Code Change Verification

This runs the full verification stack for the OpenAI Agents Python repository whenever you touch runtime code, tests, or build config. It executes make format first, then parallelizes lint, typecheck, and tests with fail-fast semantics so you catch issues quickly without waiting for every check to finish. The scripts emit heartbeat updates so you know work is still running. Skip it for docs-only changes unless someone specifically asks for the full suite. The discipline here is simple: nothing is complete until all checks pass, and you rerun the entire stack after fixes to preserve the required ordering.

skills.sh installs: 200
GitHub stars: 30.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add openai/openai-agents-python --skill code-change-verification --agent claude-code

Installs into .claude/skills of the current project.

Files

Code Change Verification

Overview

Ensure work is only marked complete after formatting, linting, type checking, and tests pass. Use this skill when changes affect runtime code, tests, or build/test configuration. You can skip it for docs-only or repository metadata unless a user asks for the full stack. This is a post-review final gate: when $implementation-final-review applies, do not invoke the broad stack until its clean-review condition applies to the stable task diff.