HVE Core is a collection of agents, prompts, coding instructions, and skills for building repeatable software-development workflows with GitHub Copilot. It is intended for individuals and teams that want structured AI-assisted research, planning, implementation, and review, while the catalogue entries provide many of its reusable workflow components.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/microsoft/hve-coreWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/microsoft/hve-core/readme)<a href="https://agentmods.dev/commands/microsoft/hve-core/readme"><img src="https://agentmods.dev/badge/commands/microsoft/hve-core/readme.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.02980 |
| Opus 5 | $0.00010 | $0.01490 |
| Sonnet 5 | $0.00004 | $0.00596 |
| Haiku 4.5 | $0.00002 | $0.00298 |
Grade A, and why
README scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Prompts
This directory contains coaching and guidance prompts designed to provide step-by-step assistance for specific development tasks. Unlike instructions that focus on systematic implementation, prompts offer educational guidance and context-aware coaching to help you learn and apply best practices. Prompts are organized by workflow focus area: planning and RPI, source control, pull requests and review, prompt engineering, Design Thinking, Responsible AI, security, accessibility, data science, and experimental tools.
Backlog and work item workflows are not prompts. They are user-invocable skills that discover the active tracker at runtime and work the same way against Azure DevOps, GitHub, and Jira. See Backlog & Work Item Management.
How to Use Prompts
Prompts can be invoked in GitHub Copilot Chat using /prompt-name syntax (for example, /rpi or /git-commit). They provide:
- Educational Guidance: Step-by-step coaching approach
- Context-Aware Assistance: Project-specific guidance and examples
- Best Practices: Established patterns and conventions
- Interactive Support: Conversational assistance for complex tasks
Available Prompts
Onboarding, Research & Planning
- RPI - Coordinates one task through Research, Plan, Implement, Review, and Follow-up with the RPI Agent and matching
rpi-*skills
Use /rpi-research, /rpi-plan, /rpi-implement, or /rpi-review when you need one bounded RPI phase. Resume longer work from the durable artifacts owned by that workflow rather than from a generic conversation checkpoint.
Source Control & Commit Quality
- Git Commit (Stage + Commit) - Stages all changes and creates a Conventional Commit automatically
- Git Commit Message Generator - Generates a compliant commit message for currently staged changes
- Git Merge - Git merge, rebase, and rebase --onto workflows with conflict handling
- Git Setup - Verification-first Git configuration assistant
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed c089c2a173b9
- yesterday First seen · 165 lines · 19 tokens per session scan A ba4bbcdfd713
README is a command published in the GitHub repository microsoft/hve-core (1,436 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 2,980 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other commands, from other repositories
start-3-1-3
Module 3.1.3: Consistency & Style - Master the Golden Rules of prompting, reference images, and variants.
humanise-response
Here’s a prompt to humanise AI essays and text. You can also append your writing sample to further teach ChatGPT to sound more like you.
explain
Command "explain" from duongductrong/cursor-kit, covering explanation approach, for code explanations, for concept explanations, teaching principles and rules.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
start-0-8
A Japanese-language command that displays the current project setup progress.
prompt-create
Create a new prompt following ground rules.