Skip to content
| Marketplace
Sign in
Visual Studio Code>Chat>HVE CoreNew to Visual Studio Code? Get it now.
HVE Core

HVE Core

ISE HVE Essentials

|
1,357 installs
| (2) | Free
HVE Core RPI (Research, Plan, Implement, Review) workflow with Git commit, merge, setup, and pull request prompts
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

HVE Core

HVE Core RPI (Research, Plan, Implement, Review) workflow with Git commit, merge, setup, and pull request prompts

HVE Core provides the flagship RPI (Research, Plan, Implement, Review, Discover) workflow for completing complex tasks through a structured five-phase process. The RPI workflow dispatches specialized agents that collaborate autonomously to deliver well-researched, planned, and validated implementations. This collection also includes Git workflow prompts for commit messages, merge operations, repository setup, and pull request management.

This collection includes agents for:

  • RPI Agent — Autonomous orchestrator that drives the full five-phase workflow
  • Task Researcher — Gathers context, discovers patterns, and produces research documents
  • Task Planner — Creates detailed implementation plans from research findings
  • Task Implementor — Executes plans with progressive tracking and change records
  • Task Reviewer — Validates implementations against plans and project conventions
  • PR Review — Comprehensive pull request review ensuring code quality and convention compliance

Git workflow prompts for:

  • Commit Messages — Generate conventional commit messages following project standards
  • Merge Operations — Handle merges, rebases, and conflict resolution workflows
  • Repository Setup — Initialize repositories with recommended configuration
  • Pull Requests — Create and manage pull requests with linked context

Supporting subagents included:

  • Codebase Researcher — Searches workspace for code patterns, conventions, and implementations
  • External Researcher — Retrieves external documentation, SDK references, and code samples
  • Phase Implementor — Executes single implementation phases with change tracking
  • Artifact Validator — Validates implementation work against plans and conventions
  • Prompt Tester — Tests prompt files by following them literally in a sandbox
  • Prompt Evaluator — Evaluates prompt execution results against quality criteria

Skills included:

  • PR Reference — Generates PR reference XML files with commit history and diffs for pull request workflows

Included Artifacts

Chat Agents

Name Description
doc-ops Autonomous documentation operations agent for pattern compliance, accuracy verification, and gap detection
implementation-validator Validates implementation quality against architectural requirements, design principles, and code standards with severity-graded findings
memory Conversation memory persistence for session continuity
phase-implementor Executes a single implementation phase from a plan with full codebase access and change tracking
plan-validator Validates implementation plans against research documents, updating the Planning Log Discrepancy Log section with severity-graded findings
pr-review Comprehensive Pull Request review assistant ensuring code quality, security, and convention compliance
prompt-builder Prompt engineering assistant with phase-based workflow for creating and validating prompts, agents, and instructions files
prompt-evaluator Evaluates prompt execution results against Prompt Quality Criteria with severity-graded findings and categorized remediation guidance
prompt-tester Tests prompt files by following them literally in a sandbox environment when creating or improving prompts, instructions, agents, or skills without improving or interpreting beyond face value
prompt-updater Modifies or creates prompts, instructions or rules, agents, skills following prompt engineering conventions and standards based on prompt evaluation and research
researcher-subagent Research subagent using search tools, read tools, fetch web page, github repo, and mcp tools
rpi-agent Autonomous RPI orchestrator running specialized subagents through Research → Plan → Implement → Review → Discover phases
rpi-validator Validates a Changes Log against the Implementation Plan, Planning Log, and Research Documents for a specific plan phase
task-implementor Executes implementation plans from .copilot-tracking/plans with progressive tracking and change records
task-planner Implementation planner for creating actionable implementation plans
task-researcher Task research specialist for comprehensive project analysis
task-reviewer Reviews completed implementation work for accuracy, completeness, and convention compliance

Prompts

Name Description
checkpoint Save or restore conversation context using memory files
doc-ops-update Invoke doc-ops agent for documentation quality assurance and updates
git-commit Stages all changes, generates a conventional commit message, shows it to the user, and commits using only git add/commit
git-commit-message Generates a commit message following the commit-message.instructions.md rules based on all changes in the branch
git-merge Coordinate Git merge, rebase, and rebase --onto workflows with consistent conflict handling.
git-setup Interactive, verification-first Git configuration assistant (non-destructive)
prompt-analyze Evaluates prompt engineering artifacts against quality criteria and reports findings
prompt-build Build or improve prompt engineering artifacts following quality criteria
prompt-refactor Refactors and cleans up prompt engineering artifacts through iterative improvement
pull-request Generates pull request descriptions from branch diffs
rpi Autonomous Research-Plan-Implement-Review-Discover workflow for completing tasks
task-implement Locates and executes implementation plans using task-implementor
task-plan Initiates implementation planning based on user context or research documents
task-research Initiates research for implementation planning based on user requirements
task-review Initiates implementation review based on user context or automatic artifact discovery

Instructions

Name Description
hve-core/commit-message Required instructions for creating all commit messages
hve-core/git-merge Required protocol for Git merge, rebase, and rebase --onto workflows with conflict handling and stop controls.
hve-core/markdown Required instructions for creating or editing any Markdown (.md) files
hve-core/prompt-builder Authoring standards for prompt engineering artifacts including prompts, agents, instructions, and skills
hve-core/pull-request Required instructions for pull request description generation and optional PR creation using diff analysis, subagent review, and MCP tools
hve-core/writing-style Required writing style conventions for voice, tone, and language in all markdown content
shared/hve-core-location Important: hve-core is the repository containing this instruction file; Guidance: if a referenced prompt, instructions, agent, or script is missing in the current directory, fall back to this hve-core location by walking up this file's directory tree.

Skills

Name Description
pr-reference Generates PR reference XML containing commit history and unified diffs between branches. Includes utilities to list changed files and read diff chunks. Use when creating pull request descriptions, preparing code reviews, analyzing branch changes, discovering work items from diffs, or generating structured diff summaries.

Getting Started

After installing this extension, the chat agents are available in GitHub Copilot Chat:

  1. Use custom agents by selecting the custom agent from the agent picker drop-down list in Copilot Chat
  2. Apply prompts through the Copilot Chat interface
  3. Reference instructions — they are automatically applied based on file patterns

Post-Installation Setup

Some chat agents create workflow artifacts in your project directory. See the installation guide for recommended .gitignore configuration and other setup details.

Pre-release Channel

HVE Core offers two installation channels:

Channel Description Maturity Levels
Stable Production-ready artifacts only stable
Pre-release Early access to new features and experimental artifacts stable, preview, experimental

To install the pre-release version, select Install Pre-Release Version from the extension page in VS Code.

Requirements

  • VS Code version 1.106.1 or higher
  • GitHub Copilot extension

License

MIT License - see LICENSE for details

Support

For issues, questions, or contributions, visit the GitHub repository.


Brought to you by Microsoft ISE HVE Essentials

  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
© 2026 Microsoft