review-for-quality

review-for-quality is a skill for Claude Code from codenamev/claude_memory. It costs 40 tokens per session (970 once invoked), scanned A, original, MIT.

A Ruby code review that examines a codebase through several established Ruby programming viewpoints and records its findings in docs/qualityreview.md.

In plain words
What is it for?
Use it to assess Ruby structure, Sequel database code, tests, error handling, naming, and boundaries between parts of the application.
Why use it?
It helps reveal unclear design, database-use, testing, and maintainability problems that may be missed in a routine review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Part of the claude-memory plugin — 14 skills, 6 commands, 6 hooks, 1 MCP server 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/codenamev/claude_memory/review-for-quality
Any agent
npx skills add codenamev/claude_memory --skill review-for-quality
Clone the repo
git clone --depth 1 https://github.com/codenamev/claude_memory

Made for: Claude Code.

Or install claude-memory, the plugin that ships this one along with the rest of its 14 skills, 6 commands, 6 hooks, 1 MCP server.

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 review-for-quality

README.md
[![agentmods](https://agentmods.dev/badge/skills/codenamev/claude_memory/review-for-quality.svg)](https://agentmods.dev/skills/codenamev/claude_memory/review-for-quality)
Your own site
<a href="https://agentmods.dev/skills/codenamev/claude_memory/review-for-quality"><img src="https://agentmods.dev/badge/skills/codenamev/claude_memory/review-for-quality.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 970 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 $0.00040 $0.00970
Opus 5 $0.00020 $0.00485
Sonnet 5 $0.00008 $0.00194
Haiku 4.5 $0.00004 $0.00097

Measured 6d ago against content hash fc69d8fbf071, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-for-quality 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.

.claude/skills/review-for-quality/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Quality Review

Critically review this Ruby codebase for best-practices, idiom use, and overall quality through the eyes of Ruby experts.

Expert Perspectives

Analyze the codebase through these 5 perspectives:

  1. Sandi Metz (POODR principles)

    • Single Responsibility Principle
    • Small, focused methods (< 5 lines ideal)
    • Classes with single purpose
    • DRY principle
    • Clear dependencies
    • High test coverage
  2. Jeremy Evans (Sequel maintainer)

    • Proper Sequel usage patterns (datasets over raw SQL)
    • Database performance optimization
    • Schema design best practices
    • Connection management
    • Transaction safety
    • Sequel plugins and extensions
  3. Kent Beck (TDD, Simple Design)

    • Test-first design
    • Simple solutions over complex ones
    • Revealing intent through naming
    • Clear boundaries between components
    • Testability without mocks
    • Command-Query Separation
  4. Avdi Grimm (Confident Ruby)

    • Confident code (no defensive nil checks everywhere)
    • Tell, don't ask principle
    • Null object pattern
    • Meaningful return values (not nil)
    • Duck typing
    • Result objects over exceptions
  5. Gary Bernhardt (Boundaries, Fast Tests)

    • Functional core, imperative shell
    • Fast unit tests (no I/O in logic)
    • Clear boundaries between layers
    • Separation of I/O and pure logic
    • Value objects
    • Immutable data structures

Review Process

  1. Explore the codebase systematically:

    • lib/claude_memory/ (all subdirectories)
    • Identify the largest files (> 500 lines)
    • Find code duplication patterns
    • Check architecture and design patterns
  2. Document EVERY issue found with:

    • Priority: 🔴 Critical / High / 🟡 Medium / Low
    • Specific file:line references
    • Which expert's principle is violated
    • Concrete improvement suggestions with code examples
    • Estimated effort to fix
  3. Track progress:

    • Compare with previous review date
    • Show metrics (lines of code, god objects, etc.)
    • Identify what's been fixed since last review
    • Highlight new issues that have emerged

Read the full file on GitHub · 155 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 155 lines · 40 tokens per session scan A fc69d8fbf071

Subscribe to this mod's changes

review-for-quality is a skill published in the GitHub repository codenamev/claude_memory (24 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 970 once invoked, about $0.0002 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 2026-08-30.