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 ux-artifactsgit 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/ux-artifacts)<a href="https://agentmods.dev/skills/microsoft/hve-core/ux-artifacts"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/ux-artifacts/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/ux-artifacts"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/ux-artifacts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 89 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00035 | $0.02411 |
| Opus 5.5 | $0.00014 | $0.00964 |
| Sonnet 5.5 | $0.00007 | $0.00482 |
| Haiku 4.5 | $0.00003 | $0.00241 |
Grade A, and why
ux-artifacts 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 2mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Artifacts
Produce one durable, evidence-labelled UX asset from supplied context. Use this skill directly or through an agent when the required outcome is an artifact rather than a coached conversation.
Goal
Turn supplied UX evidence and decisions into a current Markdown asset that another practitioner, agent, or engineer can consume without inventing research or losing uncertainty.
Modes
Load exactly one mode reference for each invocation.
| Mode | Outcome | Reference |
|---|---|---|
frame-needs |
Current context, user needs, desired outcomes, and known workarounds | references/frame-needs.md |
map-journey |
Staged journey with actions, thoughts, pain points, and opportunities | references/map-journey.md |
sketch-structure |
Surface composition, controls, interaction states, and transitions | references/sketch-structure.md |
decide-inclusion |
Concept-stage exclusion risks, demands, alternatives, and coverage gaps | references/decide-inclusion.md |
prepare-handoff |
Implementation-facing flow, states, recovery, rationale, and open decisions | references/prepare-handoff.md |
The modes are operations over supplied evidence. They are not practitioner roles, project phases, persistent workflows, or prerequisites for one another. Never invoke another mode automatically.
Flow
- Resolve
mode,project, andsubject. Ask one routing question only when the requested asset matches more than one mode. - Read references/evidence-model.md. Resolve the output path and ingest only the supplied
sourceor in-context evidence. - Load the selected mode reference. Produce its bounded asset without conducting coaching, interviews, technical conformance checks, or destination writes.
- Write the current asset to
.copilot-tracking/ux-artifacts/{project-slug}/{subject-slug}/{mode}.md. A rerun updates that file rather than creating dated duplicates or hidden state. - When
destinationis supplied, read references/to-figma.md or references/to-mural.md and append destination intent to the result. Resolve the destination inputs that reference requires before producing intent. Do not invoke either destination. - Return the asset pointer, evidence summary, unresolved items, and destination intent when requested.
What ships with it
8 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.
- 2mo ago First seen · 139 lines · 35 tokens per session scan A 5b420e4024ad
ux-artifacts is a skill published in the GitHub repository microsoft/hve-core (1,606 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 2,411 once invoked, about $0.0001 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 2026-08-30.
ux-artifacts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ux-artifactsmicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 35 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 107k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 107k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 107k | yesterday | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | yesterday | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | 3d ago | Apache-2.0 | A | 56 | Claude Code |
| prototype-webnexu-io/html-anything | Skill | 9.5k | yesterday | Apache-2.0 | A | 24 | Claude Code, Codex |