self-healer — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited self-healer (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.
Dieser Skill wird automatisch vom macOS Background Watcher ausgelöst, wenn ein SIN-Solver Mikro-Schritt fehlschlägt und eine healing_request.txt generiert wurde.
healing_request.processing.txt im aktuellen Verzeichnis. Sie enthält den fehlgeschlagenen Schritt, den Stacktrace und den PFAD ZUM SCREENSHOT (SCREENSHOT_PATH).look_at um dir den Screenshot unter SCREENSHOT_PATH anzusehen! Du MUSST sehen, wie der Browser im Moment des Fehlers aussah.step_XX.py).nodriver auf Port 9222 nutzen.healing_request.processing.txt nach erfolgreichem Fix.rm -rf ~/.local/share/opencode/tool-output/* (Riesige Log-Buffer)rm -f /tmp/m*_RESULT.png (Alte Debug-Screenshots)rm -rf ~/.npm/_cacache (Node.js Ballast)rm -f ~/.local/share/opencode/log/*.log (Alte Runner-Logs)~/.local/share/opencode/sessions), Kontexte, Memory-Daten oder Auth-Profile!~/dev/docs/sin-solver/repair-docs.md ein.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.