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 customer-card-rendergit 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/customer-card-render)<a href="https://agentmods.dev/skills/microsoft/hve-core/customer-card-render"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/customer-card-render/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/customer-card-render"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/customer-card-render.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
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 →
- high Tool Misuse · line 35 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Prompt Injection · line 155 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
- medium Prompt Injection · line 158 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
- low Supply Chain · line 35 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- low Supply Chain · line 157 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00015 | $0.01584 |
| Opus 5.5 | $0.00006 | $0.00634 |
| Sonnet 5.5 | $0.00003 | $0.00317 |
| Haiku 4.5 | $0.00002 | $0.00158 |
Grade A, and why
customer-card-render 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 yesterday.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Card Render Skill
Converts canonical Design Thinking markdown artifacts into template-driven content.yaml slide definitions.
Overview
This skill handles the Design Thinking-specific mapping layer: extracting sections from canonical markdown artifacts and filling template-driven content.yaml files. It does not build, theme, export, or validate a presentation file. The separate hve-slides skill owns HTML presentation authoring and rendering.
Keeping this layer separate means:
- Customer-card mapping logic stays independent from any presentation tooling.
- The skill can be included in packages independently.
- The generated YAML stays a reviewable, renderer-neutral artifact.
Prerequisites
-
Python 3.11+
-
uvpackage manager, installed with a package manager that verifies the download against a published hash:# Windows winget install --id astral-sh.uv -e # macOS / Linux (Homebrew) brew install uvTo install from a release archive instead, download it from the uv releases page and check it against its
.sha256file before extracting.
Directory Structure
.github/skills/experimental/customer-card-render/
├── SKILL.md
├── pyproject.toml
├── references/
│ └── mapping-spec.md
├── scripts/
│ └── generate_cards.py
├── templates/
│ ├── global-style.yaml
│ ├── persona.content.yaml
│ ├── problem.content.yaml
│ ├── scenario.content.yaml
│ ├── use-case-slide1.content.yaml
│ ├── use-case-slide2.content.yaml
│ ├── use-case-slide3.content.yaml
│ └── vision.content.yaml
└── tests/
├── fuzz_harness.py
└── test_generate_cards.py
Supported Artifact Types
| Artifact Type | Slide Layout |
|---|---|
| Vision Statement | Single slide |
| Problem Statement | Single slide |
| Scenario | Single slide |
| Use Case | 4 slides (see below) |
| Persona | Single slide |
What ships with it
17 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.
- pyproject.toml 837 B
- references/mapping-spec.md 5.7 KB
- scripts/generate_cards.py 15 KB runs code
- SECURITY.md 13 KB
- templates/global-style.yaml 292 B
- templates/persona.content.yaml 2.4 KB
- templates/problem.content.yaml 1.1 KB
- templates/scenario.content.yaml 2.0 KB
- templates/use-case-slide1.content.yaml 1.8 KB
- templates/use-case-slide2.content.yaml 2.8 KB
- templates/use-case-slide3.content.yaml 2.4 KB
- templates/use-case-slide4.content.yaml 1.6 KB
- templates/vision.content.yaml 1.6 KB
- tests/corpus/.gitkeep 0 B
- tests/fuzz_harness.py 1.0 KB runs code
- tests/test_generate_cards.py 13 KB runs code
- uv.lock 58 KB
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.
- yesterday Changed · -13 lines · -10 tokens per session 469869deef15
- 17d ago Changed · -1 lines scan C → A c485047353be
- 1mo ago Changed f0f01909468c
- 1mo ago Changed · +2 lines 6e59d1505253
- 2mo ago First seen · 163 lines · 25 tokens per session scan C 594b0694ec03
customer-card-render is a skill published in the GitHub repository microsoft/hve-core (1,606 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 1,584 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.
customer-card-render compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| customer-card-rendermicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 15 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | yesterday | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | yesterday | Apache-2.0 | A | 68 | Claude Code |
| report-to-pdfasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 17 | Claude Code, Codex |
| artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 54 | Claude Code, Codex |