parallel — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited parallel (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.
Invoked via /parallel. Only use when tasks are genuinely independent. Never use for tasks that share state or need sequential ordering.
Orchestrator. Decomposes work into isolated units, delegates, collects results.
git worktree add .claude/parallel/agent-[n] -b lstack-parallel-[n]
.claude/parallel/agent-[n]/TASK.md — task description + relevant file list only
cd .claude/parallel/agent-[n] && claude -p --allowedTools Read,Write,Bash \ "$(cat TASK.md)" > result.md 2>&1 &
git worktree remove .claude/parallel/agent-[n] --force git branch -D lstack-parallel-[n]
Summary of all agent results, one section per agent. Flag any agent that failed or produced no output.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.