Use Squad to create human-directed specialist agents that persist in a repository, share decisions through files, and help coordinate implementation, testing, and review work in GitHub Copilot.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Coordinate persistent Copilot agent teams with Squad"
slug: "coordinate-persistent-copilot-agent-teams-with-squad"
description: "Use Squad to create human-directed specialist agents that persist in a repository, share decisions through files, and help coordinate implementation, testing, and review work in GitHub Copilot."
github_stars: 2518
verification: "security_reviewed"
source: "https://github.com/bradygaster/squad"
author: "Brady Gaster"
publisher_type: "independent_open_source"
category: "Templates & Workflows"
framework: "Custom Agents"
tool_ecosystem:
github_repo: "bradygaster/squad"
github_stars: 2518
npm_package: "@bradygaster/squad-cli"
npm_weekly_downloads: 0
---
# Coordinate persistent Copilot agent teams with Squad
Use Squad to create human-directed specialist agents that persist in a repository, share decisions through files, and help coordinate implementation, testing, and review work in GitHub Copilot.
## Prerequisites
Node/npm; Squad CLI; GitHub CLI authentication; GitHub Copilot agent mode
## Installation
Use the upstream install or setup path that matches your environment:
- npm install -g @bradygaster/squad-cli
- git clone https://github.com/bradygaster/squad.git
- npm install
- npm run build
Requirements and caveats from upstream:
- Here's what I'm building: a recipe sharing app with React and Node.
- node ./packages/squad-cli/dist/cli-entry.js init
Basic usage or getting-started notes:
- ### 1. Create your project
- bash
- mkdir my-project && cd my-project
- Source: https://github.com/bradygaster/squad
- Extracted from upstream docs: https://raw.githubusercontent.com/bradygaster/squad/HEAD/README.md
## Documentation
- https://bradygaster.github.io/squad/
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/coordinate-persistent-copilot-agent-teams-with-squad/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.