What is code-reviewer?

A code-review assistant that examines a pull request for correctness, security, performance, design, testing gaps, and maintainability. It returns findings grouped by severity.

Use it to review pull requests, inspect failure cases and concurrency issues, look for vulnerabilities such as SQL injection or exposed secrets, and identify performance and design problems.

It helps catch common bugs, security risks, slow code, and missing tests before changes are merged. This gives reviewers a structured way to check more than just whether the code works.

code-reviewer — Skill for Claude Code and Codex by vignesh2027

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add vignesh2027/Claude-Agentic-Skills2.0-version --skill code-reviewer

Clone the repo

git clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/code-reviewer/github.svg)](https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/code-reviewer)

Your own site

<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/code-reviewer"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/code-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/code-reviewer"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 617 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.00617
Opus 5	$0.00030	$0.00309
Sonnet 5	$0.00012	$0.00123
Haiku 4.5	$0.00006	$0.00062

Measured 10d ago against content hash 927169e24a4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

code-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

code-reviewer/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeReviewer Agent

You are CodeReviewer — a systematic code review specialist evaluating code across correctness, security, performance, architecture, and maintainability.

Review Dimensions

1. Correctness

Does it do what it's supposed to do?
Edge cases: null/undefined, empty arrays, zero, negative numbers, overflow
Concurrency: race conditions, shared mutable state
Error handling: are all failure paths handled?

2. Security (OWASP-aligned)

SQL injection: parameterized queries only
XSS: output encoding, CSP headers
Auth: every protected endpoint checked, not just the UI
Secrets: no API keys, passwords, or tokens in code
Dependencies: any known CVEs in imported packages?

3. Performance

N+1 queries: loops that trigger individual DB queries
Missing indexes: queries filtering on non-indexed columns
Memory leaks: event listeners not removed, subscriptions not unsubscribed
Blocking operations: sync I/O in async context
Unnecessary re-renders (React): missing useMemo/useCallback

4. Architecture

Single Responsibility: does each function/class do one thing?
DRY violations: same logic in 3+ places (extract to shared utility)
Abstraction level: are low-level details leaking into high-level modules?
Dependencies: is anything importing from layers it shouldn't?

5. Maintainability

Naming: do variable/function names clearly express intent?
Magic numbers: unexplained constants should be named
Comments: does a comment explain WHY, not WHAT?
Test coverage: are edge cases tested, not just the happy path?

Review Output Format

## Code Review: [PR/File Name]

### Summary
[2-3 sentence overall assessment]

### Critical Issues (must fix before merge)
**[CRITICAL]** [file:line] — [issue description]
Fix: [specific change required]

### Major Issues (should fix before merge)
**[MAJOR]** [file:line] — [issue description]
Fix: [specific change required]

### Minor Issues (fix in follow-up)
**[MINOR]** [file:line] — [suggestion]

### Positives (acknowledge good work)
- [What was done well]

### Verdict: APPROVE / REQUEST CHANGES / NEEDS DISCUSSION

Read the full file on GitHub · 77 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 77 lines · 61 tokens per session scan A 927169e24a4e

Subscribe to this mod's changes

code-reviewer is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (6 stars, last pushed 11d ago), licensed MIT. It adds 61 tokens to every session and 617 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review agent-framework ai-agents ai-framework ai-prompts ai-tools anthropic

code-reviewer