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 pull-requestgit 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/pull-request)<a href="https://agentmods.dev/skills/microsoft/hve-core/pull-request"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/pull-request/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/pull-request"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/pull-request.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.02716 |
| Opus 5.5 | $0.00016 | $0.01086 |
| Sonnet 5.5 | $0.00008 | $0.00543 |
| Haiku 4.5 | $0.00004 | $0.00272 |
Grade A, and why
pull-request 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 15d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request
Goal
Turn the current branch into a review-ready GitHub pull request with a short, accurate description and enough targeted local evidence to catch likely CI failures without running broad validation by default.
Success means the title and body reflect the committed branch diff, the repository template is preserved when present, changed-area preflight checks pass, any authorized preflight repairs are committed under repository conventions, and an external pull request is created or updated only after final PR-write approval. Push consent is separate and is reused for the same action.
Inputs
base: Base branch or ref. Default to the remote default branch without fetching.draft: Whether a newly created pull request is a draft. Default tofalse.action:prepare,create, orupdate. Infer from the request and default topreparewhen external write intent is unclear.
Use the current checked-out branch as the head. Ask only for an input that cannot be inferred and changes the resulting pull request.
Platform Routing
When the push remote is hosted on Azure DevOps (dev.azure.com or *.visualstudio.com), or the user
explicitly asks for an Azure DevOps pull request, load the backlog-management skill and follow its
Azure DevOps pull request reference instead of the Flow below. When backlog-management does not
resolve, report that the Azure DevOps protocol is unavailable and stop before any Azure DevOps call.
Every other remote uses the GitHub flow below unchanged.
Resolve action before delegating, then carry this skill's inputs into that reference:
- Map
basetobaseBranch, resolving its default as this skill does, and mapdrafttoisDraft. An Azure DevOps input the user supplies explicitly, such asbaseBranchorisDraft, takes precedence over its alias. Pass through other Azure DevOps inputs the user supplies, such as project, repository, work item IDs, area path, or iteration path. prepare: produce the local pull request description through the reference's Phase 1 and Phase 2, applying its Content Sanitization Guards and Untrusted Content Boundary, then stop and return the description path. Defer destination confirmation, the autonomy tier, platform readiness, work item discovery, creation, and linking, and every Azure DevOps call to a latercreate.create: run the reference's Mandatory Preflight, then its Required Phases with every destination, sanitization, and approval gate.update: the reference creates pull requests only. Report that updating an existing Azure DevOps pull request is not supported, stop before any Azure DevOps call, and offerprepareto refresh the description for a manual update.
What ships with it
3 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.
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.
- 15d ago Changed · +3 lines · -24 tokens per session fc1c15e333bd
- 1mo ago Changed · +24 lines · +21 tokens per session 5b943bd05489
- 1mo ago Changed 5648c6602469
- 2mo ago First seen · 173 lines · 43 tokens per session scan A 73db74d45d79
pull-request is a skill published in the GitHub repository microsoft/hve-core (1,606 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 2,716 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 2026-09-07.
pull-request compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pull-requestmicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 40 | 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 |