Lesson 06 · OpenClaw, Safely Pro ~11 min 4 starter workflows

Your first real workflows: briefing, triage, watchers.

A safe agent that does nothing useful is a smoke detector with no kitchen. These four starters were chosen on two criteria: they deliver real daily value, and every one stays inside the rails you built in Lessons 3–5. Notice what's not here — nothing that needs your passwords, your main inbox, or marketplace skills.

The four starters

Real value, all read-and-report.

Tap each to see how you'd ask for it — in plain English — and the one safety rule baked in.

Do it · what's a starter, what must wait

Read-and-report now, or earn write access first?

The thread through all four starters: the agent reads and reports, it doesn't act on your behalf. An agent earns write access the way a new hire does — weeks of clean, observable work first. Sort each task.

Sort each task0 / 5
Do it · the watcher's discipline

Ping me, or stay silent?

A good watcher messages you only when something changed — that's the line between an assistant and a notification problem. But it should still surface failures. For each daily check, what should the agent do?

👁 Daily watcher0 / 3
The earn-it rule

All four starters let the agent do nothing irreversible — no sending mail to others, no spending, no posting, no files outside its workspace. That's deliberate. Write access to your life is earned one scope at a time, after the read-only phase proves boringly reliable. Lesson 8 covers exactly how to grant it.

The cost check-in

Four daily workflows on a mid-tier model typically lands around $5–15/month, depending on how chatty your briefings are. Check the usage dashboard after week one — the briefing word limits and "stay silent" rules are the dials that move the bill.

Build two this week

The morning briefing plus one watcher is the perfect starter pair — one scheduled push, one quiet monitor. Run them a full week. When both have been boringly reliable for seven days, you've earned the next power-up: skills. Which is also where the danger comes back — so don't skip the vetting lesson.

What you can do now

  • Set up a scheduled morning briefing with failure-reporting built in
  • Run email triage on a dedicated, forward-fed inbox — read-and-report only, never clicking links
  • Deploy watchers that alert on change and stay silent otherwise
  • Fire off research errands as proper briefs from anywhere
  • Explain why all starter workflows are read-only — and what an agent must do to earn write access
  • Estimate and tune your monthly model spend
Pro
Up next in OpenClaw, Safely

Lesson 07 · Skills: the app store with a malware problem

ClawHub has thousands of skills — and an audit found roughly a third with prompt-injection content. The vetting checklist, and why the safest skill is the one you write yourself. Start lesson 07 →

🎓
AI Coach
Ask anything about this lesson
Hey! I'm your AI Coach for this lesson. Ask me anything about the starter workflows — the briefing, triage, watchers, research errands, or why they're all read-only. What's on your mind?
Free lesson coaching is limited to 3 questions. Upgrade to Pro for unlimited coaching on every lesson.