A development guide for building, adapting, running, and testing apps with the OpenAI Agents SDK, a toolkit for creating software agents. It also points to current OpenAI documentation and handles API key setup before API work.

Use it to create an agent from an idea or existing code, define its inputs and outputs, connect tools, set approval boundaries, and add evaluations when needed.

It gives the agent a clear build order and keeps the first implementation small and testable. This reduces guesswork about project structure, tools, permissions, and reliability checks.

agents-sdk — Skill for Claude Code by openai

About the project

OpenAI Developers for Claude Code is a Claude Code plugin bundle that connects OpenAI developer documentation and workflow guidance to Claude Code. It helps users build AI applications, agents, and ChatGPT Apps from Claude Code, including setup, troubleshooting, Agents SDK development, and app submission. The catalogue entries are the plugin's skills, plugin metadata, and documentation MCP integration.

openai/openai-developers-for-claude · 23 stars · on GitHub

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 openai/openai-developers-for-claude --skill agents-sdk

Clone the repo

git clone --depth 1 https://github.com/openai/openai-developers-for-claude

Made for: Claude Code.

Or install openai-developers, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/openai/openai-developers-for-claude/agents-sdk.svg)](https://agentmods.dev/skills/openai/openai-developers-for-claude/agents-sdk)

Your own site

<a href="https://agentmods.dev/skills/openai/openai-developers-for-claude/agents-sdk"><img src="https://agentmods.dev/badge/skills/openai/openai-developers-for-claude/agents-sdk.svg" alt="Measured on agentmods" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 303 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.00303
Opus 5	$0.00023	$0.00151
Sonnet 5	$0.00009	$0.00061
Haiku 4.5	$0.00005	$0.00030

Measured 8d ago against content hash f91ad8834e38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agents-sdk 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.

plugins/openai-developers/skills/agents-sdk/SKILL.md · 34 lines

What it actually says

Agents SDK

Use this skill to turn an idea or repo into a focused Agents SDK implementation.

Before You Build

Use openai-docs to inspect current Agents SDK guidance.
If the work will call the OpenAI API, use openai-platform-api-key before building, running, testing, or debugging the API-backed path.
Inspect the repo's existing language, package manager, entrypoints, and testing style before choosing a structure.

Workflow

Define the agent contract:
- goal
- user input
- expected output
- tools
- approval or escalation boundaries
Prefer the smallest runnable implementation first.
Use tools deliberately and keep side effects narrow.
Add evals when the user asks for reliability, comparison, or regression coverage.
Provide a local run command and a concrete smoke result when implementation is requested.

Guidance

Prefer Python unless the repo or user already points to TypeScript.
Start with one agent before introducing handoffs or orchestration.
Keep prompts, tools, tests, and deployment artifacts clearly separated.
Use openai-docs again when current SDK behavior or product guidance is central to the answer.

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.

8d ago First seen · 34 lines · 45 tokens per session scan A f91ad8834e38

Subscribe to this mod's changes

agents-sdk is a skill published in the GitHub repository openai/openai-developers-for-claude (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 303 once invoked, about $0.0002 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.

Building agents

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

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