title	description	author	ms.date	ms.topic	keywords	estimated_reading_time
HVE Core	Hypervelocity Engineering prompt library for GitHub Copilot with constraint-based AI workflows and validated artifacts	Microsoft	2026-02-18	overview	hypervelocity engineering prompt engineering github copilot ai workflows custom agents copilot instructions rpi methodology	3

Hypervelocity Engineering (HVE) Core is an enterprise-ready prompt engineering framework for GitHub Copilot. Constraint-based AI workflows, validated artifacts, and structured methodologies that scale from solo developers to large teams.

Tip

Automated installation via the hve-core-installer agent in VS Code (~30 seconds)

Overview

HVE Core provides specialized agents, reusable prompts, instruction sets, and skills with JSON schema validation. The framework separates AI concerns into distinct artifact types with clear boundaries, preventing runaway behavior through constraint-based design.

The RPI (Research → Plan → Implement) methodology structures complex engineering tasks into phases where AI knows what it cannot do, changing optimization targets from "plausible code" to "verified truth."

Quick Start

1. Install

Install the VS Code extension from the Marketplace:

Need a different installation method? See the Installation Guide for CLI plugins, submodules, multi-root workspaces, and more.

2. Verify

Open GitHub Copilot Chat (Ctrl+Alt+I) and check that HVE Core agents appear in the agent picker. Look for task-researcher, task-planner, and rpi-agent.

3. Try It

Select the memory agent and type:

Remember that I'm exploring HVE Core for the first time.

The agent creates a memory file in your workspace. You now have a working HVE Core installation that responds to natural language.

Ready to go deeper? Follow the Getting Started Guide.

What's Included

Component	Count	Description	Documentation
Agents	18	Specialized AI assistants for research, planning, and implementation	Agents
Instructions	17+	Repository-specific coding guidelines applied automatically	Instructions
Prompts	18	Reusable templates for common tasks like commits and PRs	Prompts
Skills	1	Self-contained packages with cross-platform scripts and guidance	Skills
Scripts	N/A	Validation tools for linting, security, and quality	Scripts

Prompt Engineering Framework

HVE Core provides a structured approach to prompt engineering with four artifact types, each serving a distinct purpose:

Artifact	Purpose	Activation
Instructions	Passive reference guidance applied by file pattern	Automatic via applyTo glob
Prompts	Task-specific procedures with input variables	Manual via / command
Agents	Specialized personas with tool access and constraints	Manual via agent picker
Skills	Executable utilities with cross-platform scripts	Read by Copilot on demand

Key Capabilities

• Protocol patterns support step-based (sequential) and phase-based (conversational) workflow formats
• Input variables use ${input:variableName} syntax with defaults and VS Code integration
• Subagent delegation provides a first-class pattern for tool-heavy work via runSubagent
• Maturity lifecycle follows a four-stage model (experimental → preview → stable → deprecated)

Use the prompt-builder agent to create new artifacts following these patterns.

Enterprise Validation Pipeline

All AI artifacts are validated through a CI/CD pipeline with JSON schema enforcement:

*.instructions.md → instruction-frontmatter.schema.json
*.prompt.md       → prompt-frontmatter.schema.json
*.agent.md        → agent-frontmatter.schema.json
SKILL.md          → skill-frontmatter.schema.json

The validation system provides:

• Typed frontmatter validation provides structured error reporting.
• Pattern-based schema mapping enables automatic file type detection.
• Maturity enforcement ensures artifacts declare stability level.
• Link and language checks validate cross-references.

Run npm run lint:frontmatter locally before committing changes.

Project Structure

.github/
├── agents/          # Specialized Copilot chat assistants
├── instructions/    # Repository-specific coding guidelines
├── prompts/         # Reusable prompt templates
├── skills/          # Self-contained executable packages
└── workflows/       # CI/CD pipeline definitions
docs/
├── getting-started/ # Installation and first workflow guides
├── rpi/             # Research, Plan, Implement methodology
├── contributing/    # Artifact authoring guidelines
└── architecture/    # System design documentation
extension/           # VS Code extension source
scripts/
├── linting/         # Markdown, frontmatter, YAML validation
└── security/        # Dependency pinning and SHA checks

Contributing

We appreciate contributions! Whether you're fixing typos or adding new components:

1. Read our Contributing Guide
2. Check out open issues
3. Join the discussion

Documentation

Guide	Description
Getting Started	Setup and first workflow tutorial
RPI Workflow	Deep dive into Research, Plan, Implement
Contributing	Create custom agents, instructions, and prompts
Agents Reference	All available agents
Instructions Reference	All coding instructions

Responsible AI

Microsoft encourages customers to review its Responsible AI Standard when developing AI-enabled systems to ensure ethical, safe, and inclusive AI practices. Learn more at Microsoft's Responsible AI.

Legal

This project is licensed under the MIT License.

See SECURITY.md for the security policy and vulnerability reporting.

See GOVERNANCE.md for the project governance model.

Trademark Notice

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.

---

🤖 Crafted with precision by ✨Copilot following brilliant human instruction, then carefully refined by our team of discerning human reviewers.