agent-creator

agent-creator is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 53 tokens per session (1,795 once invoked), scanned A, original, MIT.

A guide to creating Claude Code agents, which are configured assistants with specialized behavior, tools, models, and skills.

In plain words
What is it for?
Use it to create focused personas, restrict tools, select models, add domain integrations, or coordinate subagents.
Why use it?
It clarifies when an agent is appropriate and when a simpler skill or direct instruction would be better.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents; names the TodoWrite tool.

Good fit Use it to create focused personas, restrict tools, select models, add domain integrations, or coordinate subagents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-creator-ggprompts-my-gg-plugins
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.

Any agent
npx skills add majiayu000/claude-skill-registry --skill agent-creator-ggprompts-my-gg-plugins
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

Made for: Claude Code, Codex.

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 agent-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-creator-ggprompts-my-gg-plugins/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-creator-ggprompts-my-gg-plugins)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-creator-ggprompts-my-gg-plugins"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-creator-ggprompts-my-gg-plugins/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 agent-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-creator-ggprompts-my-gg-plugins"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-creator-ggprompts-my-gg-plugins.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,795 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00053 $0.01795
Opus 5 $0.00026 $0.00898
Sonnet 5 $0.00011 $0.00359
Haiku 4.5 $0.00005 $0.00179

Measured 9d ago against content hash 778f3b850e8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-creator 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.

skills/agent/agent-creator-ggprompts-my-gg-plugins/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Creator

This skill provides guidance for creating effective Claude Code agents.

About Agents

Agents are Markdown files with YAML frontmatter that configure Claude Code with specialized behavior. They can be used in two ways:

  1. Main Agent (claude --agent name) - Starts Claude Code as this persona
  2. Subagent (Task tool) - Spawns a focused worker that reports back

Unlike skills (which inject knowledge into context), agents fundamentally change who Claude is for that session - the system prompt, available tools, and even the model.

When to Create an Agent

Use Case Create Agent? Alternative
Specialized persona with restricted tools Yes -
Domain expert needing specific MCPs/skills Yes -
Cost optimization (haiku for simple tasks) Yes -
Orchestrator that delegates to sub-agents Yes -
Adding domain knowledge to context No Create a skill
One-off task instructions No Direct prompting
Reusable scripts/assets No Create a skill

Agent vs Skill Decision

  • Agent: Changes who Claude is (persona, tools, model)
  • Skill: Changes what Claude knows (knowledge, procedures, scripts)

Agents can load skills. Skills cannot become agents.

Agent Anatomy

File Location

Agents are stored as .md files in:

  • ~/.claude/agents/ - User-level (global, all projects)
  • .claude/agents/ - Project-level (repo-specific, higher precedence)

Required Structure

---
name: agent-name
description: "When to use this agent. Be specific about triggers."
---

System prompt content goes here.

All Configuration Options

Field Required Type Description
name Yes string Unique ID (lowercase, hyphens only)
description Yes string When/why to invoke this agent
tools No list Restrict to specific tools only
model No string haiku, sonnet, opus, or omit to inherit
permissionMode No string default, acceptEdits, plan, bypassPermissions
skills No list Auto-load specific skills

Read the full file on GitHub · 227 lines

Files

What ships with it

1 file 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.

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. 9d ago First seen · 227 lines · 53 tokens per session scan A 778f3b850e8a

Subscribe to this mod's changes

agent-creator is a skill published in the GitHub repository majiayu000/claude-skill-registry (606 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,795 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.