aio-review-deep

aio-review-deep is a skill for Claude Code from aiocean/claude-plugins. It costs 68 tokens per session (4,577 once invoked), scanned A, original, MIT.

A deep code-review skill that sends separate reviewers to inspect security, architecture, code quality, and performance. GitNexus is used for analysis of how parts of a codebase relate to each other.

In plain words
What is it for?
Use it for multi-area reviews of pull requests or newly added features, especially when security, design, quality, and performance all need checking.
Why use it?
It provides broader review coverage before merging a pull request or after a major feature, when one review pass may miss issues.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: agent in frontmatter.

Part of the aio-codeflow plugin — 10 skills shipped together

Good fit Use it for multi-area reviews of pull requests or newly added features…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiocean/claude-plugins/aio-review-deep
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 aiocean/claude-plugins --skill aio-review-deep
Clone the repo
git clone --depth 1 https://github.com/aiocean/claude-plugins

Made for: Claude Code.

Or install aio-codeflow, the plugin that ships this one along with the rest of its 10 skills.

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.

agentmods badge for aio-review-deep

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-review-deep.svg)](https://agentmods.dev/skills/aiocean/claude-plugins/aio-review-deep)
Your own site
<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-review-deep"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-review-deep.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,577 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.04577
Opus 5 $0.00034 $0.02289
Sonnet 5 $0.00014 $0.00915
Haiku 4.5 $0.00007 $0.00458

Measured 6d ago against content hash 45c195cd0e1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

aio-review-deep 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 6d 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.

plugins/aio-codeflow/skills/aio-review-deep/SKILL.md · 472 lines

How it starts

The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fleet Review — Parallel Multi-Agent Code Review

Dispatches a fleet of specialized review agents in parallel, each scrutinizing the diff through a different lens (security, architecture, quality, performance, tests). Uses GitNexus + CodeWiki for deep codebase understanding, then runs adversarial meta-review to synthesize findings. Heavier than aio-review-quick (quick pre-commit sanity check) — reach for this before merging high-impact changes.

Environment

  • GitNexus: !npx gitnexus status 2>/dev/null && echo "AVAILABLE" || echo "NOT INSTALLED"
  • CodeWiki: !which codewiki 2>/dev/null || echo "NOT INSTALLED"

When to Use

  • User requests "review code", "code review", "review this PR"
  • Before merging a pull request
  • After implementing a major feature
  • User wants quality assessment grounded in codebase structure

Workflow

Phase 0: Detect Tools and Language/Domain

0.1 Tool Availability

Tools are pre-detected in the Environment section above. Adapt the review based on availability:

Tool Status Impact on Review
GitNexus Available Hybrid search, symbol context, dependency tracking, blast radius via impact
GitNexus Missing Fall back to CodeWiki dependency graphs + manual grep for impact
CodeWiki Available Module clustering, metrics, dependency graphs
CodeWiki Missing Skip module mapping — use GitNexus context or file-path grouping

Proceed with whatever tools are available. Both together give the richest review; either subset still works.

0.2 Detect Language/Domain and Invoke Specialist Skills

Scan the project and changed files to invoke domain-specific static analysis before the general review agents run. Each skill brings specialized linters and pattern checks that general agents cannot replicate.

# Language detection — invoke matching skills
if go.mod or *.go exists:
  → invoke /golang-mastery (go vet, golangci-lint, govulncheck, nilaway, deadcode, race detection)

if *.xcodeproj or Package.swift exists:
  → invoke /ios-mastery (SwiftUI patterns, iOS conventions, Liquid Glass compliance)

# Framework detection — scan changed files for imports
if changed files import "react" or "next":
  → invoke /react-minimal-effects (useEffect anti-patterns, React 19 hooks, React Compiler readiness)

if changed files import "xstate":
  → invoke /xstate (v5 strict patterns, setup().createMachine(), actor patterns)

# Domain detection — based on file paths
if changed files touch infra/, deploy/, monitoring/, or include logging/metrics/tracing code:
  → invoke /monitoring-observability (Golden Signals, OpenTelemetry, SLO compliance)

Read the full file on GitHub · 472 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.

  1. 6d ago First seen · 472 lines · 68 tokens per session scan A 45c195cd0e1c

Subscribe to this mod's changes

aio-review-deep is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 4,577 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.

Related

Other skills, from other repositories

design-patterns

Detect, suggest, and evaluate GoF design patterns in TypeScript/JavaScript codebases. Use when refactoring code, applying singleton/factory/observer/strategy patterns, reviewing pattern quality, or finding stack-native alternatives for React, Angular, NestJS, and Vue.

FlorianBruniaux/claude-code-ultimate-guide · 59 tokens

pr-triage

4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…

FlorianBruniaux/claude-code-ultimate-guide · 86 tokens

audit-agents-skills

Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.

FlorianBruniaux/claude-code-ultimate-guide · 41 tokens

eval-skills

Audit all skills in the current project for frontmatter completeness, effort level appropriateness, allowed-tools scoping, and content quality. Produces a scored report with effort-level recommendations for each skill. Use when onboarding to a new project, reviewing skill quality before shipping, or adding effort…

FlorianBruniaux/claude-code-ultimate-guide · 67 tokens

review-pr

Perform a comprehensive code review of a pull request.

FlorianBruniaux/claude-code-ultimate-guide · 12 tokens

sonarqube

Analyze SonarCloud quality issues for a specific PR.

FlorianBruniaux/claude-code-ultimate-guide · 14 tokens