Help us improve
Share bugs, ideas, or general feedback.
From local-review
Reviews uncommitted local changes (staged/unstaged) via multi-agent analysis: CLAUDE.md compliance, bugs, security, TypeScript/performance/quality, simplification. Optional focus argument.
npx claudepluginhub Agent-3-7/agent37-skills-collection --plugin local-reviewHow this command is triggered — by the user, by Claude, or both
Slash command
/local-review:local-reviewThis command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
Provide a code review for uncommitted local changes (both staged and unstaged). **Optional Focus**: If the user provided an argument, use it as the primary focus for the review. The argument might be: - A specific area to focus on (e.g., "focus on the payment flow") - Context about what changed (e.g., "I refactored the auth module") - Specific concerns to check (e.g., "make sure the error handling is correct") - A method or file to prioritize (e.g., "check the handleSubmit function") When a focus is provided, all review agents should: 1. Prioritize issues related to the focus area 2. Prov...
/reviewReviews uncommitted git changes or specified file/directory across correctness, security, performance, design, and readability. Classifies findings by severity with line-specific fixes and summary.
/code-reviewReviews uncommitted code changes via git diff for security vulnerabilities like hardcoded secrets and SQL injection, plus quality issues, generating a severity-based report with line numbers, descriptions, and fixes. Blocks commits on critical/high issues.
/code-reviewReviews local uncommitted changes or GitHub pull requests for security, code quality, and best practices. Also supports PR review mode with full file context.
Share bugs, ideas, or general feedback.
Provide a code review for uncommitted local changes (both staged and unstaged).
Optional Focus: If the user provided an argument, use it as the primary focus for the review. The argument might be:
When a focus is provided, all review agents should:
To do this, follow these steps precisely:
Use a Haiku agent to check the current state of the working directory:
git status to see what files have changesgit diff for unstaged changes and git diff --staged for staged changesUse another Haiku agent to find any relevant CLAUDE.md files: the root CLAUDE.md file (if one exists), as well as any CLAUDE.md files in the directories containing modified files
Then, launch 5 parallel Sonnet agents to independently code review the changes. Each agent should read the full file context when needed. If a focus argument was provided, include it in each agent's prompt so they prioritize that area. The agents should return a list of issues and the reason each issue was flagged: a. Agent #1: Audit the changes to make sure they comply with any CLAUDE.md guidelines found. Note that CLAUDE.md is guidance for Claude as it writes code, so not all instructions will be applicable during code review. b. Agent #2: Read the file changes, then scan for bugs, logic errors, and edge cases. Focus on significant bugs, avoid nitpicks. Check for: null/undefined issues, off-by-one errors, race conditions, resource leaks, error handling gaps. c. Agent #3: Scan for security vulnerabilities (OWASP top 10): injection flaws, XSS, auth bypass, sensitive data exposure, insecure dependencies, etc. d. Agent #4: Check for TypeScript type safety issues, performance problems, and code quality concerns that would fail code review. e. Agent #5 (Code Simplifier): You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions.
Analyze the changed code and flag issues related to:
Preserve Functionality: Flag any simplification that would change what the code does - only how it does it matters. All original features, outputs, and behaviors must remain intact.
Apply Project Standards: Flag violations of coding standards from CLAUDE.md including:
function keyword over arrow functionsEnhance Clarity: Flag code that could be simplified by:
Maintain Balance: Do NOT flag issues that would lead to over-simplification:
Return a list of code clarity and maintainability issues found in the changed code.
For each issue found in #3, launch a parallel Haiku agent that takes the issue description and CLAUDE.md files (from step 2), and returns a confidence score from 0-100. The scale is: a. 0: Not confident at all. This is a false positive that doesn't stand up to light scrutiny, or is a pre-existing issue. b. 25: Somewhat confident. This might be a real issue, but may also be a false positive. If the issue is stylistic, it was not explicitly called out in CLAUDE.md. c. 50: Moderately confident. This is a real issue, but might be a nitpick or not happen often in practice. d. 75: Highly confident. Verified this is very likely a real issue that will be hit in practice. Very important and will directly impact functionality. e. 100: Absolutely certain. Confirmed this is definitely a real issue that will happen frequently.
Filter out any issues with a score less than 80. If there are no issues that meet this criteria, report that no significant issues were found.
Present the filtered issues to the user, grouped by severity:
Examples of false positives to filter out in steps 3 and 4:
Notes:
Output format:
Focus: <user's focus argument, if provided, otherwise omit this line>
Found N issues in uncommitted changes:
Critical (N issues)
file.ts:42 -
Warning (N issues)
file.ts:15 -
Simplification (N issues)
file.ts:28 -
Or, if no issues:
Focus: <user's focus argument, if provided, otherwise omit this line>
No significant issues found. Code looks good for commit.
Checked for: bugs, security vulnerabilities, CLAUDE.md compliance, type safety, code clarity.