1. Habit
  2. Skills
  3. OpenAI Agents SDK skill
laguagu · 2K installs

OpenAI Agents SDK skill
Runs by itself, agents code changes.

Agent changes verified offline first.

Install the OpenAI Agents SDK skill and make it a habit: follow https://gethabit.dev/skills/laguagu/openai-agents-sdk.md

  1. 1Copy
  2. 2Paste into Claude Code, Codex or Cursor
  3. 3It runs by itself

2K installs71 starsMIT licenceSource on GitHub ↗

OpenAI Agents SDK

by laguagu · 2K installs

The skill

The openai agents sdk skill helps Python developers build agents with the openai-agents package: tools, handoffs, guardrails, sessions, streaming, tracing and offline testing.

Only when you ask.

The habit

Agent changes verified offline first.

↻ Runs by itselfagents code changes

How the habit works.
You don't have to.

Three questionsWhen does it start? How does it check its work? What does it remember?

01

It starts by itself

agents code changes. Runs in GitHub Actions or Claude Code routine.

  • ↻ agents code changes
  • pull_request touches files importing agents

02

It checks its work

offline tests pass. If a check fails, it tells you.

  • ✓ScriptedModel tests pass with model.assert_complete()
  • ✓no Runner.run_sync inside a running event loop
  • ✓every tool with side effects checks authorization
  • ✓project checks pass

03

It remembers

sdk test log. The next run reads it first: installed SDK version and last failures.

loops/openai-agents-test-loop/run-log.md

One run, step by step.
Then it stops.

Stop ruleStops after one pull request per run.

  1. 01

    Read the version

    Get the version with importlib.metadata and check exports in agents/__init__.py.

  2. 02

    Read references

    Read the reference for the changed feature, such as references/tools.md or references/sessions.md.

  3. 03

    Check patterns

    Confirm await Runner.run in async code and handoffs versus as_tool choices.

  4. 04

    Test offline

    Run ScriptedModel tests with RunConfig(tracing_disabled=True).

  5. 05

    Run checks

    Run the project's checks and report missing provider access separately.

What it may do.
Nothing more.

Safe by defaultIt writes only in its own folder and asks you before anything goes out.

Is it for you?
Use it when it fits.

Quick checkRead both lists. If the left one sounds like you, the OpenAI Agents SDK skill helps.

Use it when

  • ✓ You build agents in Python
  • ✓ You add function tools or handoffs
  • ✓ You test agent flows offline

Skip it when

  • – You use the TypeScript SDK
  • – You do not use openai-agents

Questions

OpenAI Agents SDK skill, answered.

Does it cover the TypeScript SDK?

No. The skill is Python only.

Which model should I use?

The skill says to pick from the current model catalog and keep the project's configured model.

How do I install the OpenAI Agents SDK skill?

Copy the prompt at the top into your agent. It installs the skill from laguagu/claude-code-nextjs-skills and sets up the habit. Or run npx skills add laguagu/claude-code-nextjs-skills --skill openai-agents-sdk.

Is the OpenAI Agents SDK skill free?

Yes. It is published under MIT. Habit is free too.

OpenAI Agents SDK. Now as a habit.

Install the OpenAI Agents SDK skill and make it a habit: follow https://gethabit.dev/skills/laguagu/openai-agents-sdk.md

  • Free
  • No account
  • Undo in one line

All laguagu skills →More code skills →

Works in

  • Claude Code
  • Codex
  • Cursor
  • ChatGPT
  • Claude app

Made by laguagu, published under MIT. Habit links to the original and never changes it. Is this your skill?

Copying didn't work here. Select the line and copy it by hand.