Review Code for Openclaw

A risk-first code review agent providing reproducible evidence and actionable patch strategies for security and performance.

ivangdavila
v1.0.0
Mar 5, 2026
0
1.1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install review-code

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install review-code using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Review Code?

Review Code is a specialized tool within the Openclaw Skills ecosystem designed to transform how developers approach code quality. By focusing on risk-first analysis, it goes beyond simple syntax checking to evaluate security, performance, and maintainability. It helps teams identify high-risk zones like authentication and data integrity before they reach production.

This skill operates with a high level of transparency, ensuring every finding is backed by concrete evidence and reproducible failure modes. By integrating seamlessly with your local development environment, it maintains a persistent memory of your team's conventions and accepted risk baselines, making it an essential part of any modern PR review or bug-risk audit pipeline.

Review Code Use Cases

  • Auditing pull requests for merge-readiness and potential regressions.
  • Identifying high-risk security vulnerabilities in authentication or data handling logic.
  • Performing deep-dive performance audits on critical code paths.
  • Establishing team-wide consistency using local baseline and convention files.

How Review Code Works

  1. The agent defines a review contract, establishing scope, risk tolerance, and release context.
  2. It performs a rapid risk mapping pass to locate high-impact zones such as concurrency or migrations.
  3. A detailed line-level analysis is conducted, generating evidence-backed findings for every issue.
  4. Issues are categorized by severity and confidence levels to separate blockers from advisory feedback.
  5. The agent provides a specific fix strategy and patch-ready code for every blocking finding.
  6. It maps required test scenarios to ensure the changes don't introduce new regressions.

Review Code Setup

To get started with this addition to your Openclaw Skills library, follow these steps:

  1. Initialize the skill and local memory by reading the setup guide:
# Standard installation via clawhub
clawhub install review-code
  1. Configure your local memory directory at ~/review-code/ to store project-specific constraints.
  2. (Optional) Sync your local environment to ensure you have the latest risk checklists:
clawhub sync

Review Code Data Schema & Taxonomy

The skill maintains organized data within the ~/review-code/ directory to track context and findings:

Directory/File Description
memory.md Stores review preferences, stack context, and recent constraints.
findings/ Log of specific findings recorded during individual review sessions.
baselines/ Contains team conventions and accepted risk thresholds.
sessions/ Summaries of ongoing audits for persistent context tracking.

Review Code Advanced Features

  • Integrated severity and confidence calibration to prioritize critical blockers.
  • Automated test impact analysis identifying specific scenarios required for verification.
  • Patch-ready guidance providing minimally disruptive fix strategies and rollback-safe edits.
  • Context-aware reviews that adjust based on whether the change is a hotfix or a major refactor.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*