code-quality-review

code-quality-review is a skill for Claude Code from mnthe/hardworker-marketplace. It costs 38 tokens per session (2,304 once invoked), scanned A, original, MIT.

A review checklist for judging code quality, including clear logic, error handling, maintainability, and performance.

In plain words
What is it for?
Use it during final verification to review functions, files, control flow, naming, error handling, and performance concerns.
Why use it?
It helps reviewers find hard-to-read, fragile, overly complex, or inefficient code before approval.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the ultrawork plugin — 15 skills, 9 commands shipped together

Good fit Use it during final verification to review functions, files, control flow, naming, error handling, and performance concerns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mnthe/hardworker-marketplace/code-quality-review
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 mnthe/hardworker-marketplace --skill code-quality-review
Clone the repo
git clone --depth 1 https://github.com/mnthe/hardworker-marketplace

Made for: Claude Code.

Or install ultrawork, the plugin that ships this one along with the rest of its 15 skills, 9 commands.

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-quality-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/mnthe/hardworker-marketplace/code-quality-review/github.svg)](https://agentmods.dev/skills/mnthe/hardworker-marketplace/code-quality-review)
Your own site
<a href="https://agentmods.dev/skills/mnthe/hardworker-marketplace/code-quality-review"><img src="https://agentmods.dev/badge/skills/mnthe/hardworker-marketplace/code-quality-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for code-quality-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/mnthe/hardworker-marketplace/code-quality-review"><img src="https://agentmods.dev/badge/skills/mnthe/hardworker-marketplace/code-quality-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,304 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 $0.00038 $0.02304
Opus 5 $0.00019 $0.01152
Sonnet 5 $0.00008 $0.00461
Haiku 4.5 $0.00004 $0.00230

Measured 9d ago against content hash 5a874990fe41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

code-quality-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 9d 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/ultrawork/skills/code-quality-review/SKILL.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Quality Review

Systematic code quality assessment for ultrawork verification phase.

What This Skill Provides

Structured checklists for evaluating code quality across multiple dimensions:

  • Logic and readability
  • Error handling and resilience
  • Code style and maintainability
  • Performance and efficiency

When to Use This Skill

  • During VERIFICATION phase after workers complete tasks
  • When reviewing evidence before marking tasks as complete
  • Before approving design decisions that impact code quality
  • When auditing implementations for production readiness

Quality Dimensions

1. Logic and Readability

Checklist:

[ ] Functions have single, clear responsibilities
[ ] Functions are under 50 lines
[ ] Files are under 800 lines
[ ] Nesting depth is 4 levels or less
[ ] Control flow is straightforward (no convoluted conditionals)
[ ] Variable and function names are descriptive
[ ] No magic numbers (constants are named)
[ ] Complex logic has explanatory comments
[ ] Boolean conditions are readable (avoid double negatives)
[ ] Early returns reduce nesting

Red Flags:

  • Functions doing multiple unrelated things
  • Variable names like x, tmp, data, thing
  • Magic numbers: if (status === 42)
  • Deep nesting: if { if { if { if { ... }}}}
  • Complex conditions: if (!(!isValid && !isExpired))

Examples:

// ❌ Bad: Unclear logic, magic numbers
function process(x) {
  if (x > 100 && x < 500) {
    return x * 0.95;
  }
  return x;
}

// ✅ Good: Clear intent, named constants
const BULK_ORDER_MIN = 100;
const BULK_ORDER_MAX = 500;
const BULK_DISCOUNT_RATE = 0.95;

function applyBulkDiscount(orderTotal) {
  const isBulkOrder = orderTotal >= BULK_ORDER_MIN && orderTotal <= BULK_ORDER_MAX;
  return isBulkOrder ? orderTotal * BULK_DISCOUNT_RATE : orderTotal;
}

2. Error Handling

Checklist:

[ ] All async operations have error handling
[ ] try/catch blocks used for risky operations
[ ] Errors are logged with context
[ ] User-facing errors are sanitized
[ ] Error messages are actionable
[ ] No silent failures (empty catch blocks)
[ ] Edge cases are handled (null, undefined, empty arrays)
[ ] Input validation exists for external data
[ ] Database operations handle connection failures
[ ] API calls have timeout handling

Read the full file on GitHub · 377 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. 9d ago First seen · 377 lines · 38 tokens per session scan A 5a874990fe41

Subscribe to this mod's changes

code-quality-review is a skill published in the GitHub repository mnthe/hardworker-marketplace (4 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 2,304 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 2026-08-31.