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.
git 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/commands/microsoft/hve-core/pptx)<a href="https://agentmods.dev/commands/microsoft/hve-core/pptx"><img src="https://agentmods.dev/badge/commands/microsoft/hve-core/pptx.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.00224 |
| Opus 5 | $0.00005 | $0.00112 |
| Sonnet 5 | $0.00002 | $0.00045 |
| Haiku 4.5 | $0.00001 | $0.00022 |
Grade A, and why
pptx 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 today.
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.
What it actually says
PowerPoint Slide Deck
Inputs
- ${input:source}: (Optional) Source PPTX file or content directory to work from. Defaults to creating a new deck.
- ${input:action}: (Optional) Action to perform:
create,update,cleanup, orfrom-existing. Defaults tocreatewhen omitted. - ${input:requirements}: (Optional) Additional requirements, objectives, or constraints for the slide deck.
Requirements
- Establish a working directory under
.copilot-tracking/ppt/for all artifacts. - Organize content, images, and scripts as separate artifacts before generating slides.
- Generate slide decks programmatically using Python with
python-pptx. - Validate each iteration against the quality checklist before presenting results.
- Iterate on fixes until the deck passes all validation checks.
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.
- today First seen · 22 lines · 10 tokens per session scan A 545a618a0dc5
pptx is a command published in the GitHub repository microsoft/hve-core (1,436 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 224 once invoked, about $0.0001 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 2026-09-06.
Other commands, from other repositories
portaljs-define-schema
Define a dataset's metadata profile — infer a Frictionless Table Schema from its data, add Data Package metadata (license, sources, keywords), and write it into datasets.json so the showcase renders a typed field table. Extend or customize via the L0→L3 profile ladder.
vlm-ocr
Run the vlm-ocr skill on the task below. It has three phases: evaluate (compare candidate OCR systems against stratified human ground truth and pick one on measured CER/WER), run (build and execute the production VLM-OCR pipeline — model selection, image handling, prompts, architecture, batching, accuracy evaluation…
PRD Generation
Generate comprehensive Product Requirements Document from epic description.
brainstorm
Design-first ideation workflow that explores user intent, clarifies constraints, proposes approaches, and produces an approved design document before planning.
docai-classify
Build and use a Document Intelligence classifier — train a classifier to identify document types and split multi-document files.
docai-custom-model
Build a custom Document Intelligence extraction model — prepare training data, label fields, train, evaluate accuracy, and deploy for production use.