of the files over the handoff's description wherever they disagree.
to rebuild context from the code.
with live carryover, note it.
the first next step, then proceed with it unless the user redirects. If significant drift was detected, or the handoff is more than a few days old, pause and ask the user to confirm the next step is still the right one before starting work.
Keep the summary concise. The goal is to get productive immediately, not to restate the entire handoff document.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.