requesting-code-review

Analyze staged git diffs for security risks and baseline-aware test regressions.

Updated May 16, 2026
One-click install
npx skills add https://github.com/jaredcroxton/hermes-mirror --skill requesting-code-review-jaredcroxton
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: requesting-code-review
Source: https://github.com/jaredcroxton/hermes-mirror/tree/main/agents/skills/software-development/requesting-code-review
Command: npx skills add https://github.com/jaredcroxton/hermes-mirror --skill requesting-code-review-jaredcroxton

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents insecure or buggy code from being committed by running a pre-commit verification pipeline that discovers issues early and blocks risky changes.

Core Features & Use Cases

  • Pre-commit diff verification: Extracts staged changes and flags high-risk patterns from added lines.
  • Baseline-aware quality gates: Captures existing failure counts, then blocks only regressions introduced by the new changes.
  • Independent fail-closed reviewer: Uses an isolated reviewer pass that treats malformed or suspicious findings as failures, then outputs a strict JSON verdict.
  • Auto-fix loop: Performs up to two targeted fix-and-reverify cycles by delegating fixes only for reported issues.

Use case: Before merging a feature that edits multiple files, run this skill to ensure no secrets, injection vectors, or logic issues slip in, and to confirm tests/lint don’t regress relative to baseline.

Quick Start

Run the requesting-code-review skill right before you commit staged changes to automatically scan security risks, run baseline-aware tests, and either approve or guide auto-fixes.

Frequently Asked Questions about requesting-code-review

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

FAQPage Schema
How do I run pre-commit code verification on staged git changes?

To verify staged changes, run the pre-commit pipeline to extract the git diff, perform targeted static security scans on added lines, count regressions against baseline failures, and obtain an independent reviewer verdict.

What does baseline-aware test regression checking do during a code review?

Baseline-aware checking captures existing failure counts, then blocks only new regressions introduced by the staged diff, ensuring pre-existing test or lint failures do not falsely block your commit.

Can I automatically fix security and linting issues before committing?

Yes, an auto-fix loop delegates fixes for reported issues and re-verifies the staged diff, running up to two targeted fix-and-reverify cycles to ensure commit readiness.

Does pre-commit security scanning check for secrets and injection vectors in added lines?

Yes, pre-commit security scanning extracts staged changes and flags high-risk patterns from added lines to identify secrets, injection vectors, and logic issues before you commit.

Why does an independent fail-closed reviewer block suspicious code findings?

An independent fail-closed reviewer blocks suspicious findings by treating malformed or suspicious results as failures, outputting a strict JSON verdict that prevents risky changes from being committed.