Files
claude-howto/07-plugins/pr-review/README.md
T
Luong NGUYEN b9a973bf32 docs: accuracy pass against Claude Code v2.1.220 (#155)
Internal accuracy pass against v2.1.220 — no missing upstream features, but broken example code, disagreeing counts, and metadata drift.

Functional fixes: pre-commit.sh now exits 2 so it actually blocks; dependency-check.sh reads file_path from stdin JSON instead of $1; database-mcp.json uses ${DATABASE_URL}; broken fences repaired; three command templates had invalid skill names.

Factual corrections: /fork and /subtask unswapped and /subtask added; /fewer-permission-prompts; permissions.defaultMode; dontAsk/auto unreversed; 31 hook events verified name-by-name; subagent depth 3; skill precedence enterprise > project > personal; /output-style removed not deprecated; permissionDecision gained defer.

Follow-up review fixed defects the pass left behind: zh/vi headers claiming 31 events above 25-name lists, a surviving hardcoded DB credential in the MCP README examples, an unbalanced fence swallowing a metadata footer, and non-canonical tool names. All four translated CATALOG summary tables were recounted so their arithmetic holds.

Full detail in CHANGELOG.md under v2.1.220-r2.
2026-08-04 15:41:12 +07:00

103 lines
2.2 KiB
Markdown

<picture>
<source media="(prefers-color-scheme: dark)" srcset="../../resources/logos/claude-howto-logo-dark.svg">
<img alt="Claude How To" src="../../resources/logos/claude-howto-logo.svg">
</picture>
# PR Review Plugin
Complete PR review workflow with security, testing, and documentation checks.
## Features
✅ Security analysis
✅ Test coverage checking
✅ Documentation verification
✅ Code quality assessment
✅ Performance impact analysis
## Installation
```bash
/plugin install pr-review
```
## What's Included
### Slash Commands
- `/review-pr` - Comprehensive PR review
- `/check-security` - Security-focused review
- `/check-tests` - Test coverage analysis
### Subagents
- `security-reviewer` - Security vulnerability detection
- `test-checker` - Test coverage analysis
- `performance-analyzer` - Performance impact evaluation
### MCP Servers
- GitHub integration for PR data
### Hooks
- `pre-review.js` - Pre-review validation
## Usage
### Basic PR Review
```
/review-pr
```
### Security Check Only
```
/check-security
```
### Test Coverage Check
```
/check-tests
```
## Requirements
- Claude Code 2.1+
- GitHub access
- Git repository
## Configuration
Set up your GitHub token:
```bash
export GITHUB_TOKEN="your_github_token"
```
## Example Workflow
```
User: /review-pr
Claude:
1. Runs pre-review hook (validates git repo)
2. Fetches PR data via GitHub MCP
3. Delegates security review to security-reviewer subagent
4. Delegates testing to test-checker subagent
5. Delegates performance to performance-analyzer subagent
6. Synthesizes all findings
7. Provides comprehensive review report
Result:
✅ Security: No critical issues found
⚠️ Testing: Coverage is 65%, recommend 80%+
✅ Performance: No significant impact
📝 Recommendations: Add tests for edge cases
```
---
**Last Updated**: August 4, 2026
**Claude Code Version**: 2.1.220
**Sources**:
- https://code.claude.com/docs/en/plugins
- https://github.com/anthropics/claude-code/releases/tag/v2.1.131
- https://github.com/anthropics/claude-code/releases/tag/v2.1.138
- https://code.claude.com/docs/en/model-config
**Compatible Models**: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5