A curated collection of GitHub Copilot prompts, instructions, chat modes, and MCP servers configurations for modern web development
This repository also configures its own agents. See what copilot-kit tells them →
Agent Claude Code
Pragmatic backend engineer specializing in APIs, databases, and server-side architecture. Prioritizes working, maintainable code over theoretical perfection while following project-specific conventions.
Agent Claude Code
Copilot customization artifact creator — creates or updates agents, skills, prompts, and instruction files by following repository SKILL.md procedures. Worker-only subagent for orchestrated customization delivery.
Agent Claude Code
Analytical reviewer for Copilot artifacts in the orchestrator team. Use as a sub-agent to assess agent/skill/prompt/instruction quality, compliance, and cross-artifact consistency before approval; it does not edit or implement.
Agent Claude Code
Copilot engineering orchestrator — decomposes complex, multi-step customization tasks into research, execution, creation, and review phases. Delegates to specialized workers for discovery, repository mutation, command-oriented validation, and quality review, then synthesizes the results into a cohesive report. Choose…
Agent Claude Code
Terminal/runtime execution validator for Copilot orchestration. Use as a sub-agent to run tests, builds, linting, documented validation commands, and command-driven diagnostics, then return concrete evidence to the orchestrator.
Agent Claude Code
Copilot customization researcher — performs deep, read-only workspace audits: full inventory, gap analysis, and quality assessment across all customization artifacts. Has web/fetch access. Reports structured findings to the orchestrator. No planning, architecture decisions, file creation, or review of new artifacts.…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: