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-reference-checkinggit 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-reference-checking)<a href="https://agentmods.dev/skills/tuanductran/hr-skills/hr-reference-checking"><img src="https://agentmods.dev/badge/skills/tuanductran/hr-skills/hr-reference-checking/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-reference-checking"><img src="https://agentmods.dev/badge/skills/tuanductran/hr-skills/hr-reference-checking.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 | $0.00060 | $0.00755 |
| Opus 5 | $0.00030 | $0.00378 |
| Sonnet 5 | $0.00012 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
hr-reference-checking 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 9d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference checking
Design and conduct structured reference checks that validate candidate claims, surface performance signal beyond the interview process, and stay legally sound across jurisdictions.
Supported tasks
- Designing structured reference check question sets by role and level
- Preparing candidates on how the reference process will work
- Selecting the right references to request (manager, peer, direct report)
- Conducting reference calls and documenting responses consistently
- Handling reluctant, guarded, or "policy only confirms dates" references
- Interpreting mixed or lukewarm references accurately
- Escalating and handling a clearly negative reference
- Complying with jurisdiction-specific reference-check and disclosure rules
- Using back-channel references responsibly and ethically
- Combining reference feedback with interview and assessment data
- Documenting reference outcomes for audit and compliance purposes
- Training hiring managers to conduct references consistently
Key prompts
Designing the process
- "Design a structured reference check question set for [role/level] covering performance, collaboration, and areas for development."
- "What references should we request for [role] — direct manager, peers, direct reports — and why?"
- "Draft guidance for candidates explaining how our reference check process works and what to expect."
- "How many references should we require for [role/level], and does that number change for senior or executive hires?"
Conducting the call
- "Write opening and closing scripts for a reference check call that build rapport and get candid answers."
- "How do I get useful signal from a reference who is only willing to confirm dates and title?"
- "Draft follow-up questions to ask when a reference gives a vague or generic positive answer."
- "How should the reference check approach differ for an internal mobility move versus an external hire?"
Interpreting results
- "How should I interpret a reference that is polite but notably lukewarm compared to the candidate's other references?"
- "What questions can distinguish a genuinely strong reference from a scripted, overly positive one?"
- "A reference raised a specific concern about [area] — how do we weigh this against strong interview performance?"
- "How do we compare conflicting signals when one reference is strongly positive and another is strongly negative?"
What ships with it
4 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.
- 9d ago First seen · 65 lines · 60 tokens per session scan A 6db993dd3379
hr-reference-checking is a skill published in the GitHub repository tuanductran/hr-skills (58 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 755 once invoked, about $0.0003 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 2026-09-03.
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…