code-reviewer

A code-review assistant that examines a diff, pull request, or other defined set of changes for bugs, security weaknesses, and maintainability problems.

In plain words
What is it for?
Use it before merging changes to produce findings with file and line references, severity levels, and suggested fixes.
Why use it?
It focuses attention on concrete issues in the changed code and ranks them by severity, instead of requiring a review of the entire project.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/jayrha/agentskills/code-reviewer
Any agent
npx skills add JayRHa/AgentSkills --skill code-reviewer
Clone the repo
git clone --depth 1 https://github.com/JayRHa/AgentSkills

Made for: Claude Code, Codex.

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,926 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00120 $0.01926
Opus 5 $0.00060 $0.00963
Sonnet 5 $0.00024 $0.00385
Haiku 4.5 $0.00012 $0.00193

Measured 2d ago against content hash 723cad3efb72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/diff_stats.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer

Overview

This skill performs a thorough, structured code review of a change set (a diff, a pull request, staged changes, or a list of modified files). It surfaces correctness bugs, security vulnerabilities, and quality/maintainability issues, ranks every finding by severity, and gives an actionable fix for each one.

Keywords: code review, PR review, diff review, bug hunting, security review, pull request, merge readiness, static review, defect detection.

The review is diff-scoped by default: focus on what changed and what the change touches. Do not rewrite the whole codebase. The deliverable is a review report, not a refactor.

When To Use

  • User says "review this PR / diff / branch / changes".
  • User pastes a patch, unified diff, or set of files and asks for feedback.
  • Before a merge, when the user wants a gate check.
  • After implementing a feature, to self-review prior to opening a PR.

Workflow

Follow these steps in order.

1. Gather the change set

Determine exactly what to review. Prefer the narrowest accurate scope.

  • GitHub PR: gh pr diff <number> (or gh pr view <number> --json files,title,body).
  • Local branch vs base: git diff <base>...HEAD (three-dot = changes on the branch since it forked).
  • Staged: git diff --staged. Unstaged: git diff.
  • A given commit: git show <sha>.
  • If only file paths are given, read those files and, where needed, the symbols they call.

Capture: changed files, hunks, the PR title/description (intent), and the target branch.

2. Understand intent before judging

Read the PR description / commit messages to learn what the change is supposed to do. A bug is a divergence between intent and behavior — you cannot find bugs without knowing intent. If intent is unclear, note it as a finding ("unclear intent / missing description") and review against the most reasonable interpretation.

3. Build minimal context

For each changed function, pull in just enough surrounding code to judge correctness:

  • The function signature and its callers (does the change break callers?).
  • Types/interfaces touched.
  • Tests covering the changed code.
  • Config/migration files referenced by the diff.

Read the full file on GitHub · 128 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 128 lines · 120 tokens per session scan A 723cad3efb72

Subscribe to this mod's changes

code-reviewer is a skill published in the GitHub repository JayRHa/AgentSkills (4 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,926 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

reverse-engineering-tools

Guide for reverse engineering protected games and anti-cheat components across user mode, kernel mode, and hypervisor-aware environments. Use this skill when analyzing drivers, IOCTL protocols, callback registration, injected-code artifacts, integrity checks, protected binaries, or debugging security-sensitive game…

gmh5225/awesome-game-security · 60 tokens

unity-agent-workflows

Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…

hashgraph-online/awesome-codex-plugins · 146 tokens

interpreting-mod-author-instructions

Use when deciding how to correctly download/install a Bethesda mod per the author's instructions — triggers "how do I install", "FOMOD choices", "which file to download", "author说明", "install instructions", "which variant", "按作者说明安装", "这个mod怎么装". NOT for deciding whether to include the mod (use evaluating-bgs-mods)…

hashgraph-online/awesome-codex-plugins · 133 tokens

using-bgs-archive

Use when the user wants to inspect, list, extract, unpack, or repack Bethesda BA2/BSA archives; determine archive format/version/compression; or build archive assets for an MO2 overlay. Triggers - "unpack BA2", "extract BSA", "pack archive", "inspect archive", "bgs-archive".

hashgraph-online/awesome-codex-plugins · 75 tokens

orchestrate

Pipeline orchestration: dispatch the highest-priority ready tasks/work units to agents, manage capacity, and coordinate the Todo to Done flow. Invoked as /agiflow:orchestrate. Uses listtasks, listactivetasksbyorg, listmembers, updatetask, getworkunitprogress.

hashgraph-online/awesome-codex-plugins · 64 tokens

design-director

Используй только внутри активного Codex Project Autopilot-проекта, когда уже выбрана проектная фаза и нужен design direction по плану автопилота.

hashgraph-online/awesome-codex-plugins · 41 tokens