This repository contains my personal configuration for GitHub Copilot Agent in VS Code.
It can serve as a useful starting point for those new to GitHub Copilot in VS Code.
These instructions are designed to help achieve effective responses to zero-shot prompting during typical development tasks.
.github- .github/agents: Custom Agents
- .github/instructions: Custom Instructions
- .github/skills: Agent Skills
- .github/copilot-instructions.md: Workspace-optimized instructions
.vscode- .vscode/mcp.json: Default MCP server configuration
- .vscode/settings.json: Default VS Code settings
- VS Code: Version 1.108.x
- Required MCP commands:
npx,docker,uvx - Tested models:
Claude Opus 4.5,Claude Sonnet 4.5,GPT-5.2
Note: Behavior may vary depending on the model. Each model interprets instructions and context differently.
- copilot-agent.instructions.md: 6-phase execution protocol with SSOT hierarchy, quality standards, and no-assumption rules
- subagents.instructions.md: SSOT defining forbidden MCP calls, delegation rules, and Context Package contract
- taming-copilot.instructions.md: User directive priority, code-on-request-only, and direct/concise response philosophy
- task-direction-approval.instructions.md: Mandatory user consent before tech/architecture changes with failure-to-options protocol
- investigation-mode: Pause implementation after 2+ consecutive failures, switch to root-cause analysis before resuming
- minimalist-surgical-development: Smallest diff first, standard libraries preferred, no unsolicited refactoring
- root-cause-tracing: Trace bugs backward through call stack to find the original trigger, not the symptom
- task-direction-approval: Explain failure cause, present 2-3 options with trade-offs, wait for explicit user choice
- uncertainty-verification: Verify exact commands/configs/APIs via official docs before stating - no assumption-based specifics
- verification-before-completion: Run verification commands and confirm output before any completion claims - evidence before assertions
- critical-thinking.agent.md: Question assumptions and guide toward optimal solutions
- mentor.agent.md: Support engineer growth through critical questioning and mentorship