team-planner

Coordinate specialist agents to decompose and parallelize engineering tasks.

42|9|Updated Mar 16, 2026
One-click install
npx skills add https://github.com/drvoss/everything-copilot-cli --skill team-planner-drvoss
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team-planner
Source: https://github.com/drvoss/everything-copilot-cli/tree/main/skills/copilot-exclusive/team-planner
Command: npx skills add https://github.com/drvoss/everything-copilot-cli --skill team-planner-drvoss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Large, multi-domain tasks often overwhelm a single agent or model and require coordinated expertise, clear ownership, and deterministic tracking; team-planner provides a Copilot CLI-native pattern to decompose work, assemble specialist agents, and monitor progress until synthesis.

Core Features & Use Cases

  • Team design and tracking: Define a team roster and task assignments using the Copilot CLI session SQL database so ownership is explicit and auditable.
  • Deterministic dispatch: Dispatch background agents via the task tool or use /fleet for automatic fan-out to execute parallel specialists.
  • Monitoring and synthesis: Poll and follow up with running agents using read_agent and write_agent, record results in SQL, and use a general-purpose synthesizer to consolidate findings.
  • Use cases: Full-stack audits combining security, performance, and architecture reviews; parallelized feature work split across domain specialists; heavyweight code-review pipelines that require pair-agent review loops.

Quick Start

Dispatch a three-person team to audit the repository for security, performance, and architecture issues and track each assignment in the SQL session database.

Frequently Asked Questions about team-planner

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

FAQPage Schema
How do I parallelize multi-domain code reviews across different specialist agents?

Multi-domain code reviews can be parallelized by assembling specialist agents and dispatching them via the task tool or /fleet for automatic fan-out, tracking each assignment and result in SQL session tables for deterministic monitoring and synthesis.

What is the best way to orchestrate parallel AI agents for full-stack audits?

Full-stack audits can be orchestrated by decomposing the task into security, performance, and architecture domains, assigning each to a specialist agent, and using SQL session tables to track ownership and poll progress until results are synthesized.

How does tracking AI agent tasks with SQL work in Copilot CLI?

Tracking AI agent tasks with SQL in Copilot CLI uses session database tables to define team rosters and assignments, while read_agent and write_agent primitives monitor running agents and record results for deterministic auditability.

Can I use Copilot CLI to dispatch background agents for parallel feature work?

Copilot CLI can dispatch background agents for parallel feature work using the task tool or /fleet command, enabling automatic fan-out to domain specialists while monitoring their progress through SQL session tables.

When should I use multiple specialist agents instead of a single model for engineering tasks?

Multiple specialist agents are needed when large, multi-domain tasks overwhelm a single model and require coordinated expertise, clear ownership, and deterministic tracking across domains like security, performance, and architecture.

Does team-planner require external dependencies to manage AI agent orchestration?

Team-planner requires no external dependencies, relying entirely on Copilot CLI primitives like SQL session tables, the task tool, /fleet, read_agent, and write_agent for deterministic dispatch, monitoring, and synthesis.