Code review commands

rhuss/cc-spex

Command

Push and create PR for team review, with optional watch mode for CI monitoring.

Aedelon/claude-code-blueprint

Command

Code review of selected code or last diff.

harnessworks/harness-starter-kit

Command

Review the current change set from an opposing harness-engineering perspective.

fletchgqc/agentbox

Command Claude Code

Executes multiple review cycles and amalgamates the results.

fletchgqc/agentbox

Command Claude Code

Conducts code review.

kylesnowschwartz/SimpleClaude

Command

Part of sc-refactor

Multi-model adversarial review using external AI CLIs (Codex, Gemini) and Claude for diverse-perspective critique of any target.

kylesnowschwartz/SimpleClaude

Command

Part of sc-refactor

Context-aware PR review with ticket integration and multi-phase validation.

GGGODLIN/claude-pr-review

Command

Multi-axis PR review (CC context-aware + Codex neutral & adversarial + Gemini Flash; optional Gemini Pro) with Traditional Chinese comparison report.

dtsola/xiaoyaoprivatebill

Command Claude Code

Code review a pull request.

linggen/linggen-memory

Command

Part of linggen

Drain the memory review queue — solve each item from evidence, ask the user only when evidence can't settle it.

assafkip/kipi-system

Command

Part of kipi-dsse

Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.

SimplyLiz/ckb

Command Claude Code

Run a CKB-augmented code review optimized for minimal token usage.

cpj-dev/dsh-plugin-cc

Command

Part of dsh

A read-only command that reviews local code changes. It checks uncommitted work, or compares the current branch with its default base when the working tree is clean.

opentrace/opentrace

Command Claude Code

Fetch PR review comments, fix the issues, reply to threads, and push. Pass a PR number as argument, or omit to use the current branch's PR. Use this command when: "check pr comments", "fix pr feedback", "address review comments" "resolve pr comments", "review-pr", "handle pr comments" After pushing code that has been…

microsoft/Agent365-Samples

Command Claude Code ✓ vendor

Automatically resolve code review comments that are marked as "Agent Resolvable: Yes" from a review generated by /review-pr or /review-staged.

microsoft/Agent365-Samples

Command Claude Code ✓ vendor

Review code changes in a specific pull request using a comprehensive multi-agent code review process with specialized reviewers for security, patterns, quality, and standards.

microsoft/Agent365-Samples

Command Claude Code ✓ vendor

Review staged (uncommitted) changes using a comprehensive multi-agent code review process. Use this before committing to get feedback on your changes.

suntay44/web-to-mobile-magic-plugin

Command

Part of web-to-mobile-magic-plugin

Senior-level deep review of an existing mobile app. Reads targeted source files to analyze architecture, code quality, robustness, performance, and security. Produces a prioritized findings report.

beevibe-ai/beevibe-cto

Command

Part of adr

Discover the team's code-review principles from their own repo. Scans for code-review lenses (state-boundaries, llm-call-discipline, etc.), extracts positive patterns + antipatterns + ambiguities with file:line citations, walks the user through an interactive interview to confirm, and writes .adr/principles.{md,json}.…

sonpiaz/evox

Command Claude Code

Review code changes for quality and correctness. Argument: file path, PR number, or "staged" for staged changes.

closedloop-ai/claude-plugins

Command

Part of code-review

Run comprehensive code review — locally or on GitHub PRs with inline comments.

KaimingWan/oh-my-kiro

Command

Command "evaluate" from KaimingWan/oh-my-kiro, covering step 1: resolve evaluation target, step 2: gather context, step 3: dispatch 4 parallel evaluator subagents, subagent #2: "product manager" — alignment and subagent #3: "breaker" — correctness + robustness.

ForestHubAI/edge-agents

Command Claude Code

Perform a thorough audit of the React canvas in ts/workflow-builder/src/ against five categories. Use Agent subagents to explore categories in parallel where possible.

aderegil/claude-certified-architect

Command Claude Code

Review the file at $ARGUMENTS for code quality issues.