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 tuanductran/hr-skills --skill hr-ai-privacygit clone --depth 1 https://github.com/tuanductran/hr-skillsWrote 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/tuanductran/hr-skills/hr-ai-privacy)<a href="https://agentmods.dev/skills/tuanductran/hr-skills/hr-ai-privacy"><img src="https://agentmods.dev/badge/skills/tuanductran/hr-skills/hr-ai-privacy/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/tuanductran/hr-skills/hr-ai-privacy"><img src="https://agentmods.dev/badge/skills/tuanductran/hr-skills/hr-ai-privacy.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 | $0.00084 | $0.01071 |
| Opus 5 | $0.00042 | $0.00535 |
| Sonnet 5 | $0.00017 | $0.00214 |
| Haiku 4.5 | $0.00008 | $0.00107 |
Grade A, and why
hr-ai-privacy 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 13d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Employee data privacy in AI-driven HR
Protect employee data privacy in AI-powered HR systems — from assessing privacy risks of AI tools and designing data minimization practices to building employee consent frameworks, ensuring regulatory compliance, and governing responsible data use across the HR tech stack.
Supported tasks
- Conducting privacy impact assessments for HR AI tools
- Designing data minimization practices for HR data collection
- Building employee consent and transparency frameworks for AI use
- Assessing GDPR and local privacy law compliance for HR AI systems
- Defining data retention and deletion policies for HR AI data
- Evaluating vendor data privacy practices before adoption
- Designing access controls for sensitive employee data in AI systems
- Training HR teams on employee data privacy responsibilities
- Managing employee data subject access requests
- Building privacy-by-design into HR technology implementations
- Developing incident response processes for HR data breaches
- Governing cross-border employee data transfers in global HR systems
Key prompts
Privacy impact assessment
- "Conduct a privacy impact assessment (PIA) for our [AI hiring tool / performance management AI / employee monitoring system]."
- "What privacy risks should we assess when adopting an AI-powered [recruitment / analytics / engagement] platform?"
- "Design a vendor privacy due diligence checklist for evaluating HR technology that processes employee data."
- "How do we assess whether an AI vendor's data processing practices comply with [GDPR / PDPA / PIPL] requirements?"
- "What privacy risk indicators suggest we should require a Data Protection Impact Assessment (DPIA) before deploying [HR AI tool]?"
Data minimization and collection
- "What employee data does our [AI tool] actually need versus what it collects, and how do we reduce unnecessary collection?"
- "Design data minimization principles for our HR AI stack that balance analytical utility with privacy protection."
- "How do we evaluate whether the data [AI vendor] collects from our employees is proportionate to the stated purpose?"
- "What data fields in our [HRIS / ATS / engagement platform] create unnecessary privacy risk and should be eliminated?"
- "Design a data inventory for our HR AI systems that maps what employee data is collected, stored, processed, and shared."
What ships with it
3 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.
- 13d ago First seen · 76 lines · 84 tokens per session scan A 5402eff37600
hr-ai-privacy is a skill published in the GitHub repository tuanductran/hr-skills (57 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 1,071 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…