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.
npx skills add microsoft/hve-core --skill pr-referencegit 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/skills/microsoft/hve-core/pr-reference)<a href="https://agentmods.dev/skills/microsoft/hve-core/pr-reference"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/pr-reference/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/hve-core/pr-reference"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/pr-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.01412 |
| Opus 5.5 | $0.00021 | $0.00565 |
| Sonnet 5.5 | $0.00010 | $0.00282 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
pr-reference 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 1mo ago.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Reference Generation Skill
Overview
Queries git for commit metadata and diff output, then produces a structured XML document. Both bash and PowerShell implementations are provided.
Use cases:
- PR description generation from commit history
- Code review preparation with structured diff context
- Work item discovery by analyzing branch changes
- Security analysis of modified files
After successful generation, include a file link to the absolute path of the XML output in the response.
Prerequisites
The repository must have at least one commit diverging from the base branch.
| Platform | Runtime |
|---|---|
| macOS / Linux | Bash (pre-installed) |
| Windows | PowerShell 7+ (pwsh) |
| Cross-platform | PowerShell 7+ (pwsh) |
Quick Start
Run the following command to generate a PR reference with default settings (compares against origin/main):
scripts/generate.sh
scripts/generate.sh --base-branch auto --merge-base --exclude-ext yml,json
scripts/generate.ps1
scripts/generate.ps1 -BaseBranch auto -MergeBase -ExcludeExt yml,json
Output saves to .copilot-tracking/pr/pr-reference.xml by default.
Parameters Reference
| Parameter | Flag (bash) | Flag (PowerShell) | Default | Description |
|---|---|---|---|---|
| Base branch | --base-branch |
-BaseBranch |
origin/main (bash) / main (PowerShell) |
Target branch for comparison. Use auto to detect remote default. |
| Merge base | --merge-base |
-MergeBase |
false | Use git merge-base for three-way comparison |
| Exclude markdown | --no-md-diff |
-ExcludeMarkdownDiff |
false | Exclude markdown files (*.md) from the diff |
| Exclude extensions | --exclude-ext |
-ExcludeExt |
(none) | Comma-separated extensions to exclude (e.g., yml,yaml,json,png) |
| Exclude paths | --exclude-path |
-ExcludePath |
(none) | Comma-separated path prefixes to exclude (for example, documentation and GitHub configuration directories) |
| Output path | --output |
-OutputPath |
.copilot-tracking/pr/pr-reference.xml |
Custom output file path |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/REFERENCE.md 8.8 KB
- scripts/generate.ps1 15 KB runs code
- scripts/generate.sh 5.8 KB runs code
- scripts/list-changed-files.ps1 7.5 KB runs code
- scripts/list-changed-files.sh 5.7 KB runs code
- scripts/read-diff.ps1 8.2 KB runs code
- scripts/read-diff.sh 5.7 KB runs code
- scripts/shared.psm1 2.5 KB
- tests/generate.Tests.ps1 20 KB runs code
- tests/list-changed-files.Tests.ps1 27 KB runs code
- tests/read-diff.Tests.ps1 19 KB runs code
- tests/shared.Tests.ps1 5.7 KB runs code
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.
- 1mo ago Changed · +1 lines 536f4cee9fd0
- 2mo ago First seen · 125 lines · 52 tokens per session scan A cc5939a82009
pr-reference is a skill published in the GitHub repository microsoft/hve-core (1,606 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,412 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
pr-reference compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pr-referencemicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 52 | Claude Code |
| review-implement-phaseprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 38 | Claude Code |
| github-pr-workflowpaperclipai/paperclip | Skill | 112k | today | MIT | A | 39 | Claude Code, Codex |
| review-deltatirth8205/code-review-graph | Skill | 33k | yesterday | MIT | A | 24 | Claude Code |
| github-contributordaymade/claude-code-skills | Skill | 1.5k | today | MIT | A | 105 | Claude Code, Codex |
| lean-reviewSnowflake-Labs/cocoplus | Skill | 728 | yesterday | MIT | A | 44 | Claude Code |
| hero-diff-highlightUnclecheng-li/AI_Animation | Skill | 1.7k | 13d ago | MIT | A | 0 | Claude Code, Codex |