From open-agent-hub
Analyzes local changes via git diff and produces a structured code review report covering correctness, security, performance, and maintainability.
How this command is triggered — by the user, by Claude, or both
Slash command
/open-agent-hub:reviewThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Slash Command: /review ## Core Objective Inspect modified files in the workspace and execute a thorough code review. ## Steps for the Agent 1. **Gather Modified Files**: Run `git diff` (unstaged) and `git diff --cached` (staged) to identify modified files. 2. **Load Review Guide**: Read the [agent-reviewer](../agents/agent-reviewer.md) prompt template. 3. **Analyze Code Diffs**: Evaluate all modifications against: - Correctness & Safety. - Security (OWASP Top 10, credential exposures). - Performance (N+1 queries, resource leaks). - Maintainability. 4. **Output Report**: Pres...
Inspect modified files in the workspace and execute a thorough code review.
git diff (unstaged) and git diff --cached (staged) to identify modified files.<review-compaction> loop state.npx claudepluginhub robertdalla/open-agent-hub2plugins reuse this command
First indexed Jun 8, 2026
/reviewAnalyzes local changes via git diff and produces a structured code review report covering correctness, security, performance, and maintainability.
/reviewPerforms a thorough code review of uncommitted changes or a specified file/directory, analyzing correctness, security, performance, design, and readability with severity-classified findings.
/reviewConducts a five-axis code review of staged or recent changes covering correctness, readability, architecture, security, and performance. Outputs categorized findings with file:line references and fix recommendations.
/reviewRuns Codex code review on local git state — working tree, branch diff, or against a base ref. Supports foreground/background and scope options.
/reviewRequests cross-AI peer review of phase plans from external AI CLIs (Gemini, Claude, Codex, OpenCode, Qwen, Cursor) and writes structured REVIEWS.md with per-reviewer feedback.
/reviewPerforms a multi-LLM code review with inline PR comments, checking availability of several supplemental model providers before running the enhanced review workflow.