move-code-review

move-code-review is a skill for Claude Code, Codex from contract-hero/sui-pilot. It costs 168 tokens per session (5,671 once invoked), scanned A, original, MIT.

A security and architecture review guide for Sui Move smart contracts, which are programs that run on the Sui blockchain. It examines permissions, calculations, blockchain objects, shared-object traffic, versions, unused code, transfers, and tests.

In plain words
What is it for?
Use it to review or audit Move packages and check their access control, arithmetic, object design, version handling, transfer behavior, and testing approach.
Why use it?
It helps find flaws that could cause stolen funds, blocked operations, wrong results, or difficult maintenance before the contract is released.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the sui-pilot plugin — 6 skills, 6 commands, 1 agent shipped together

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/contract-hero/sui-pilot/move-code-review
Any agent
npx skills add contract-hero/sui-pilot --skill move-code-review
Clone the repo
git clone --depth 1 https://github.com/contract-hero/sui-pilot

Made for: Claude Code, Codex.

Or install sui-pilot, the plugin that ships this one along with the rest of its 6 skills, 6 commands, 1 agent.

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 move-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/contract-hero/sui-pilot/move-code-review.svg)](https://agentmods.dev/skills/contract-hero/sui-pilot/move-code-review)
Your own site
<a href="https://agentmods.dev/skills/contract-hero/sui-pilot/move-code-review"><img src="https://agentmods.dev/badge/skills/contract-hero/sui-pilot/move-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,671 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 $0.00168 $0.05671
Opus 5 $0.00084 $0.02835
Sonnet 5 $0.00034 $0.01134
Haiku 4.5 $0.00017 $0.00567

Measured 5d ago against content hash 697b42bc2659, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

move-code-review 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 5d 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.

skills/move-code-review/SKILL.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Move Code Review

Doc-First Requirement: Before flagging security issues or recommending patterns, verify current best practices against the sui-pilot documentation (.move-book-docs/, .sui-docs/, .walrus-docs/, .seal-docs/, .ts-sdk-docs/). Use Glob/Grep against ${CLAUDE_PLUGIN_ROOT}/.<source>-docs/. Sui Move security patterns evolve—what was vulnerable may now be safe (or vice versa). For Move language semantics or idioms, prefer .move-book-docs/. Reviews that touch Walrus blob access, Seal key server usage, or TS-SDK call sites must cross-check the corresponding ecosystem docs. When citing specific security patterns, reference the doc file path.

You are an expert Sui Move security and architecture reviewer. Your knowledge is derived from patterns observed across 40+ production Move contract reviews. Your job is to find security vulnerabilities, design anti-patterns, and architecture issues that could cause financial loss, denial of service, incorrect behavior, or maintainability problems.

Scope & Complementarity

This skill covers security, design, and architecture review. It does NOT cover Move 2024 Edition syntax, method style, macros, module labels, import patterns, or formatting — those belong to /move-code-quality.

Run both skills for a complete review:

  1. /move-code-review → security, architecture, design (this skill)
  2. /move-code-quality → syntax, idioms, Move 2024 compliance

Severity Classification

Every finding is assigned a severity level with a fixed numeric weight. These are pre-assigned per check type based on potential damage, not reviewer judgment.

Level Label Weight Criteria
S1 Critical 10 Direct financial loss, unauthorized access, data corruption, funds locked permanently
S2 High 7 Incorrect behavior, data integrity loss, availability impact, denial of service
S3 Medium 4 Maintainability risk, scalability limit, reduced composability, correctness risk under edge conditions
S4 Low 2 Code quality, documentation gaps, style issues that hinder long-term maintenance

Read the full file on GitHub · 366 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. 5d ago First seen · 366 lines · 168 tokens per session scan A 697b42bc2659

Subscribe to this mod's changes

move-code-review is a skill published in the GitHub repository contract-hero/sui-pilot (10 stars, last pushed 4d ago), licensed MIT. It adds 168 tokens to every session and 5,671 once invoked, about $0.0008 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.