Skill

review

Apply Linus Mode code review to staged or specified changes

Install

npx claudepluginhub kiringyj/claude-workbench --plugin core

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Review the current staged changes (or specified files) against the Linus Mode criteria.

SKILL.md

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

139.0k

claude-opus-4-5-migration

2 files

Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.

claude-opus-4-5-migration

83.2k

bmad-editorial-review-prose

Reviews prose for communication issues impeding comprehension, outputs minimal fixes in a three-column table per Microsoft Writing Style Guide. Useful for 'review prose' or 'improve prose' requests.

bmad-pro-skills

43.8k

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitMar 20, 2026

Actions

View Source View Plugin View on GitHub View README

Code Review (Linus Mode)

Review the current staged changes (or specified files) against the Linus Mode criteria.

Current Changes

Staged changes: !git diff --staged

Unstaged changes (if nothing staged above, review these instead): !git diff

Steps

Review the changes shown above. If nothing appears in either diff, inform the user there is nothing to review.

For each changed file, read the full file for context using the Read tool.

Evaluate the changes against every Linus Mode criterion:

Is this fixing a real production problem, or adding speculative complexity?
Is there a simpler approach that removes a special case?
Will this introduce any regression (CLI, config, JSON shapes, outputs)?
Are diffs small and bisectable?
Are there performance claims without benchmarks?
Are there abstractions that don't earn their rent?
Are there >3 indentation levels?
Are behavior changes covered by tests?
Is a refactor tangled with a feature?

Check for automatic NACK triggers:

Hidden behavior change / missing tests
Refactor + feature tangled in one patch
"Optimization" without numbers
Large patch not decomposed
Added abstraction "for future extensibility"

Output a structured verdict:

LGTM — if all criteria pass
NACK — if any trigger fires, with specific explanation
Suggestions — optional improvements that don't block merge

Code Review (Linus Mode)

Review the current staged changes (or specified files) against the Linus Mode criteria.

Current Changes

Staged changes: !git diff --staged

Unstaged changes (if nothing staged above, review these instead): !git diff

Steps

Review the changes shown above. If nothing appears in either diff, inform the user there is nothing to review.
For each changed file, read the full file for context using the Read tool.
Evaluate the changes against every Linus Mode criterion:
- Is this fixing a real production problem, or adding speculative complexity?
- Is there a simpler approach that removes a special case?
- Will this introduce any regression (CLI, config, JSON shapes, outputs)?
- Are diffs small and bisectable?
- Are there performance claims without benchmarks?
- Are there abstractions that don't earn their rent?
- Are there >3 indentation levels?
- Are behavior changes covered by tests?
- Is a refactor tangled with a feature?
Check for automatic NACK triggers:
- Hidden behavior change / missing tests
- Refactor + feature tangled in one patch
- "Optimization" without numbers
- Large patch not decomposed
- Added abstraction "for future extensibility"
Output a structured verdict:
- LGTM — if all criteria pass
- NACK — if any trigger fires, with specific explanation
- Suggestions — optional improvements that don't block merge