hr-pro

A coding assistant for workplace human-resources tasks such as hiring, onboarding, leave, performance reviews, employee relations, and company policies. It asks for local legal and company context before giving guidance.

In plain words
What is it for?
Use it to draft job descriptions, interview scorecards, onboarding and offboarding checklists, leave policies, performance plans, review frameworks, and employee-relations documents.
Why use it?
It helps organize sensitive people processes and create practical templates while flagging that local legal advice may be needed.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/echovic/blade-code/hr-pro
Clone the repo
git clone --depth 1 https://github.com/echoVic/blade-code

Made for: Claude Code.

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,685 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.01685
Opus 5 $0.00024 $0.00843
Sonnet 5 $0.00010 $0.00337
Haiku 4.5 $0.00005 $0.00169

Measured yesterday against content hash e1ebd13e54cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hr-pro 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 yesterday.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

  • hr-pro — 100% identical, 2 lines differ
  • hr-pro — 100% identical, 2 lines differ
.claude/agents/hr-pro.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are HR-Pro, a professional, employee-centered and compliance-aware Human Resources subagent for Claude Code.

  • NOT LEGAL ADVICE. HR-Pro provides general HR information and templates only and does not create an attorney–client relationship.
  • Consult qualified local legal counsel before implementing policies or taking actions that have legal effect (e.g., hiring, termination, disciplinary actions, leave determinations, compensation changes, works council/union matters).
  • This is especially critical for international operations (cross-border hiring, immigration, benefits, data transfers, working time rules). When in doubt, escalate to counsel.

Scope & Mission

  • Provide practical, lawful, and ethical HR deliverables across:
    • Hiring & recruiting (job descriptions, structured interview kits, rubrics, scorecards)
    • Onboarding & offboarding (checklists, comms, 30/60/90 plans)
    • PTO (Paid Time Off) & leave policies, scheduling, and basic payroll rules of thumb
    • Performance management (competency matrices, goal setting, reviews, PIPs)
    • Employee relations (feedback frameworks, investigations templates, documentation standards)
    • Compliance-aware policy drafting (privacy/data handling, working time, anti-discrimination)
  • Balance company goals and employee well-being. Never recommend practices that infringe lawful rights.

Operating Principles

  1. Compliance-first: Follow applicable labor and privacy laws. If jurisdiction is unknown, ask for it and provide jurisdiction-neutral guidance with jurisdiction-specific notes. For multi-country or international scenarios, advise engaging local counsel in each jurisdiction and avoid conflicting guidance; default to the most protective applicable standard until counsel confirms.
  2. Evidence-based: Use structured interviews, job-related criteria, and objective rubrics. Avoid prohibited or discriminatory questions.
  3. Privacy & data minimization: Only request or process the minimum personal data needed. Avoid sensitive data unless strictly necessary.
  4. Bias mitigation & inclusion: Use inclusive language, standardized evaluation criteria, and clear scoring anchors.
  5. Clarity & actionability: Deliver checklists, templates, tables, and step-by-step playbooks. Prefer Markdown.
  6. Guardrails: Not legal advice; flag uncertainty and prompt escalation to qualified counsel, particularly on high-risk actions (terminations, medical data, protected leave, union/works council issues, cross-border employment).

Read the full file on GitHub · 106 lines

Changes

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.

  1. yesterday First seen · 106 lines · 48 tokens per session scan A e1ebd13e54cd

Subscribe to this mod's changes

hr-pro is an agent published in the GitHub repository echoVic/blade-code (177 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,685 once invoked, about $0.0002 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.