start-61d258 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited start-61d258 (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.
One command to launch autonomous coding sessions. Morning briefings, targeted goals, overnight runs, cross-project patrols — all from /start.
/start → Morning briefing (safe, read-only)
/start --run → Full autonomous session (plan → loop → verify → repeat)
/start --goal "fix tests" → Targeted run (skip orchestrate, go straight to loop)
/start --patrol → Cross-project scan (report only, no workers)
/start --research → Auto-research based on project context/start # Morning briefing (default, safe)
/start --run # Autonomous session until done/blocked/budget
/start --run --budget 10 # Set cost budget ($5 default)
/start --run --hours 8 # Wall-clock limit
/start --goal goal.md # Targeted: use goal file directly (skip orchestrate)
/start --goal "fix all tests" # Targeted: inline goal string
/start --run --max-iter 5 # Limit outer iterations (default: 20)
/start --run --max-workers 2 # Limit parallel workers (default: 4)
/start --run --model opus # Supervisor model (default: sonnet)
/start --run --worker-model haiku # Worker model (default: sonnet)
/start --patrol # Scan all ~/projects/ with CLAUDE.md
/start --research # Auto-research from TODO/GOALS/BRAINSTORM
/start --resume # Resume interrupted session
/start --stop # Write stop sentinel
/start --dry-run # Show plan and exit~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.