メニュー
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/openai/openai-agents-python --skill code-change-verificationコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Analyze main branch implementation and configuration to find missing, incorrect, or outdated documentation in docs/. Use when asked to audit doc coverage, sync docs with code, or propose doc updates/structure changes. Only update English docs under docs/** and never touch translated docs under docs/ja, docs/ko, or docs/zh. Provide a report and ask for approval before editing docs.
Perform a risk-tiered zero-base final review loop before an implementation is declared complete. Use only when the user explicitly invokes $implementation-final-review or repository instructions authorize automatic invocation after implementation. Audit the complete merge-base diff for requirement fit, contract-surface coverage, await-boundary and lifecycle gaps, released compatibility, security, protocol, and persistence boundaries, unnecessary complexity, package and generated public surfaces, and adversarial test coverage; use compact self-contained reviewer packets and two concurrent no-history independent reviewers per round, defer broad final repository verification until review is clean and observable host capacity is available, preserve clean evidence for unchanged semantic components, close repeated root-cause groups instead of accumulating local patches, and enforce bounded review cycles in one task-global ledger.
Start and carry an explicitly invoked openai-agents-python implementation through a fresh isolated worktree and a local PR-ready handoff. Fetch the latest origin/main, keep task changes uncommitted, replay them onto the latest main before final review, run applicable verification and $implementation-final-review, use $pr-draft-summary to generate the complete PR draft and branch name, then create one clean local commit with takeover provenance when applicable. Use only when the user explicitly invokes this skill; never push, open a PR, or mutate GitHub.
SKILL.md を表示中
| name | code-change-verification |
| description | Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository. |
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.
./.agents/skills/code-change-verification so it loads automatically for the repository.env UV_DEFAULT_INDEX=https://pypi.org/simple bash .agents/skills/code-change-verification/scripts/run.sh.powershell -ExecutionPolicy Bypass -File .agents/skills/code-change-verification/scripts/run.ps1.make format first, then run make lint, make typecheck, and make tests in parallel with fail-fast semantics.make typecheck and the rest of this complete stack until review is clean.finalize message. If host telemetry is unavailable, do not block solely because capacity cannot be measured.The full test suite exercises UnixLocalSandboxSession, which starts its own macOS sandbox. A
nested run inside the Codex filesystem sandbox fails with
sandbox-exec: sandbox_apply: Operation not permitted even when the implementation is correct.
When Codex invokes the macOS/Linux verification command:
sandbox_permissions=require_escalated on the first invocation. The matching allow rule makes
this non-interactive; it does not require a new user approval.This execution policy changes only where the verification process runs. The SDK sandbox tests must remain enabled and unchanged.
The verification scripts assume repository dependencies are already installed. Do not run make sync as part of every verification pass; use it for a fresh checkout, after dependency files change, or when dependency resolution fails before the checks start.
On Linux, some Python packages with native extensions may require system packages such as libffi-dev, Python development headers, or build tools. If verification cannot start because one of these packages is missing, treat it as a local environment setup issue. Install the missing dependency when possible, or report the failing command and missing dependency in the PR test plan before rerunning verification in a prepared environment.
make sync first to install dev requirements via uv.make format first, then make lint, make typecheck, and make tests.make lint, make typecheck, and make tests after make format completes, but you must stop the remaining steps as soon as one fails.make format first, then runs make lint, make typecheck, and make tests in parallel with fail-fast semantics from the repository root. It also emits periodic heartbeat updates while the parallel steps are still running. Prefer this entry point to preserve the required ordering while reducing total runtime.make format first and the remaining steps in parallel with fail-fast semantics, plus periodic heartbeat updates while work is still running. Use from PowerShell with execution policy bypass if required by your environment.