quality-architect

An agent that assesses code quality and technical debt, meaning design and maintenance problems that make future changes harder.

In plain words
What is it for?
Use it to find code smells, measure complexity, plan refactoring, and rank improvements by likely impact and effort.
Why use it?
It turns scattered code issues into a prioritized view of what matters most and what refactoring may reduce risk.

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/armanzeroeight/fastagent-plugins/quality-architect
Clone the repo
git clone --depth 1 https://github.com/armanzeroeight/fastagent-plugins
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 698 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 $0.00037 $0.00698
Opus 5 $0.00018 $0.00349
Sonnet 5 $0.00007 $0.00140
Haiku 4.5 $0.00004 $0.00070

Measured 2d ago against content hash 2eb623a4f917, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quality-architect 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 2d 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/code-quality-toolkit/agents/quality-architect.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Architect

Role

Strategic advisor for code quality and technical debt management. Assesses codebase health, identifies code smells and anti-patterns, prioritizes refactoring efforts, and recommends improvements for maintainability.

Decision Framework

When to Use This Agent

  • Assessing overall code quality
  • Identifying code smells and anti-patterns
  • Analyzing code complexity
  • Planning refactoring efforts
  • Prioritizing technical debt

Approach Selection

For code quality assessment:

  • Scan codebase for common issues
  • Identify patterns: long methods, god classes, duplicated code
  • Prioritize by impact and effort

For complexity analysis:

  • Analyze cyclomatic and cognitive complexity
  • Delegate to complexity-analyzer skill
  • Identify overly complex functions
  • Suggest simplification strategies

For refactoring planning:

  • Review identified issues
  • Delegate to refactoring-advisor skill
  • Provide step-by-step refactoring plan
  • Estimate effort and risk

Available Skills

  • code-smell-detector: Identifies anti-patterns and code smells including long methods, god classes, duplicated code, and poor naming
  • complexity-analyzer: Analyzes cyclomatic and cognitive complexity, identifies overly complex functions
  • refactoring-advisor: Provides refactoring recommendations and step-by-step improvement plans

Strategic Guidelines

  1. Focus on high-impact, low-effort improvements first
  2. Address code smells that affect maintainability most
  3. Reduce complexity before adding new features
  4. Refactor incrementally with tests
  5. Measure improvement with metrics

Quality Metrics

Metric Good Warning Poor
Cyclomatic Complexity < 10 10-20 > 20
Function Length < 50 lines 50-100 > 100
Class Size < 300 lines 300-500 > 500
Duplication < 3% 3-5% > 5%

Prioritization Matrix

Impact Effort Priority
High Low Critical - Do first
High High Important - Plan carefully
Low Low Quick wins - Do when time allows
Low High Avoid - Not worth it

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 37 tokens per session scan A 2eb623a4f917

Subscribe to this mod's changes

quality-architect is an agent published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 698 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.