agent-supervisor

Coordinates Claude Code task lists by monitoring progress, detecting stalls, and flagging issues without implementing code.

1|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/AskTinNguyen/vesper-team-skills --skill agent-supervisor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-supervisor
Source: https://github.com/AskTinNguyen/vesper-team-skills/tree/main/agent-supervisor
Command: npx skills add https://github.com/AskTinNguyen/vesper-team-skills --skill agent-supervisor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bash, python3, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Supervisors and coordinates multiple agents on the Claude Code task list, creating tasks and flagging issues while never implementing code.

Core Features & Use Cases

  • Mode-based supervision: Pure Supervisor, PR Status Tracker, and Review Follower to fit orchestration needs.
  • Polling, diffing, and reporting to detect stalls, gaps, and progress across agents.
  • Integration with github-sync and task-list tooling to keep work synchronized and auditable.

Quick Start

Start in Pure Supervisor mode to begin monitoring the task list and coordinating, without writing any code.

Frequently Asked Questions about agent-supervisor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I coordinate multi-agent workflows without writing implementation code?

Multi-agent workflows are coordinated by supervising the Claude Code task list to monitor progress, detect stalls, and track PR statuses across agents without executing implementation logic.

How does task list monitoring detect stalled agents?

Task list monitoring detects stalled agents by polling the task list at configurable intervals, diffing previous states against current states, and flagging stalls when thresholds are exceeded.

Can I track pull request statuses across multiple agents simultaneously?

Pull request statuses are tracked across multiple agents using the PR Status Tracker mode, which integrates with github-sync to keep work synchronized and auditable.

Do I need bash and python3 to run multi-agent task supervision?

Bash and python3 are required dependencies to run multi-agent task supervision scripts, enabling the execution of polling, diffing, and reporting logic within the workflow environment.

What is the best way to start orchestrating tasks with a multi-agent supervisor?

Starting in Pure Supervisor mode is the recommended way to begin orchestrating tasks, allowing you to monitor the task list and coordinate agents before enabling advanced tracking features.

When should I avoid using an automated task supervisor for agent workflows?

Automated task supervision should be avoided when your workflow requires direct implementation from the orchestrator, as this supervisor strictly coordinates and monitors without writing code.