Assess Patch Risk — Agent Skill by OpenAI

From the author

Assess an immutable patch artifact's program impact, regression risk, and auto-merge eligibility. Use for generated patch files, provider pull-request diffs, or commit ranges when reviewers need evidence about affected runtime paths, contracts, tests, and recoverability. This skill is read-only and does not generate, edit, apply, push, or merge the patch.

— the description by OpenAI

Install

Get the skill from its source (we cannot redistribute it):
https://github.com/openai/plugins/tree/d420d13051bffe4543ed39e30fa46b87148e47dd/plugins/codex-security/skills/assess-patch-risk

Documentation by OpenAI

The licence of this skill does not allow us to copy its documentation. Read it at the source

Files

SKILL.md(opens on GitHub)Not mirrored: opens on GitHub9.3 KiB
agents/openai.yaml(opens on GitHub)Not mirrored: opens on GitHub274 B
references/risk-rubric.md(opens on GitHub)Not mirrored: opens on GitHub4.9 KiB

Requirements and compatibility

Written for: OpenAI Codex

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Pr
Matt Pocock· Community
A standardized template and set of best practices for writing clear, evidence-based pull request descriptions.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Retro
Matt Pocock· Community
Conduct a structured retrospective on coding sessions to improve agent environment and performance.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Triage
Matt Pocock· Community
A systematic workflow for managing, verifying, and preparing project issues and pull requests for agent-led implementation.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Code Review
Matt Pocock· Community
Performs a dual-axis code review by comparing changes against project standards and functional specifications in parallel.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Requesting Code Review
Jesse Vincent (obra)· Community
A structured workflow for dispatching an AI subagent to perform automated code reviews on specific git commits.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository314k
Code Simplification
Addy Osmani· Community
A systematic, model-agnostic process for refactoring code to improve readability and maintainability without altering existing behavior.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository113.9k