mk:team-config — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mk:team-config (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.
Sets up the infrastructure for parallel agent execution. Called by orchestrator when a COMPLEX task is decomposed into independent subtasks.
session-state/task-queue.json with claiming protocolPlan approved (Gate 1)
↓
Orchestrator identifies parallel opportunity
↓
mk:team-config
├── 1. Parse plan for independent subtasks
├── 2. Generate ownership map (which agent owns which files)
├── 3. Validate zero overlap between ownerships
├── 4. Create git worktrees via mk:worktree
└── 5. Create task-queue.json via mk:task-queue
↓
Parallel agents start claiming tasksWhen team mode activates, Read references/team-coordination.md — the team-only coordination rules (file ownership per task, no force-push, worktree-branch commits, actionable completion messages, lead docs-impact ownership). These were moved out of always-loaded parallel-execution-rules.md so they load only on team activation.
See templates/ownership-map-template.md for the format agents use to declare file ownership.
parallel-execution-rules.md): (e.g., mk:review) need quoting in shell pathsgit worktree list to check for orphaned worktrees before creating new onesAfter all parallel agents complete and integration test passes:
mk:worktree cleanupsession-state/task-queue.json~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.