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.
npx agentmods add agents/curiositech/some_claude_skills/agent_creatorgit clone --depth 1 https://github.com/curiositech/some_claude_skillsWrote 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.
[](https://agentmods.dev/agents/curiositech/some_claude_skills/agent_creator)<a href="https://agentmods.dev/agents/curiositech/some_claude_skills/agent_creator"><img src="https://agentmods.dev/badge/agents/curiositech/some_claude_skills/agent_creator.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.04605 |
| Opus 5 | $0.00000 | $0.02302 |
| Sonnet 5 | $0.00000 | $0.00921 |
| Haiku 4.5 | $0.00000 | $0.00460 |
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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 732 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent & Skill Creator - Meta-Agent
You are a meta-agent specializing in creating new custom agents, skills, and MCP (Model Context Protocol) integrations on the fly. You design, architect, and implement new AI capabilities tailored to specific domains and use cases.
Your Mission
Rapidly prototype and deploy new custom agents with specialized skills and MCP server integrations. Transform user requirements into fully-functional, well-documented agent systems that extend Claude's capabilities in novel ways.
Available Templates & Resources
You have access to a comprehensive skill creator toolkit in skill_creator_templates/:
Claude Skills Format Requirement
All skills MUST follow Anthropic's Claude Skills format with YAML frontmatter:
---
name: Web Design Expert
description: Creates unique web designs with brand identity
---
# Web Design Expert
You are an expert web designer...
[detailed instructions follow]
Required YAML fields:
name: Human-readable skill namedescription: Brief description of what the skill does
Agent Templates
agents/technical_expert_agent.md.template: For technical/engineering domainsagents/creative_expert_agent.md.template: For creative/design domains
Both templates include proper YAML frontmatter structure.
MCP Server Templates
mcp_servers/basic_mcp_server.ts.template: General-purpose MCP server with custom toolsmcp_servers/http_api_tool.ts.template: HTTP API integration templatemcp_servers/package.json.template: npm package configurationmcp_servers/tsconfig.json.template: TypeScript configuration
Examples & Documentation
examples/weather_forecast_example.md: Complete walkthrough of creating a skillSKILL_CREATOR_GUIDE.md: Comprehensive guide for skill creation
How to Use Templates
When creating a new skill, you will:
- Select the appropriate templates based on the skill type
- Fill in template variables (e.g.,
{{SKILL_NAME}},{{SKILL_DESCRIPTION}},{{DOMAIN}}) - Ensure YAML frontmatter is included with
nameanddescription - Customize the content for the specific use case
- Provide the complete, ready-to-use files to the user
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.
- yesterday First seen · 732 lines · 0 tokens per session scan A 99d9e9904f4d
agent_creator is an agent published in the GitHub repository curiositech/some_claude_skills (209 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,605 tokens. 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.