code-review

code-review is a skill for Claude Code, Codex from ggg123124/vrchat-assistant. It costs 96 tokens per session (1,759 once invoked), scanned A, original, MIT.

A structured process for examining code changes, pull requests, files, and feature branches for correctness, design problems, and security issues.

In plain words
What is it for?
Reviewing changes before merge, explaining why findings matter, and suggesting fixes for behavior, error handling, maintainability, and security.
Why use it?
It looks beyond formatting and lint errors to find bugs and risks that automated checks may miss.

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/ggg123124/vrchat-assistant/code-review
Any agent
npx skills add ggg123124/vrchat-assistant --skill code-review
Clone the repo
git clone --depth 1 https://github.com/ggg123124/vrchat-assistant

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.

agentmods badge for code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/code-review.svg)](https://agentmods.dev/skills/ggg123124/vrchat-assistant/code-review)
Your own site
<a href="https://agentmods.dev/skills/ggg123124/vrchat-assistant/code-review"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,759 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 5.1 $0.00096 $0.01759
Opus 5 $0.00048 $0.00879
Sonnet 5 $0.00019 $0.00352
Haiku 4.5 $0.00010 $0.00176

Measured yesterday against content hash 599d9c6ee868, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/code-review/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review — Multi-Pass Deep Analysis

You are a senior engineer conducting a code review. Not a linter. Not a style checker. You catch the bugs that pass CI, the design flaws that create tech debt, and the security holes that cause incidents.

Mindset

  • Correctness first. Does it do what it claims to do? Does it handle what happens when things go wrong?
  • No nitpicking. Don't comment on formatting, naming preferences, or style unless it causes actual confusion. Focus on substance.
  • Explain the WHY. Every comment explains why it matters, not just what to change.
  • Suggest, don't dictate. Offer the fix. Let the author decide.
  • Acknowledge good work. If something is well-written, say so. Reviews that only criticize are demoralizing and incomplete.

The Review Protocol

Step 0: Understand the Change

Before reviewing a single line:

  1. Read the PR description / commit message — what is the intent?
  2. Check the diff scope — what files changed, how many lines?
  3. Identify the type of change:
    • Feature (new behavior)
    • Bug fix (correcting behavior)
    • Refactor (changing structure, same behavior)
    • Performance (optimization)
    • Infrastructure (config, CI, deps)

Understanding intent prevents misguided feedback. A refactor that doesn't change behavior shouldn't be reviewed for feature completeness.

Pass 1: Correctness

The most important pass. Does the code work?

CORRECTNESS CHECKLIST:
═══════════════════════
□ Does the code do what the description says it does?
□ Are all code paths handled? (if/else completeness, switch defaults)
□ Are error conditions handled? (try/catch, error returns, null checks)
□ Are edge cases covered?
  - Empty inputs ([], {}, "", 0, null, undefined)
  - Boundary values (max int, empty string, single element)
  - Concurrent access (if applicable)
□ Are return types correct and consistent?
□ Do loops terminate? Are off-by-one errors possible?
□ Are async operations properly awaited?
□ Are resources properly cleaned up? (connections, file handles, listeners)
□ Does state mutation happen in the right order?
□ Are comparisons correct? (=== vs ==, > vs >=, AND vs OR)

Read the full file on GitHub · 222 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. yesterday First seen · 222 lines · 96 tokens per session scan A 599d9c6ee868

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository ggg123124/vrchat-assistant (21 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 1,759 once invoked, about $0.0005 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 2026-09-04.

Related

Other skills, from other repositories

no-mistakes

Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach upstream. Use when the user asks to run no-mistakes, gate or ship or validate their changes, push safely, asks you to do a task and then validate it, or invokes /no-mistakes.

mnemosyne-oss/mnemosyne · 81 tokens

mnemosyne-context

Load this when working on the mnemosyne memory system — its repo, sync server, memory databases, or CI. Covers architecture, the surface/sync data model, dev workflow (tests/ruff/CI matrix), release policy, and known gotchas that are easy to get wrong. Use for any "mnemosyne" dev or devops task, or when a…

mnemosyne-oss/mnemosyne · 88 tokens

hermes-memory-providers

Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.

mnemosyne-oss/mnemosyne · 34 tokens

mnemosyne

Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.

mnemosyne-oss/mnemosyne · 22 tokens

mnemosyne-memory-override

Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.

mnemosyne-oss/mnemosyne · 46 tokens

hermes-self-evaluation

Use this skill when the user asks to audit, review, or optimize Hermes's own performance — analyzing session data, skills, configuration, costs, and usage patterns to identify improvements, automation opportunities, and system optimizations.

AtlasOmnia/donna-starter · 69 tokens