requesting-code-review

Verifies git diffs with security scans, baseline tests, and independent reviewer subagents before commits.

Updated Jun 7, 2026
One-click install
npx skills add https://github.com/Chensihakniroth/ANAKOT-AGENT --skill requesting-code-review-chensihakniroth
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: requesting-code-review
Source: https://github.com/Chensihakniroth/ANAKOT-AGENT/tree/main/skills/software-development/requesting-code-review
Command: npx skills add https://github.com/Chensihakniroth/ANAKOT-AGENT --skill requesting-code-review-chensihakniroth

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code changes often get committed without independent verification, letting security vulnerabilities, logic errors, and test regressions slip into the repository because the same agent that wrote the code also reviewed it. ## Core Features & Use Cases - Static Security Scanning: Greps added diff lines for hardcoded secrets, shell injection, eval/exec, unsafe pickle deserialization, and SQL injection patterns. - Baseline-Aware Quality Gates: Runs pytest, npm test, cargo test, or go test plus linters like ruff, mypy, eslint, and clippy, blocking only NEW failures introduced by your changes. - Independent Reviewer Subagent: Dispatches a fresh-context reviewer via delegate_task that returns a fail-closed JSON verdict on security concerns and logic errors. - Auto-Fix Loop: Spawns a separate fix agent for up to 2 fix-and-reverify cycles before escalating unresolved issues to the user. - Use Case: After implementing a feature across multiple files, run this pipeline before git commit to catch a leaked API key and a broken test, auto-fix them, and commit with a [verified] prefix. ## Quick Start Verify my staged changes with a security scan and independent review before committing them.

Frequently Asked Questions about requesting-code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I review code changes before committing in git?▼

Run git diff --cached to capture staged changes, scan added lines for secrets and injection patterns, then run the project's test suite and linters. An independent reviewer subagent evaluates the diff and returns a JSON pass/fail verdict before the commit proceeds.

How to detect hardcoded secrets in a git diff?▼

Pipe git diff --cached through grep for added lines matching patterns like api_key, secret, password, or token assigned to quoted strings. Any match is treated as a security concern that blocks the commit until fixed.

What is the difference between pre-commit review and GitHub PR review?▼

Pre-commit review verifies your own local changes before they are committed, using static scans and an independent subagent. GitHub PR review examines other people's pull requests on GitHub and posts inline comments on the platform.

Does the verification work if no test framework is installed?▼

Yes. If no test framework is detected, the regression check is skipped silently and the reviewer subagent verdict still runs. Missing lint tools are also skipped without failing the pipeline.

What happens when the auto-fix loop keeps failing verification?▼

The pipeline allows a maximum of 2 fix-and-reverify cycles using a separate fix agent. If issues remain after both attempts, it escalates to the user with the remaining problems and suggests git stash or git reset to undo the changes.

When should I skip pre-commit code verification?▼

Skip verification for documentation-only changes, pure configuration tweaks, or when the user explicitly says to skip it. It is designed for code changes involving two or more file edits in a git repository.