verify-quality

verify-quality is a skill for Claude Code, Codex from Aurite-ai/agent-verifier. It costs 38 tokens per session (2,045 once invoked), scanned A, original, MIT.

A local review checklist for code quality, including names, structure, documentation, and common maintenance problems. It focuses on implementation files rather than tests or generated files.

In plain words
What is it for?
Use it to inspect Python, TypeScript, JavaScript, Go, or Rust projects for naming, organization, documentation, and general quality problems.
Why use it?
It helps find unclear naming, missing explanations, magic values, and organizational issues before they make a codebase harder to maintain. Its findings are heuristic, so they still require human judgment.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/aurite-ai/agent-verifier/verify-quality
Any agent
npx skills add Aurite-ai/agent-verifier --skill verify-quality
Clone the repo
git clone --depth 1 https://github.com/Aurite-ai/agent-verifier

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 verify-quality

README.md
[![agentmods](https://agentmods.dev/badge/skills/aurite-ai/agent-verifier/verify-quality.svg)](https://agentmods.dev/skills/aurite-ai/agent-verifier/verify-quality)
Your own site
<a href="https://agentmods.dev/skills/aurite-ai/agent-verifier/verify-quality"><img src="https://agentmods.dev/badge/skills/aurite-ai/agent-verifier/verify-quality.svg" alt="Measured on agentmods" 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 2,045 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00038 $0.02045
Opus 5 $0.00019 $0.01022
Sonnet 5 $0.00008 $0.00409
Haiku 4.5 $0.00004 $0.00204

Measured 6d ago against content hash 43161a11a910, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

verify-quality scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

response = requests.get(f"{BASE_URL}/users/{user_id}")
skills/verify-quality/SKILL.md · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Quality Verification

Purpose

Verify code for quality anti-patterns including poor naming, missing documentation, magic values, and organizational issues. All analysis happens locally.

When to Use

Trigger this skill when the user asks to:

  • "verify agent quality"
  • "verify quality"
  • "check code quality"
  • "review code organization"
  • "check naming conventions"

Note: For full verification including security, patterns, and language-specific checks, tell the user to say "verify agent".

Process

Step 1: Discover Files

Locate files to analyze:

Source files:

  • *.py, *.ts, *.js, *.go, *.rs - Source code
  • Focus on main implementation files, not tests

Directories to check:

  • src/, lib/, app/, project root
  • agent/, tools/, utils/

Exclude:

  • node_modules/, .venv/, venv/, __pycache__/
  • Test files (*.test.*, *.spec.*, *_test.go)
  • Generated files, migrations

Step 2: Run Quality Checks

All checks in this skill are [HEURISTIC] — they require judgment. Tag findings with [H].


2.1 [HEURISTIC] Naming Conventions

Check for:

Issue Examples
Single-letter variables (except loops) x = get_data(), d = {}
Unclear abbreviations proc_usr_req(), calc_val()
Inconsistent casing Mixing camelCase and snake_case in same file
Names that don't describe purpose data, temp, result, info
Boolean names without is/has/can enabled = check() vs is_enabled = check()

Good naming:

# ✅ Clear, descriptive
user_profile = get_user_profile(user_id)
is_authenticated = check_authentication(token)
max_retry_attempts = 3

# ⚠️ Unclear
x = get_up(uid)
auth = check(t)
n = 3

Severity: ⚠️ Warning


2.2 [HEURISTIC] Code Organization

Check for:

Issue Description
Large files > 500 lines for a single module
Large functions > 50 lines for a single function
Deep nesting > 4 levels of indentation
Mixed concerns Business logic mixed with I/O in same function
God objects Classes with > 10 public methods or > 20 attributes

Read the full file on GitHub · 354 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 · 354 lines · 38 tokens per session scan A 43161a11a910

Subscribe to this mod's changes

verify-quality is a skill published in the GitHub repository Aurite-ai/agent-verifier (44 stars, last pushed 9d ago), licensed MIT. It adds 38 tokens to every session and 2,045 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

procoder

Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…

azrtydxb/procoder · 101 tokens

Tech Debt Auditor

Identifies and prioritizes technical debt in a codebase with an effort/impact matrix.

Notysoty/openagentskills · 22 tokens

Unit Test Improver

Reviews existing unit tests for gaps, weak assertions, and missing edge cases, then rewrites them to be more robust.

Notysoty/openagentskills · 29 tokens

quality

This skill should be used when the user asks about "code quality", "formatting", "linting", "lint rules", "code style", "error handling", "unsafe code", "documentation comments", "doc comments", "rustfmt", "prettier", "eslint", "clippy", or needs guidance on code quality enforcement and configuration.

zircote-plugins/sdlc-quality · 74 tokens

pr-review

Use when conducting manual PR reviews - provides structured checklist covering security, performance, maintainability, and code quality dimensions with anti-sycophancy principles.

JeremyDev87/codingbuddy · 32 tokens

receiving-code-review

Use when receiving PR review feedback or code review comments. Enforces verification-first response to review feedback with anti-sycophancy classification and constructive disagreement protocol.

JeremyDev87/codingbuddy · 36 tokens