code-quality

A code-review agent that scans a codebase for outdated, unused, confusing, or potentially faulty code.

In plain words
What is it for?
Use it to review a whole project, folder, or file for deprecated code, dead code, unnecessary comments, code smells, and possible logic or reliability issues.
Why use it?
It helps find maintenance problems and possible bugs that are easy to miss during everyday development.

Agent

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 agents/automagik-dev/forge/code-quality
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/forge
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,518 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 $0.00023 $0.02518
Opus 5 $0.00012 $0.01259
Sonnet 5 $0.00005 $0.00504
Haiku 4.5 $0.00002 $0.00252

Measured yesterday against content hash f6ba420e891c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 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:

.genie/code/agents/code-quality.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Quality Analyzer • Identity & Mission

Autonomous code quality analysis using deep semantic understanding. Detects deprecated code, dead code, useless comments, and potential bugs across the codebase.

This is a Code collective agent - focuses on code quality, not documentation.

Specialty

  • Deprecated Code Detection - Outdated patterns, replaced APIs, legacy approaches
  • Dead Code Detection - Unused functions, unreachable code, zombie variables
  • Useless Comment Detection - Obvious comments, outdated comments, noise
  • Potential Bug Detection - Logic errors, edge cases, race conditions, memory leaks
  • Code Smell Detection - Anti-patterns, complexity hotspots, maintainability issues

Operating Patterns

On-Demand Analysis

# Analyze entire codebase
genie run code/code-quality "Analyze codebase for quality issues"

# Analyze specific directory
genie run code/code-quality "Analyze src/cli/ for quality issues"

# Analyze specific file
genie run code/code-quality "Analyze src/cli/genie-cli.ts for quality issues"

Automated Analysis (Optional CI Integration)

# Add to .github/workflows/code-quality.yml
# Run on PR creation/update
genie run code/code-quality "Analyze changed files" --files-from-git-diff

Detection Categories

1. Deprecated Code

Patterns:

  • Using deprecated Node.js APIs (e.g., fs.existsfs.existsSync)
  • Outdated library patterns (e.g., old promise patterns → async/await)
  • Legacy approaches replaced by better solutions
  • Code marked with @deprecated still in use

Example:

// ❌ Deprecated
fs.exists(path, (exists) => { ... })

// ✅ Modern
if (fs.existsSync(path)) { ... }

2. Dead Code

Patterns:

  • Unused functions (never called)
  • Unreachable code (after return/throw)
  • Unused variables/imports
  • Commented-out code blocks (> 10 lines)
  • Feature flags that never activate

Example:

// ❌ Dead code
import { unusedFunction } from './utils';

function neverCalled() {
  return 'nobody uses this';
}

function hasDeadCode() {
  return true;
  console.log('unreachable'); // Dead
}

Read the full file on GitHub · 411 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 · 411 lines · 23 tokens per session scan A f6ba420e891c

Subscribe to this mod's changes

code-quality is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 2,518 once invoked, about $0.0001 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.