review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited review (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.
Unified review. The integration that no other skill pack ships.
When you run /review on a diff, it scans every file:
One report. Both lanes. The thing teams actually need.
Run /review when:
# review the working directory
node ~/.claude/skills/dragoon/skills/review/scripts/review.js
# review only changed files in git
node ~/.claude/skills/dragoon/skills/review/scripts/review.js --diff
# review a specific file or folder
node ~/.claude/skills/dragoon/skills/review/scripts/review.js src/Card.tsx
# CI gate: fail if design score < 80 or any high-severity findings
node ~/.claude/skills/dragoon/skills/review/scripts/review.js --diff --threshold 80Flags:
--diff only review files in git diff (uses git diff --name-only HEAD)--manifest <p> use a specific manifest--json machine-readable--threshold <n> CI gate--no-design skip design critique (slop only)--no-slop skip slop (critique only)--help full usage0 clean (or threshold met)1 high-severity findings, or threshold not met2 bad usageEngineering signals:
eng-001 unresolved TODO / FIXME / HACK / XXX markerseng-002 use of any type in TypeScripteng-003 files over 600 linesDesign signals: all 12 slop rules. See node ~/.claude/skills/dragoon/skills/slop/scripts/slop.js --rules.
Design quality: full /critique scoring on the project's manifest.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.