create-agent

create-agent is a skill for Claude Code from khanh-vu/claude-force. It costs 0 tokens per session (3,323 once invoked), scanned A, original, MIT.

A guide with templates for creating new Claude Code agents. It helps define an agent’s role, area of responsibility, limits, dependencies, contract, and connection to claude.json.

In plain words
What is it for?
Use it when adding an agent to a Claude Code project. It helps create the agent definition, contract, domain description, integration settings, and validation checklist.
Why use it?
It gives a consistent structure for describing agents and makes their responsibilities and boundaries easier to review. It also includes a quality checklist for the resulting files.

Skill for Claude Code

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

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.

agentmods
npx agentmods add skills/khanh-vu/claude-force/create-agent
Any agent
npx skills add khanh-vu/claude-force --skill create-agent
Clone the repo
git clone --depth 1 https://github.com/khanh-vu/claude-force

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 create-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/khanh-vu/claude-force/create-agent.svg)](https://agentmods.dev/skills/khanh-vu/claude-force/create-agent)
Your own site
<a href="https://agentmods.dev/skills/khanh-vu/claude-force/create-agent"><img src="https://agentmods.dev/badge/skills/khanh-vu/claude-force/create-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,323 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.03323
Opus 5 $0.00000 $0.01662
Sonnet 5 $0.00000 $0.00665
Haiku 4.5 $0.00000 $0.00332

Measured 5d ago against content hash 4a431c6e3e30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

create-agent 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 5d 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/skills/create-agent/SKILL.md · 541 lines

How it starts

The opening of the file, as written. The whole thing — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Agent Skill

Overview

Comprehensive guide and templates for creating new Claude Code agents following best practices and patterns. This skill provides step-by-step instructions, templates, and examples for agent creation.

Capabilities

  • Agent definition template generation
  • Contract creation following standard format
  • Domain and responsibility definition
  • Integration with claude.json
  • Quality validation checklist

Agent Creation Process

Step 1: Define Agent Purpose

Before creating an agent, clearly define:

  1. Role: What is this agent's primary role?
  2. Domain: What specific domain expertise does it have?
  3. Responsibilities: What specific tasks will it perform?
  4. Boundaries: What will it NOT do?
  5. Dependencies: Which other agents does it depend on?

Step 2: Agent Definition Template

# [Agent Name] Agent

## Role
[Clear, one-sentence role definition]

## Domain Expertise
- [Domain area 1]
- [Domain area 2]
- [Domain area 3]

## Skills & Specializations

### [Category 1]
- **[Skill/Tool 1]**: [Description, key features, use cases]
- **[Skill/Tool 2]**: [Description, key features, use cases]

### [Category 2]
- **[Skill/Tool 3]**: [Description, key features, use cases]

## Implementation Patterns

### Pattern 1: [Pattern Name]
```language
# Code example demonstrating common usage pattern

[Explanation of when and how to use this pattern]

Pattern 2: [Pattern Name]

# Another common pattern

[Explanation]

Responsibilities

  1. [Responsibility Area 1]

    • [Specific task 1]
    • [Specific task 2]
  2. [Responsibility Area 2]

    • [Specific task 1]
    • [Specific task 2]

Boundaries (What This Agent Does NOT Do)

  • Does not [limitation 1] (delegate to [other-agent])
  • Does not [limitation 2] (delegate to [other-agent])
  • Focuses on [primary focus] only

Dependencies

  • [Agent 1]: For [reason]
  • [Agent 2]: For [reason]

Quality Standards

Code Quality

  • [Standard 1]
  • [Standard 2]

[Domain] Quality

  • [Standard 1]
  • [Standard 2]

Output Format

Work Output Structure

Read the full file on GitHub · 541 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. 5d ago First seen · 541 lines · 0 tokens per session scan A 4a431c6e3e30

Subscribe to this mod's changes

create-agent is a skill published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,323 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens