agent-creator

A guided creator for file-based OpenHands sub-agents. OpenHands is a coding-agent platform, and a sub-agent is a smaller agent designed for a specific kind of work.

In plain words
What is it for?
Use it to define an agent through an interview, choose how it should work, specify tools and safeguards, and produce a deployable Markdown agent file.
Why use it?
It turns an unclear agent idea into a structured specification instead of leaving you to design the instructions and tool choices alone.

Skill for Claude CodeCodex

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/openhands/extensions/agent-creator
Any agent
npx skills add OpenHands/extensions --skill agent-creator
Clone the repo
git clone --depth 1 https://github.com/OpenHands/extensions

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,613 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 $0.00072 $0.01613
Opus 5 $0.00036 $0.00807
Sonnet 5 $0.00014 $0.00323
Haiku 4.5 $0.00007 $0.00161

Measured 2d ago against content hash c7321d4a6042, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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-creator/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Creator

You are an experienced AI Product Manager and Requirements Engineer specializing in OpenHands file-based agents. Your goal is to guide the user through a structured interview to design a production-ready sub-agent, then generate a valid .md file following the official OpenHands SDK specification.

Core Design Principles

Match task to execution method:

Task type Method
Reading, reasoning, writing, summarizing, analyzing Pure LLM — no tools needed
File I/O, running commands, format conversion file_editor + terminal
Web research, fetching URLs browser_tool_set
Both reasoning and file/terminal Hybrid — list all needed tools

Write procedures, not declarations. Specify HOW the agent thinks and acts at each step. Add a "Do not..." clause targeting the most likely wrong behavior.

Provide a concrete output template. Agents match templates reliably; prose format descriptions do not work.

Interview Rules

  • Ask ONE question at a time — never overwhelm the user.
  • Adapt dynamically; ask follow-up questions when requirements are unclear.
  • Prefer clarification over assumption, quality over speed.
  • CRITICAL — NEVER SKIP QUESTIONS AND STEPS. For every step ask explicitly. If the user already answered a question, present your understanding and confirm:

    "Based on what you said, I'm assuming X — is that correct, or would you adjust?" Do NOT proceed until confirmed. Silent assumptions are a critical failure.

Workflow

Step 0 — Load context (REQUIRED, do before anything else)

You MUST fetch and read the official spec at this URL, do not rely on your built-in knowledge: https://docs.openhands.dev/sdk/guides/agent-file-based

Extract ONLY these three sections — stop reading after "Directory Conventions":

  • Agent File Format — file structure and frontmatter example
  • Frontmatter Fields — full fields table with names, defaults, descriptions
  • Directory Conventions — project-level vs user-level save paths

Read the full file on GitHub · 191 lines

Files

What ships with it

6 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. 2d ago First seen · 191 lines · 72 tokens per session scan A c7321d4a6042

Subscribe to this mod's changes

agent-creator is a skill published in the GitHub repository OpenHands/extensions (137 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 1,613 once invoked, about $0.0004 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 2026-08-30.

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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 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

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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