A code-review checklist for examining changed code before it is merged. It checks whether the code still behaves correctly and looks for security, performance, maintenance, and testing problems.

Use it to review a pull request, feature, refactor, branch, or selected files. It produces concrete feedback ranked by severity, with file and line references when possible.

It helps find regressions and important risks before they reach users, instead of spending review time mainly on formatting or style.

review-code — Skill for Claude Code and Codex by PacificStudio/openase

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 PacificStudio/openase --skill review-code

Clone the repo

git clone --depth 1 https://github.com/PacificStudio/openase

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/pacificstudio/openase/review-code/github.svg)](https://agentmods.dev/skills/pacificstudio/openase/review-code)

Your own site

<a href="https://agentmods.dev/skills/pacificstudio/openase/review-code"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/review-code/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/pacificstudio/openase/review-code"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/review-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 627 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00018	$0.00627
Opus 5.5	$0.00007	$0.00251
Sonnet 5.5	$0.00004	$0.00125
Haiku 4.5	$0.00002	$0.00063

Measured 1mo ago against content hash 57a83930729e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-code 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 1mo 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.

internal/builtin/skills/review-code/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Code

Overview

Conduct a thorough code review for quality, security, performance, and maintainability. Focus on the real risks first, then provide concrete, severity-rated feedback with file and line references where possible.

When To Use

Before merging a pull request.
After implementing a feature or refactor.
When the user asks for a review of changed files or a branch.
When the code looks correct at first glance but may still hide regressions or design debt.

Review Workflow

Identify the review scope.
- Review the current diff, named files, or the whole change set.
- Prefer reviewing the actual changed surface before expanding further.
Check behavioral correctness first.
- Regressions against existing behavior.
- Missing edge-case handling.
- Broken invariants or data consistency risks.
Review the main quality categories.
- Security risks.
- Code quality and complexity.
- Performance concerns.
- Error handling and observability.
- Maintainability, coupling, and testability.
Evaluate the test story.
- Are the important paths covered?
- Are the tests proving behavior rather than implementation trivia?
- Is there an obvious missing regression test for the change?
Rate findings by severity.
- CRITICAL: must fix before merge; security or correctness issue with serious impact.
- HIGH: should fix before merge; likely bug, major regression risk, or serious design flaw.
- MEDIUM: worthwhile fix; non-blocking but meaningful quality issue.
- LOW: suggestion, cleanup, or style improvement.
Report findings in priority order.
- File and line reference.
- What is wrong.
- Why it matters.
- Concrete fix guidance.

Review Categories

Security: secrets, unsafe input handling, authz gaps, injection, XSS, CSRF.
Code quality: complexity, duplication, large functions, fragile branching.
Performance: avoidable repeated work, inefficient algorithms, N+1 patterns, unnecessary re-renders.
Maintainability: unclear naming, tight coupling, hidden assumptions, hard-to-test logic.
Reliability: missing error handling, weak retries, silent failures, incomplete logging.

Read the full file on GitHub · 78 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.

1mo ago First seen · 78 lines · 18 tokens per session scan A 57a83930729e

Subscribe to this mod's changes

review-code is a skill published in the GitHub repository PacificStudio/openase (269 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 627 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Code review agent ai software-engineering

open-code-review

Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…

alibaba/open-code-review · 98 tokens

review

Comprehensive security and correctness audit. Use for review, deep review, thermo nuclear, or thermonuclear requests and branch or PR diff audits.

vercel/eve · 31 tokens

meta-codereview-current-diff

Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.

opensquilla/opensquilla · 73 tokens

review-code