agent-team-orchestration — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited agent-team-orchestration (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
Production playbook for running multi-agent teams with clear roles, structured task flow, and quality gates.
A builder and a reviewer. The simplest useful team.
Orchestrator (you) — Route tasks, track state, report results
Builder agent — Execute work, produce artifacts1. Create task record (file, DB, or task board)
2. Spawn builder with:
- Task ID and description
- Output path for artifacts
- Handoff instructions (what to produce, where to put it)
3. On completion: review artifacts, mark done, reportBuilder produces artifact → Reviewer checks it → Orchestrator ships or returnsThat's the core loop. Everything below scales this pattern.
Every agent has one primary role. Overlap causes confusion.
| Role | Purpose | Model guidance |
|---|---|---|
| Orchestrator | Route work, track state, make priority calls | High-reasoning model (handles judgment) |
| Builder | Produce artifacts — code, docs, configs | Can use cost-effective models for mechanical work |
| Reviewer | Verify quality, push back on gaps | High-reasoning model (catches what builders miss) |
| Ops | Cron jobs, standups, health checks, dispatching | Cheapest model that's reliable |
→ Read [references/team-setup.md](references/team-setup.md) when defining a new team or adding agents.
Every task moves through a defined lifecycle:
Inbox → Assigned → In Progress → Review → Done | FailedRules:
→ Read [references/task-lifecycle.md](references/task-lifecycle.md) when designing task flows or debugging stuck tasks.
When work passes between agents, the handoff message includes:
Bad handoff: "Done, check the files." Good handoff: "Built auth module at `/shared/artifacts/auth/`. Run `npm test auth` to verify. Known issue: rate limiting not implemented yet. Next: reviewer checks error handling edge cases."
Cross-role reviews prevent quality drift:
Skip the review step and quality degrades within 3-5 tasks. Every time.
→ Read [references/communication.md](references/communication.md) when setting up agent communication channels. → Read [references/patterns.md](references/patterns.md) for proven multi-step workflows.
| File | Read when... |
|---|---|
| team-setup.md | Defining agents, roles, models, workspaces |
| task-lifecycle.md | Designing task states, transitions, comments |
| communication.md | Setting up async/sync communication, artifact paths |
| patterns.md | Implementing specific workflows (spec→build→test, parallel research, escalation) |
Agent produces great work, but you can't find it. Always specify the exact output path in the spawn prompt. Use a shared artifacts directory with predictable structure.
"It's a small change, skip review." Do this three times and you have compounding errors. Every artifact gets at least one set of eyes that didn't produce it.
Silent agents create coordination blind spots. Require comments at: start, blocker, handoff, completion. If an agent goes silent, assume it's stuck.
Assigning browser-based testing to an agent without browser access. Assigning image work to a text-only model. Check capabilities before routing.
The orchestrator routes and tracks — it doesn't build. The moment you start "just quickly doing this one thing," you've lost oversight of the rest of the team.
sessions_spawn directly. This skill is for sustained workflows with multiple handoffs.This skill is for sustained team workflows — recurring collaboration patterns where agents depend on each other's output over multiple tasks.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.