ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

supervising-agents

Use when YOU are dispatching tasks to subagents (Agent tool, openclaw, parallel workers). You become the supervisor by default. This skill guides how to monitor, intervene, and verify your subagents.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/allenclove/supervising-agents
Or

Supervising Agents

Core Principle

The dispatcher IS the supervisor. When you dispatch a task, you own the outcome.

YOU dispatch → YOU monitor → YOU verify → YOU report

If the subagent fails, YOU are responsible for catching it.
If you don't verify, YOU are responsible for the bad output.

Part 1: The 5-Phase Workflow

PREPARE ──► DISPATCH ──► MONITOR ──► VERIFY ──► REPORT
    │           │           │           │          │
    ▼           ▼           ▼           ▼          ▼
 Define      Lock in     Active      Evidence    To human
 clearly    commitment   checking    required   accountable

Part 2: PREPARE Phase

Pre-Dispatch Checklist (MUST COMPLETE)

□ TASK DEFINED
  Goal (one sentence): _______________________________
  Requirements (list ALL): _______________________________
  Deliverables (specific files): _______________________________

□ TIME SET
  Budget: _____ minutes
  Check interval: _____ minutes (rule: budget/5, min 3 min)

□ VERIFICATION PLANNED
  How to check output exists: _______________________________
  How to verify correctness: _______________________________

□ RED FLAGS DEFINED
  What "going wrong" looks like: _______________________________

Decision: Should You Dispatch?

ConditionDecision
Task is trivial (< 5 min)Do it yourself
Task requires judgment you don't haveAsk human first
Task has clear requirements and deliverables✓ Dispatch with supervision

Part 3: DISPATCH Phase

Dispatch Prompt Template

TASK: [One sentence - what success looks like]

REQUIREMENTS (complete ALL):
1. [requirement 1]
2. [requirement 2]
3. [requirement 3]

DELIVERABLES:
- [file 1] - [expected content]
- [file 2] - [expected content]

TIME: [X] minutes

─── BEFORE YOU START ───
Reply to confirm:
1. What is the goal? (your words)
2. What steps will you take?
3. How will you know you're done?

Do NOT start until you confirm.

After Dispatch: Record Agent ID

// Agent tool returns: agentId: 'abc123'
// SAVE THIS - you need it for SendMessage

const agentId = 'abc123';  // Keep track of this

Part 4: MONITOR Phase (CRITICAL)

The #1 Mistake: Passive Waiting

❌ WRONG: Dispatch → Wait → Check at end
✓ RIGHT: Dispatch → Active monitor → Intervene early

Active Monitoring Techniques

Technique 1: Output File Watching

# Check if output files exist
ls -la [expected output directory]

# Check file sizes (should be > 0)
wc -l [expected files]

# Check modification times
find . -name "*.md" -mmin -5  # Files modified in last 5 min

If no output after 1 check interval → INTERVENE NOW

Technique 2: SendMessage Probe

Metadata

Stars4473
Views2
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-allenclove-supervising-agents": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.