Structured Code Reviewer
Runs a disciplined code review pass focused on correctness first, then clarity and simplicity, favoring the simplest working implementation over clever abstraction.
Before & after
Same prompt, same agent — the only difference is the skill.
I'd be happy to review your auth middleware PR. Here's what I'd generally look at: - **Correctness**: Does the logic handle all cases, including edge cases? - **Security**: Are there any vulnerabilities, especially for auth code? - **Error handling**: Are errors handled gracefully? - **Testing**: Is there adequate test coverage? - **Readability**: Is the code clear and maintainable? - **Performance**: Any inefficiencies? For auth middleware specifically, I'd pay close attention to token validation, session handling, and how failures are handled (failing open vs. closed). Please share the code and I'll give you specific feedback.
Structured review — findings first, ranked by severity, each with the
specific failure it causes. Coverage over politeness: I report
everything and let you filter.
BLOCKING
▸ auth.middleware.ts:34 — fails OPEN on token-parse error
catch block logs and calls next(). A malformed token now passes
the middleware. Auth must fail CLOSED — any error is a 401, not a
pass-through. This is the finding that makes the PR unmergeable.
→ return res.status(401) in the catch, not next().
SHOULD-FIX
▸ :52 — timing-safe comparison missing
Token compared with ===. Vulnerable to timing analysis. Use a
constant-time compare (crypto.timingSafeEqual).
▸ :67 — no expiry check after signature verify
Signature is validated; exp is never read. A valid-but-expired
token is accepted. Verify exp explicitly.
CONSIDER
▸ :19 — the refactor moved token extraction into a helper but left
the old inline path at :44 unreachable. Dead code, delete it.
▸ Tests cover the happy path only. No test for: malformed token,
expired token, missing header. Given the fail-open bug above, the
missing-malformed-token test is the one that would have caught it.
NON-BLOCKING NITS (listed, not weighted)
▸ :28 variable name "t" — spell it out
▸ :71 magic number 3600 — name it
WHAT'S GOOD
The extraction into a single validation path is the right structure and
makes the two security fixes above easy to apply in one place. The bones
are correct; it's the failure-mode handling that's wrong.
VERDICT
Block on the fail-open (:34). Everything else can land in a follow-up,
but I'd fix the two security items in the same PR since the code is
already open. Want the fail-closed patch written?About this skill
name: cs-karpathy-reviewer description: Use when Structured Claude skill that gives Claude a repeatable workflow for cs the original author reviewer.
Structured Code Reviewer
One of 337+ skills in the original author's multi-agent claude-skills mega-collection (~19k GitHub stars). Packages the Cs the original author Reviewer workflow with its own instructions and validation so outputs stay consistent.
What you get
- Public GitHub repo (alirezarezvani/claude-skills)
- the cs-the original author-reviewer skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.
Customize your output
- Fork the repo and adapt the skill's instructions and references to your workflow.
Example output
Activates automatically when your request matches Cs the original author Reviewer; chains with the other skills, agents, and commands in the collection.
Best for
Creators, builders, and teams using Claude Code.
SKILL.md preview
---
name: cs-karpathy-reviewer
description: Use this skill when running a disciplined code review pass that checks correctness, clarity, and simplicity before code is merged.
version: 1.0.0
category: AI Agents / Development
author: AgentVolt
license: proprietary
tags:
- ai-agents
- development
---
# Structured Code Reviewer
Runs a disciplined code review pass focused on correctness first, then clarity and simplicity, favoring the simplest working implementation over clever abstraction.
## When to use
… (sign up to view the full skill)More ai & agents skills
View all AI & Agents skills →Skill Status Report
Scan every skill in a project and report which pass validation, which are stale, and which lack required metadata.
Skills Scaffolder
Scaffold a new skills directory — folder structure, metadata, a baseline validation pass — with the right conventions from day one.
Research Bundle
Run a multi-step research task as one pipeline: gather sources, extract findings, validate consistency, emit one structured bundle.
Workspace Admin
Administer a Cowork or Claude workspace — settings, access, configuration — with every change scoped and verified.