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 architecture-diagramsgit 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/architecture-diagrams)<a href="https://agentmods.dev/skills/microsoft/hve-core/architecture-diagrams"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/architecture-diagrams/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/architecture-diagrams"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/architecture-diagrams.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 | $0.00037 | $0.02404 |
| Opus 5 | $0.00018 | $0.01202 |
| Sonnet 5 | $0.00007 | $0.00481 |
| Haiku 4.5 | $0.00004 | $0.00240 |
Grade A, and why
architecture-diagrams 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 9d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Diagrams Skill
Goal
Turn infrastructure source files or a declared DS_CATALOG_V1 data model into a readable architecture diagram for reviews, ADRs, and design discussions. Preserve the caller's selected output format and the source's authority boundaries.
Infrastructure inputs include Terraform, Bicep, ARM templates, shell scripts, Kubernetes manifests, and Docker or Compose files. Catalog input uses declared entities and relationships from data-catalog, the durable data-catalog skill. It does not infer a data model from SQL or ORM files.
This skill documents infrastructure topology and data models. To document a software system, meaning its containers, its components, and the people and systems around it, use the c4-architecture skill instead.
Success criteria
- The diagram includes only the confirmed source scope.
- Infrastructure sources retain their existing parsing and relationship behavior.
- Catalog diagrams preserve declared entity IDs, endpoints, cardinality, endpoint minimums, join keys, confidence, and evidence basis without inventing relationships.
- Caller preference controls ASCII or Mermaid output.
- Inferred and assumed catalog relationships remain visibly distinct from confirmed relationships.
Constraints
- Treat a diagram as a view over source authority, not a semantic authority of its own.
- Read catalog-erd.md for
DS_CATALOG_V1input, multiplicity mapping, confidence rendering, the catalog output contract, and the Functional Planner compatibility boundary. - Do not parse SQL DDL, Prisma, SQLAlchemy, or another ORM as catalog input.
- Do not render primary-key, foreign-key, or uniqueness markers for catalog join keys; the catalog declares field names, not database key roles.
- Keep the Feasibility Study Interchange Profile and downstream requirement mappings in their owning workstreams.
Stop rules
- Stop and ask for scope when infrastructure boundaries are ambiguous.
- Stop and report an unsupported catalog version, unresolved endpoint, unknown cardinality, missing or invalid endpoint minimum, unknown confidence value, or malformed join-key declaration instead of guessing or partially rendering.
- Stop before diagram generation when no output preference can be resolved.
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.
- pyproject.toml 561 B
- references/catalog-erd.md 5.0 KB
- scripts/render_catalog_erd.py 25 KB runs code
- tests/corpus/0_valid_catalog 157 B
- tests/corpus/1_empty_frontmatter 8 B
- tests/corpus/2_unclosed_sequence 20 B
- tests/corpus/3_scalar_entities 29 B
- tests/corpus/4_no_frontmatter 15 B
- tests/corpus/README.md 1.2 KB
- tests/fuzz_harness.py 1.1 KB runs code
- tests/test_render_catalog_erd.py 25 KB runs code
- uv.lock 67 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.
- 9d ago First seen · 263 lines · 37 tokens per session scan A 391136a9a6e7
architecture-diagrams is a skill published in the GitHub repository microsoft/hve-core (1,437 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,404 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.