code review plus

    1

    A structured multi-hunter code review pipeline that finds bugs, audits security, and automates fixes.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    code review plus

    Example session with this skill installed

    /code-review-plus performance review this diff for latency bottlenecks

    • Read your context and instructions
    • Compiled the code review plus
    • Generated the document

    I have completed the performance audit for the provided diff. The review focused on execution hotpaths and memory allocation.

    Performance Review Report

    IDSeverityHunterFindingFile:Line
    1P1PerformanceNested loop results in O(N^2) complexity on main threadsrc/processor.ts:42
    2P2PerformanceUnnecessary object spreading in high-frequency filtersrc/utils/filter.ts:12
    3P3PerformanceRedundant logging in production telemetry pathsrc/logger.ts:89

    Synthesis

    The primary concern is the quadratic complexity in processor.ts, which will cause UI blocking on larger datasets. The object spreading in the filter utility is contributing to minor GC pressure but is less critical than the loop structure.

    Persistence

    Report saved to docs/code-review/2023-10-27_1430_perf.md.

    Next steps

    1. Run /code-review-plus fix 1 to apply the optimized loop implementation.
    2. Run /code-review-plus fix all to address the P2 and P3 findings simultaneously.
    3. Review docs/code-review/ to see how these findings compare to previous sessions.

    code-review-plus.pdf

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Static code analysis often misses the architectural context, while manual reviews are slow and inconsistent. This skill provides a structured multi-hunter pipeline to audit PRs for bugs, security vulnerabilities, and performance bottlenecks.

    The skills is free on my Github, the $5 amount is a way to show your appreciation for the work behind this project.

    What it does

    • Multi-perspective auditing uses specific hunters for correctness, security, architecture, quality, and performance.
    • Automated remediation applies fixes for identified P0 and P1 issues directly to the source code.
    • Regression gating ensures that suggested fixes do not introduce new issues during the application phase.
    • Finding persistence logs review history to docs/code-review/ for long-term tracking and false-positive management.
    • Sensitive data redaction automatically masks secrets and credentials in reports and fixes.

    How it works

    1. Scope the review by calling /code-review-plus with an optional hunter name to define the audit depth.
    2. Review the generated report to identify P0, P1, and high-priority vulnerability findings.
    3. Fix issues by running /code-review-plus fix to apply priority patches or target specific finding IDs.
    4. Prune old review logs using the prune command to maintain a clean documentation directory.

    Why this beats prompting it yourself

    Generic prompts often return a mix of nits and critical errors without clear prioritization. This skill uses a tiered pipeline and a "Pass B" verification step to filter out false positives and ensure that every P0/P1 finding is proven.

    Use cases

    • Audit pull requests for logical errors and architectural alignment before merging.
    • Scan for hardcoded secrets and security vulnerabilities in new code diffs.
    • Automate the application of style and quality fixes across a large changeset.
    • Maintain a persistent audit trail of code reviews within the repository.

    Known limitations

    Requires a review report or history file to be present before the fix command can be used. Secrets are redacted by default and cannot be recovered through the report.

    Requires a previous review report or history file to execute fixes. Secrets are automatically redacted in outputs.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    Node.js

    Permissions

    Network Access
    Read Files
    Listed1 month ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions

    Code Review Plus uses a 'multi-hunter' pipeline that assigns specific agents to different domains like security, performance, and architecture, filtering out minor 'nits' to focus on high-priority P0/P1 fixes.

    Yes, the skill includes a `fix` command that can automatically apply patches for identified bugs and security vulnerabilities directly to your source code. You can run `/code-review-plus fix` to fix blocking findings, `/code-review-plus fix 1,2` to fix findings 1 and 2, `/code-review-plus fix all` to fix all findings.

    The skill is designed to work within standard development environments.

    All findings and audit trails are stored locally in your repository's `docs/code-review/` directory, ensuring you have a persistent, version-controlled history of every review.

    The skill includes an automated redaction layer that masks secrets and credentials in both reports and suggested fixes, preventing sensitive data from leaking into logs.

    You receive the full structured pipeline, including the multi-hunter auditing logic, the automated remediation engine, and the regression gating system for safe code updates.

    New in Code Quality & Review