migration auditor
by Samuel Rose
$5
Catches dangerous database migrations before they hit production. Reviews schema changes for locking hazards, data loss, missing rollbacks, and index issues across PostgreSQL, MySQL, and SQLite.
3
1
Codex Skills for Code Quality & Review
Skills that help AI agents perform thorough code reviews, identify anti-patterns, suggest refactors, and enforce coding standards.
1,513 live code quality & review skills for Codex CLI.
New in Code Quality & Review
opencode coding
by Roy Yuen
$5
Enforce senior-level coding standards with a focus on verification, minimal diffs, and evidence-based bug fixing.
4
0
inline comment
by CCSW LLC
$9.99
Best way to steer your agents, effortlessly.
3
4
codex grade coding
by Roy Yuen
Free
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.
4
3234.7(3)
java best practice checker
by Larbi Wiran
Free
Expert Java code auditor for SE 8–24, flagging performance leaks, threading risks, and modernization gaps.
10
915.0(2)
aaai26 ai review
by 聊言青
Free
A multi-stage, evidence-grounded academic review agent modeled on the AAAI-26 AI Review Pilot research.
2
215.0(1)
agent portability checker
by Rian O'Leary
Free
Audit and auto-fix agent skills to remove platform lock-in and ensure cross-platform compatibility.
4
32
codegraph ast grep
by servrox
Free
Supercharge repo exploration and refactoring with semantic call-graph tracing and structural AST pattern matching.
2
8
pr reviewer
by Kevin Cline
$12
Automated, high-precision code reviews that detect bugs, security flaws, and performance bottlenecks in your PRs.
3
2
Auto Code Reviewer
by Aman G.
$5
Three-pass automated code review that catches error handling gaps, structural issues, and naming problems — then auto-fixes everything before code reaches the user.
2
1
coding plus
by Roy Yuen
$5
Upgrade your AI agent with a senior-level engineering SOP focused on inspection, minimal diffs, and hard verification.
2
0
skill install safety gate
by Roy Yuen
Free
Automated security and compatibility firewall for installing AI agent skills and Codex/OpenClaw packages.
2
27
test gen
by Kevin Cline
$12
Automated test generation with edge case analysis and framework-native syntax for TS, Python, Go, and Rust.
2
0
tech debt scanner
by Timoranjes
Free
Stop shipping debt with every feature — get a severity-rated inventory of every code smell, stale dependency, and untested path in minutes
2
12
code converter
by Kevin Cline
$12
Idiomatic code translation between Python, TypeScript, and Go that preserves logic and adapts language-specific patterns.
2
0
engineer mindset
by Kevin Cline
$9
Transform your agent into a Senior Engineer that analyzes architecture and reuses code before writing a single line.
2
0
Coding Agent Quality Gate
$14
Review AI-written code before you ship it: finds security holes, logic errors, missing error handling and risky shortcuts the way a senior engineer would, with a verdict and exact fixes.
3
13
dependency audit
by Kevin Cline
$12
Audit project manifests against source code to find unused, missing, and misplaced dependencies across major languages.
2
0
🧹 Code Comment Cleaner
$5
Preview code-like comment blocks across JavaScript, TypeScript, Python, Java, Go, Rust, HTML, and CSS. Preservation rules run before candidate detection; confirmed cleanups create .bak backups and remove only reviewed ranges.
4
1
agent regression guard
by Rian O'Leary
$5
Automated risk classification and regression checking to stop AI agents from breaking your codebase.
2
0
0 refactor advisor
by Julian
Free
Transform technical debt into a prioritized roadmap with professional-grade refactoring reports.
2
8
finalize
by Alex Shi
$5
The ultimate pre-commit checklist agent for cleaning code, updating docs, and validating repository state.
2
0
elon musk algorithm
by Julian
$9
Apply the 5-step engineering algorithm to ruthlessly delete, simplify, and accelerate any process or codebase.
2
0
Socratic Code Reviewer
Free
Socratic code review - the questions a senior reviewer would ask, covering correctness, edge cases, concurrency, API design and test adequacy. Use when the user says review my code, review this pull request, I want questions not a rewrite, review this diff, critique my implementation, or find problems in my code.
2
264.0(1)
Codex code review skills by task
A Codex code review skill gives Codex a fixed checklist for pull requests, so every diff gets the same questions before it merges. Pick by task.
Review a pull request. pr reviewer (USD 12) compares your branch with the base branch for bugs, security flaws and performance issues. Tip: run it before you push.
Check AI-written code. Coding Agent Quality Gate (USD 14) reviews code the agent wrote for security, logic and error handling and ends with a verdict. Tip: run it once a task is done, not after every edit.
Find tech debt. tech debt scanner is free and gives a severity-rated inventory of code smells, stale dependencies and untested paths, and Refactor Advisor (free, listed as 0-refactor-advisor) turns debt into a prioritized refactoring roadmap. Tip: fix the quick wins first and rescan.
Check one language or the dependencies. java best practice checker (free) audits Java from SE 8 to 24, and dependency audit (USD 12) finds unused, missing and misplaced dependencies. Tip: run the dependency check before a major upgrade.
Which review skill to pick
Solo developers without a second reviewer and teams that merge a lot of AI-generated code are who we would point here first. Pick the reviewer for every pull request, the gate for agent-written code and the scanner when you plan a refactor. Start free on a small repository and pay once you know which checks you run every week.
Be careful with skills that apply fixes themselves, such as Auto Code Reviewer (USD 5), which runs a three-pass review and then fixes what it finds: run them on a clean branch and read the diff. These skills run in your Codex session, so keep your CI tests as the check that blocks a merge. A skill gives a second opinion and does not replace the human who owns the merge. Read about automating code review with AI and compare more in the best code review skills for agents.
Review skills vs. rules in AGENTS.md
AGENTS.md is always loaded, globally from ~/.codex and per directory from the project root down, so it suits always-true project rules. A skill loads when the task fits its description or when you ask for it by name, so it suits a review workflow you repeat across repos. Connect Codex to Agensi once and it loads the latest approved version for that session, with nothing saved to ~/.agents/skills; see the MCP setup guide and the complete AGENTS.md guide. See also Codex testing skills, code review skills for Claude Code or the Codex skills marketplace.
Frequently asked questions
Connect an MCP-compatible agent to Agensi and ask it to use the skill on your task. Approve any required purchase. The latest approved instructions load on each use; never save skill files to disk.
Some are free, but most are paid. Paid skills show the price upfront, are a one-time purchase, and include future updates from the creator.
Yes. Every listing is checked by an 8-point automated security scan before it can go live, and the result is shown on each skill page alongside the file list.
Get in touch
Questions, partnership ideas, or feedback on the platform? Tell us what's working and what isn't, we love to hear from you!
SR
Samuel Rose
Founder & CEO of Agensi
Email UsBook a Callinfo@agensi.io
We typically respond within a few hours during business hours.