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 analysis-authoringgit 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/analysis-authoring)<a href="https://agentmods.dev/skills/microsoft/hve-core/analysis-authoring"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/analysis-authoring/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/analysis-authoring"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/analysis-authoring.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 73 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 | $0.00055 | $0.00969 |
| Opus 5.5 | $0.00022 | $0.00388 |
| Sonnet 5.5 | $0.00011 | $0.00194 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
analysis-authoring 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis Authoring Conventions
Goal
Produce exploratory notebooks and analytical dashboards whose structure, visualization choices, and scale handling are deliberate rather than incidental. This skill supplies the editorial judgment that generic file, notebook, terminal, and browser tooling does not carry.
Flow
- Confirm the analysis question, the datasets in scope, and the deliverable shape: notebook, dashboard, or both.
- Read the available profile and objectives artifacts rather than re-deriving column semantics.
data-catalogowns the profile contract and semantic roles. - Select the deliverable's section sequence from the matching reference, including only the conditional sections the data supports.
- Choose each visualization from its analytical goal, applying the scale thresholds rather than plotting whole datasets by default.
- Record interpretation next to each figure so a reader learns what the figure answers, not only what it shows.
- Validate the deliverable against its completeness expectations, and for dashboards apply the responsiveness budgets as project-adjustable defaults.
Inputs
- The analysis question and intended audience
- Dataset locations and, when available, an existing data profile and declared objectives
- The deliverable shape and its destination
- Any project-specific performance budget that overrides the defaults here
Success criteria
- The deliverable follows the section sequence for its shape, and conditional sections appear only when the data supports them.
- Every figure is preceded by the question it answers and is followed by an interpretation placeholder or an actual reading.
- Visualization selection matches the analytical goal, and dense or high-cardinality data is sampled, binned, or truncated deliberately.
- Every meaningful distinction is encoded in a channel besides colour, and categorical and continuous scales use colourblind-safe palettes.
- Notebook code stays modular, with repeated transformation logic extracted rather than duplicated across cells.
- Dashboard caching distinguishes serializable data from global resources, and cross-page interaction state is explicit.
- Dashboard validation reports functional, data, and responsiveness findings against stated budgets.
- Uncertainty, data limitations, and open questions are written down rather than implied.
What ships with it
2 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 · 81 lines · 55 tokens per session scan A fde091d1f759
analysis-authoring is a skill published in the GitHub repository microsoft/hve-core (1,606 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 969 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 2026-08-30.
analysis-authoring compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| analysis-authoringmicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 55 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |