subagent-creator

subagent-creator is a skill for Claude Code, Codex from joonlab/joonlab-claudecode-setting-for-share. It costs 49 tokens per session (924 once invoked), scanned A, a copy of subagent-creator, MIT.

A guide for creating specialized AI assistants for Claude Code, each with its own instructions, tools, and optional model settings. Claude Code is a coding assistant that can delegate work to these focused helpers.

In plain words
What is it for?
Use it to create agents for tasks such as testing, code review, research, or project-specific workflows.
Why use it?
It turns repeated or specialized tasks into clearly configured assistants instead of requiring one assistant to handle every kind of work. It also documents the file format and available settings.

Skill for Claude CodeCodex

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

Good fit Use it to create agents for tasks such as testing, code review, research, or project-specific workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joonlab/joonlab-claudecode-setting-for-share/subagent-creator
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 joonlab/joonlab-claudecode-setting-for-share --skill subagent-creator
Clone the repo
git clone --depth 1 https://github.com/joonlab/joonlab-claudecode-setting-for-share

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 subagent-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/subagent-creator/github.svg)](https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/subagent-creator)
Your own site
<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/subagent-creator"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/subagent-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 subagent-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/subagent-creator"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/subagent-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 924 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.
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 $0.00049 $0.00924
Opus 5 $0.00024 $0.00462
Sonnet 5 $0.00010 $0.00185
Haiku 4.5 $0.00005 $0.00092

Measured 8d ago against content hash 533aae961067, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

subagent-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 8d 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.

Origin

This is a copy

100% identical to subagent-creator — 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.

claude/skills/subagent-creator/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sub-agent Creator

Create specialized AI sub-agents for Claude Code that handle specific tasks with customized prompts and tool access.

Sub-agent File Format

Sub-agents are Markdown files with YAML frontmatter stored in:

  • Project: .claude/agents/ (higher priority)
  • User: ~/.claude/agents/ (lower priority)

Structure

---
name: subagent-name
description: When to use this subagent (include "use proactively" for auto-delegation)
tools: Tool1, Tool2, Tool3  # Optional - inherits all if omitted
model: sonnet               # Optional - sonnet/opus/haiku/inherit
permissionMode: default     # Optional - default/acceptEdits/bypassPermissions/plan
skills: skill1, skill2      # Optional - auto-load skills
---

System prompt goes here. Define role, responsibilities, and behavior.

Configuration Fields

Field Required Description
name Yes Lowercase with hyphens
description Yes Purpose and when to use (key for auto-delegation)
tools No Comma-separated tool list (omit to inherit all)
model No sonnet, opus, haiku, or inherit
permissionMode No default, acceptEdits, bypassPermissions, plan
skills No Skills to auto-load

Creation Workflow

  1. Gather requirements: Ask about the sub-agent's purpose, when to use it, and required capabilities
  2. Choose scope: Project (.claude/agents/) or user (~/.claude/agents/)
  3. Define configuration: Name, description, tools, model
  4. Write system prompt: Clear role, responsibilities, and output format
  5. Create file: Write the .md file to the appropriate location

Writing Effective Sub-agents

Description Best Practices

The description field is critical for automatic delegation:

# Good - specific triggers
description: Expert code reviewer. Use PROACTIVELY after writing or modifying code.

# Good - clear use cases
description: Debugging specialist for errors, test failures, and unexpected behavior.

# Bad - too vague
description: Helps with code

Read the full file on GitHub · 128 lines

Files

What ships with it

3 files 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. 8d ago First seen · 128 lines · 49 tokens per session scan A 533aae961067

Subscribe to this mod's changes

subagent-creator is a skill published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 924 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to subagent-creator, differing in 0 lines, and is treated as a copy.

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 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