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 dt-rpi-integrationgit 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/dt-rpi-integration)<a href="https://agentmods.dev/skills/microsoft/hve-core/dt-rpi-integration"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/dt-rpi-integration/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/dt-rpi-integration"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/dt-rpi-integration.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 18 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 | $0.00036 | $0.00702 |
| Opus 5.5 | $0.00014 | $0.00281 |
| Sonnet 5.5 | $0.00007 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
dt-rpi-integration 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 1mo 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Thinking → RPI Integration — Skill Entry
This skill is the entry point for Design Thinking to RPI integration knowledge.
The DT coach loads these references when Design Thinking coaching graduates into the RPI workflow. Every DT exit produces research-ready input for rpi-research. The retained downstream phases, rpi-plan, rpi-implement, and rpi-review, consume the resulting context. RPI Agent is the lifecycle wrapper when end-to-end coordination is needed; it does not replace rpi-research as the handoff target.
Integration references
| Reference | When to load |
|---|---|
| Handoff contract | Exit points, artifact schemas, RPI input contracts, and quality markers for lateral DT-to-RPI handoff |
| Space-exit handoffs | Step-by-step Problem, Solution, and Implementation Space exit procedures that compile the handoff summary and the RPI entry document |
| Research context | DT-aware rpi-research framing for handoffs from the DT coach |
| Planning context | DT-aware rpi-plan context for plans originating from DT artifacts |
| Implement context | DT-aware rpi-implement context applying fidelity and stakeholder constraints |
| Review context | DT-aware rpi-review criteria for evaluating Design Thinking artifacts |
| Subagent handoff | Readiness assessment, artifact compilation, and validation via subagent dispatch |
| Image prompt generation | Method 5 concept visualization with lo-fi prompt enforcement |
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.
- references/image-prompt-generation.md 9.0 KB
- references/rpi-handoff-contract.md 7.2 KB
- references/rpi-implement-context.md 4.3 KB
- references/rpi-planning-context.md 5.8 KB
- references/rpi-research-context.md 4.2 KB
- references/rpi-review-context.md 6.1 KB
- references/space-exit-handoffs.md 17 KB
- references/subagent-handoff.md 3.3 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.
- 1mo ago Changed · +2 lines 5030b032d973
- 2mo ago First seen · 39 lines · 36 tokens per session scan A adaee3a9e2ae
dt-rpi-integration is a skill published in the GitHub repository microsoft/hve-core (1,606 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 702 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.
dt-rpi-integration compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dt-rpi-integrationmicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 36 | 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 |