agent-creator

agent-creator is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 19 tokens per session (4,270 once invoked), scanned A, original, MIT.

A guide to designing Claude Code agents with specialized instructions, tool limits, model choices, and integrations.

In plain words
What is it for?
Use it to create new agents or refactor oversized agent definitions into focused configurations.
Why use it?
It helps separate an agent’s identity and responsibilities from general instructions, making the setup easier to maintain.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/validate-agent.sh .claude/agents/{agent-name}.md.

Good fit Use it to create new agents or refactor oversized agent definitions into focused configurations.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry
agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-creator

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/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-creator)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-creator"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-creator/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"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,270 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 $0.00019 $0.04270
Opus 5 $0.00010 $0.02135
Sonnet 5 $0.00004 $0.00854
Haiku 4.5 $0.00002 $0.00427

Measured 9d ago against content hash c5e4e46e47b5, 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/SKILL.md · 566 lines

How it starts

The opening of the file, as written. The whole thing — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: agent-creator description: Use this skill when architecting new Claude Code agents following Anthropic best practices. Guides through YAML frontmatter creation, agent structure definition, role boundaries, and validation. Critical for creating minimal agent files (~150 lines) with proper skill invocations. Examples: Context: User wants to create a new agent for security auditing user: "Create a security-auditor agent" assistant: "I'll use the agent-creator skill to build this agent following Anthropic best practices" New agent creation requires the agent-creator skill to ensure proper structure and YAML frontmatter. Context: Existing agent file is too verbose and needs refactoring user: "The architect agent is 2000 lines, refactor it to minimal structure" assistant: "I'll use the agent-creator skill to refactor this into a minimal ~150 line agent with a separate skill file" Agent refactoring requires the agent-creator skill to separate identity from technical procedures. color: orange

Agent Creator Skill

Purpose: Guide creation of Claude Code agents following Anthropic official best practices.

When to use: Creating new agents, refactoring existing agents, validating agent structure.


🎯 Core Principles

Agent Structure Philosophy

  • Minimal agents (~150 lines): Only identity, role, boundaries, and skill invocation
  • Comprehensive skills: All technical procedures, workflows, and references
  • Progressive disclosure: Metadata → Agent .md → SKILL.md → References (on demand)
  • Mandatory skill invocation: Agents MUST invoke their skill before work

Separation of Concerns

Agent .md (150 lines)           Skill SKILL.md (varies)
├─ YAML frontmatter             ├─ Technical workflows
├─ Identity & role              ├─ Context7 checkpoints
├─ Authority & boundaries       ├─ MCP integrations
├─ Workspace isolation          ├─ Best practices
├─ Mandatory skill call         ├─ Code patterns
└─ Quick reference              └─ References/ (on demand)

Read the full file on GitHub · 566 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 · 566 lines · 19 tokens per session scan A c5e4e46e47b5

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 19 tokens to every session and 4,270 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 2026-09-03.