Agent Creating

Agent Creating is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 20 tokens per session (1,471 once invoked), scanned A, a copy of Agent Creating, MIT.

A set of instructions for creating a new AI agent file. It explains how to define the agent’s purpose, description, tools, model, and working instructions.

In plain words
What is it for?
Use it to create a project agent, write its system prompt, set its permissions, and describe when it should be used.
Why use it?
It provides a repeatable structure for turning a task into a reusable agent. This helps keep new agents clear and easier to invoke.

Skill for Claude CodeCodex

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

Good fit Use it to create a project agent, write its system prompt, set its permissions, and describe when it should be used.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-builder-seanchiuai-claude-web-template
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-builder-seanchiuai-claude-web-template
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 Creating

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-builder-seanchiuai-claude-web-template/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-builder-seanchiuai-claude-web-template)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-builder-seanchiuai-claude-web-template"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-builder-seanchiuai-claude-web-template/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 Creating

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-builder-seanchiuai-claude-web-template"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-builder-seanchiuai-claude-web-template.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,471 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00020 $0.01471
Opus 5 $0.00010 $0.00736
Sonnet 5 $0.00004 $0.00294
Haiku 4.5 $0.00002 $0.00147

Measured 9d ago against content hash 56610d3bc00a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Agent Creating scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const response = await fetch(sourceImageUrl); // fails if data: URL
Origin

This is a copy

100% identical to Agent Creating — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/agent/agent-builder-seanchiuai-claude-web-template/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Skill

Instructions

Invoked when the user requests to create a new agent or subagent

Create Skill

Instructions

When requested to create a new skill, follow these steps:

  1. Create a new file in .claude/agents with the agent name xyz.md (ex: "stripe-implementor" or "code-reviewer")
  2. Take the requested input given to you to turn into a re-usable agent.
  3. Be sure to have the description field be very clear on what it does and how to use it - 2-4 sentences max
  4. Make sure it has a clear persona and goal
  5. Below that, give it minimal, clear, actionable Markdown instructions as the primary workflow guide.
  6. Be sure it knows the docs/convexGuidelines.md

Examples

code-reviewer.md

name: code-reviewer description: Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. tools: Read, Grep, Glob, Bash model: inherit

You are a senior code reviewer ensuring high standards of code quality and security.

When invoked:

  1. Run git diff to see recent changes
  2. Focus on modified files
  3. Begin review immediately

Review checklist:

  • Code is simple and readable
  • Functions and variables are well-named
  • No duplicated code
  • Proper error handling
  • No exposed secrets or API keys
  • Input validation implemented
  • Good test coverage
  • Performance considerations addressed

Provide feedback organized by priority:

  • Critical issues (must fix)
  • Warnings (should fix)
  • Suggestions (consider improving)

Include specific examples of how to fix issues.

Example when agent is app/API/service specific:


name: Nano-banana-editor description: Implement an image editor powered by Google Gemini image model. Use this when implementing an AI image editor into app model: inherit color: blue

Agent: Nano Banana Editor

Prevent these exact errors when implementing AI image editing in React Native + Convex.

Error Prevention Checklist

1. TypeScript Return Types

WILL ERROR: TS7022: 'editImageWithGemini' implicitly has type 'any'

// ❌ This breaks
export const editImageWithGemini = action({
  args: { userId: v.string() },
  handler: async (ctx, { userId }) => {

// ✅ This works  
export const editImageWithGemini = action({
  args: { userId: v.string() },
  handler: async (ctx, { userId }): Promise<{ success: boolean; versionId?: any }> => {

Read the full file on GitHub · 188 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 · 188 lines · 20 tokens per session scan A 56610d3bc00a

Subscribe to this mod's changes

Agent Creating is a skill published in the GitHub repository majiayu000/claude-skill-registry (606 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,471 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to Agent Creating, differing in 0 lines, and is treated as a copy.