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 privacy-by-designgit 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/privacy-by-design)<a href="https://agentmods.dev/skills/microsoft/hve-core/privacy-by-design"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/privacy-by-design/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/privacy-by-design"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/privacy-by-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.02633 |
| Opus 5.5 | $0.00019 | $0.01053 |
| Sonnet 5.5 | $0.00010 | $0.00527 |
| Haiku 4.5 | $0.00005 | $0.00263 |
Grade A, and why
privacy-by-design 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 10d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Privacy by Design
This SKILL.md is the entrypoint for the Privacy by Design skill.
The skill provides structured assessment references for the 7 Foundation Principles of Privacy by Design (Cavoukian, 2009). Consumers that explicitly load it can assess privacy practices across the software lifecycle. It complements privacy-standards with principle-level criteria, retention and disposal checks, regulatory mappings, a finding schema and implementation patterns. Current agent wiring is described under Integration below.
[!NOTE] This skill is a planning aid, not legal advice. Its standards summaries support privacy reasoning and review preparation; they do not substitute for qualified legal counsel or a formal regulatory interpretation.
Goal
Produce an evidence-based assessment against the 7 PbD Foundation Principles, with per-principle verdicts, explicit evidence gaps, deficiency severity, and remediation for established deficiencies. Assessment labels describe this planning rubric, not legal certification.
Success criteria
- All 7 principles have a verdict, evidence completeness, and severity (
N/Awhen no deficiency is established). - Each FAIL or PARTIAL finding includes a specific, actionable remediation.
- Findings use the structured schema defined in
finding-schema.md. - Cross-jurisdictional obligations are identified for the applicable regulatory scope.
- Retention and disposal are assessed for any system that stores personal data.
- An overall assessment verdict (COMPLIANT / PARTIALLY_COMPLIANT / NON_COMPLIANT / INCOMPLETE) is determined without treating missing evidence as a failed control.
- Finding, principle, checklist and severity counts reconcile under the finding schema.
When to use this skill
Use when you need to:
- Assess a system, feature, or data flow against the 7 PbD Foundation Principles
- Verify that privacy is embedded proactively (not bolted on after incidents)
- Check data retention schedules, disposal methods, and legal hold procedures
- Map privacy requirements across GDPR Art. 25, CCPA/CPRA, and Australian Privacy Principles
- Generate per-principle PASS/PARTIAL/FAIL/INSUFFICIENT_EVIDENCE results with evidence-backed severity
- Identify code-level and configuration-level privacy patterns or anti-patterns
- Produce backlog items from privacy assessment findings
What ships with it
14 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/00-principle-index.md 4.0 KB
- references/01-proactive-not-reactive.md 4.4 KB
- references/02-privacy-as-the-default.md 4.5 KB
- references/03-privacy-embedded-into-design.md 4.7 KB
- references/04-full-functionality.md 4.4 KB
- references/05-end-to-end-security.md 5.8 KB
- references/06-visibility-and-transparency.md 5.6 KB
- references/07-respect-for-user-privacy.md 5.5 KB
- references/assessment-protocol.md 9.7 KB
- references/cross-jurisdictional-mapping.md 13 KB
- references/data-retention-and-disposal.md 7.1 KB
- references/finding-schema.md 11 KB
- references/implementation-patterns.md 10 KB
- references/industry-privacy-profiles.md 11 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.
- 10d ago First seen · 187 lines · 48 tokens per session scan A f572bf9c0c92
privacy-by-design is a skill published in the GitHub repository microsoft/hve-core (1,606 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 2,633 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 2026-10-29.
privacy-by-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| privacy-by-designmicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 48 | Claude Code |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | yesterday | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | yesterday | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | today | MIT | A | 49 | Claude Code |
| regulatory-research-fallbackHKUDS/OpenSpace | Skill | 7.9k | 2d ago | MIT | A | 20 | Claude Code, Codex |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | today | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 8d ago | Apache-2.0 | A | 57 | Claude Code, Codex |