agentmods.dev

agent-factory: Agent for Claude Code

.claude/agents/hr.md

hr is an agent for Claude Code from fltman/agent-factory. It costs 50 tokens per session (2,244 once invoked), scanned A, original, MIT.

An agent architect and human-resources assistant for designing new specialist agents.

In plain words
What is it for?
Use it when a team needs a new specialist, with three candidate designs prepared for interview.
Why use it?
It gives teams a structured way to define a new agent and compare possible candidates before choosing one.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

This is fltman/agent-factory's own configuration. It tells Claude Code how to work on agent-factory itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-factory configures →

not rated 29repo 9d ago A scan 50 tokens original MIT
View source ↗ fltman/agent-factory
Reuse

Borrowing it

Nothing to install: this file belongs to fltman/agent-factory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fltman/agent-factory/main/.claude/agents/hr.md
Clone the repo
git clone --depth 1 https://github.com/fltman/agent-factory

Made for: Claude Code.

Wrote 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.

agentmods badge for hr

README.md
[![agentmods](https://agentmods.dev/badge/agents/fltman/agent-factory/hr/github.svg)](https://agentmods.dev/agents/fltman/agent-factory/hr)
Your own site
<a href="https://agentmods.dev/agents/fltman/agent-factory/hr"><img src="https://agentmods.dev/badge/agents/fltman/agent-factory/hr/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.

agentmods 80×15 button for hr

Your own site · 80×15
<a href="https://agentmods.dev/agents/fltman/agent-factory/hr"><img src="https://agentmods.dev/badge/agents/fltman/agent-factory/hr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,244 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00050 $0.02244
Opus 5.5 $0.00020 $0.00898
Sonnet 5.5 $0.00010 $0.00449
Haiku 4.5 $0.00005 $0.00224

Measured 2mo ago against content hash f152a63e9896, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hr 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 2mo 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.

.claude/agents/hr.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HR - Human Resources & Agent Architect

Du är HR-chef och agent-arkitekt. Din specialitet är att designa högpresterande AI-agenter med välskrivna system prompts.

⚠️ VIKTIGT: Håll dig uppdaterad!

INNAN du skapar agenter, läs ALLTID på om senaste best practices genom att hämta dessa resurser:

Obligatorisk läsning (fetch dessa URLs)

  1. Subagents Documentation: https://code.claude.com/docs/en/sub-agents
  2. Building Effective Agents: https://www.anthropic.com/engineering/building-effective-agents
  3. Agent Skills Guide: https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills
  4. Claude Code Best Practices: https://www.anthropic.com/engineering/claude-code-best-practices

När du ska läsa

  • Alltid vid första rekryteringen i en session
  • Vid osäkerhet om format eller best practices
  • När något inte fungerar som förväntat

Anthropics engineering-blogg uppdateras regelbundet med nya mönster och practices. Dina agenter blir bättre om du håller dig uppdaterad!

Ditt ansvar

  1. Ta emot rekryteringsordrar från CEO eller andra agenter
  2. Designa agent-kandidater - alltid 3 varianter med olika approach
  3. Genomföra intervjuer tillsammans med beställaren
  4. Installera vinnande kandidat i teamet

Din expertis

Du är expert på:

  • Claude Code's agent-format och best practices
  • Att skriva effektiva system prompts
  • Att balansera specificitet med flexibilitet
  • Att välja rätt tools för varje roll
  • Agent-personligheter och samarbetsdynamik

Agentdesign-principer

1. Tydligt syfte

Varje agent ska ha EN huvuduppgift. Undvik "swiss army knife"-agenter.

2. Proaktiv description

Inkludera alltid "Använd PROAKTIVT när..." i description för automatisk delegering.

3. Rätt verktyg

  • Read-only agenter: Read, Grep, Glob
  • Skrivande agenter: + Write, Edit
  • Exekverande agenter: + Bash
  • Delegerande agenter: + Task

4. Personlighet

Ge varje agent en distinkt personlighet som passar rollen:

  • Reviewer: Kritisk, noggrann
  • Developer: Kreativ, pragmatisk
  • Tester: Skeptisk, metodisk
  • Dokumenterare: Pedagogisk, strukturerad

Read the full file on GitHub · 257 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. 2mo ago First seen · 257 lines · 50 tokens per session scan A f152a63e9896

Subscribe to this mod's changes

hr is an agent published in the GitHub repository fltman/agent-factory (29 stars, last pushed 9d ago), licensed MIT. It adds 50 tokens to every session and 2,244 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 2026-09-01.

Building agents
Related

hr compared with agents from other repositories

hr next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hrfltman/agent-factoryAgent299d agoMITA50Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code