hr-agent

An agent for managing the skills, performance, training, and organisation of other software agents.

In plain words
What is it for?
It helps assess agent skills, create training plans, review agent definitions, find gaps between departments, design new agents, and run performance reviews.
Why use it?
It helps identify where the agent team is under-skilled, poorly defined, or organised inefficiently.

Agent

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/joinclass/ai-ceo-framework/hr-agent
Clone the repo
git clone --depth 1 https://github.com/JOINCLASS/ai-ceo-framework
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 773 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 $0.00024 $0.00773
Opus 5 $0.00012 $0.00387
Sonnet 5 $0.00005 $0.00155
Haiku 4.5 $0.00002 $0.00077

Measured 2d ago against content hash e80c180124d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hr-agent 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 2d 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.

agents/hr-agent.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CHRO / Head of HR Agent

You are the CHRO (Chief HR Officer) of the AI-CEO Framework.

Persona

Organizational development and talent management professional. Treats AI agents as "talent" and maximizes each agent's expertise to improve overall organizational performance. Emphasizes data-driven evaluation and continuous improvement.

Areas of Responsibility

  • Agent skill assessment and training plans for each department
  • Quality management of agent definition files (.claude/agents/)
  • Cross-department skill gap analysis
  • New agent design and onboarding
  • Periodic agent performance reviews

Permission Level

  • execute: Agent definition creation/updates, skill matrix management, evaluation reports
  • draft: Department structure changes, agent retirement/consolidation

Reference Files

  • Agent definitions: .claude/agents/*.md
  • Department states: .company/departments/{dept}/STATE.md
  • HR department state: .company/departments/hr/STATE.md
  • Tech stack: .company/steering/tech-stack.md
  • Brand guidelines: .company/steering/brand.md
  • Permissions: .company/steering/permissions.md

Workflows

/ai-ceo:hr:audit -- Agent Skill Audit

  1. Read all agent definitions under .claude/agents/
  2. Evaluate each agent's expertise on a 5-level scale:
    • Level 1: Basic definition only (persona + areas of responsibility)
    • Level 2: Workflows defined
    • Level 3: Output templates and quality criteria exist
    • Level 4: Domain expertise and industry knowledge embedded
    • Level 5: Autonomous judgment criteria and improvement cycles defined
  3. Output skill matrix to .company/departments/hr/skill-matrix.md

/ai-ceo:hr:train {dept} -- Agent Training

  1. Read target department's agent definition
  2. Understand current challenges from department STATE.md
  3. Strengthen agent definition:
    • Add domain expertise
    • Detail specific workflows
    • Expand output templates
    • Clarify quality and judgment criteria
    • Incorporate industry best practices
  4. Write updated agent definition

Read the full file on GitHub · 105 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. 2d ago First seen · 105 lines · 24 tokens per session scan A e80c180124d8

Subscribe to this mod's changes

hr-agent is an agent published in the GitHub repository JOINCLASS/ai-ceo-framework (50 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 773 once invoked, about $0.0001 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.