# assess-patch-risk

This skill examines a fixed patch artifact to assess its program impact, regression exposure, and case for automatic merging. Use it when reviewing proposed changes.

- skill · `type=skill` · Codex, ChatGPT · ★ 7604
- Author: OpenAI · official OpenAI repository
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/openai/plugins/tree/HEAD/plugins/codex-security/skills/assess-patch-risk/SKILL.md
- Updated: 2026-10-08
- HTML: https://affpapa.org/en/nevibecode/skills/assess-patch-risk

## What it does

The skill accepts a fixed patch file, a provider’s final pull-request comparison, or a commit range with defined endpoints. It traces affected runtime paths, contracts, and state, then separates the potential damage of a defect from the chance of one occurring. Its assessment also covers test protection, recovery options, and how complete the available evidence is.

Before rating risk or merge eligibility, it consults a risk rubric. The review checks relevant boundaries such as authorization, data handling, and migrations, and considers what tests actually cover. It returns a recommendation to merge, revise, reject, take no action, or gather more evidence. The skill is read-only: it will not apply or push changes. It requires a fixed artifact rather than a changing working tree.

## Install

### Codex (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/plugins --skill assess-patch-risk -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/assess-patch-risk/SKILL.md` — For all projects use ~/.agents/skills/

### Claude Code

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/plugins --skill assess-patch-risk -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/assess-patch-risk/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/assess-patch-risk/

### Cursor

**Manually: put the files in place**
- File: `.cursor/skills/assess-patch-risk/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install openai/plugins assess-patch-risk
```

2. **Manually: put the files in place**
- File: `.github/skills/assess-patch-risk/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/openai/plugins --path plugins/codex-security/skills/assess-patch-risk
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/assess-patch-risk/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/openai/plugins/tree/HEAD/plugins/codex-security/skills/assess-patch-risk/SKILL.md

## When to use it
- trace a patch’s effect on live application paths
- separate regression probability from potential damage
- check whether tests cover the changed behavior
- assess rollback options and automatic-merge eligibility

## Example prompts
- Review this fixed patch and trace its impact through the application.
- Assess the pull-request diff for regression risk, test coverage, and automatic-merge eligibility.
- Analyze this commit range using the supplied base and head, then recommend whether to merge.

## Similar
- [improve-codebase-architecture](https://affpapa.org/en/nevibecode/skills/improve-codebase-architecture.md) — skill · 1163035 installs
- [tdd](https://affpapa.org/en/nevibecode/skills/tdd.md) — skill · 1141062 installs
- [triage](https://affpapa.org/en/nevibecode/skills/triage.md) — skill · 990453 installs
- [codebase-design](https://affpapa.org/en/nevibecode/skills/codebase-design.md) — skill · 850344 installs
- [code-review](https://affpapa.org/en/nevibecode/skills/code-review.md) — skill · 789521 installs
- [implement](https://affpapa.org/en/nevibecode/skills/implement.md) — skill · 774700 installs

From the same set: [openai/plugins](https://affpapa.org/en/nevibecode/by/openai/plugins.md) — 528 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md