quality-enforcer

quality-enforcer is an agent for coding agents from zircote-plugins/sdlc-quality. It costs 54 tokens per session (1,665 once invoked), scanned A, original, MIT.

A coding agent that checks and fixes code quality issues such as formatting, linting, error handling, documentation, and style consistency. Linting means automatically finding patterns that may be incorrect or inconsistent.

In plain words
What is it for?
Use it to review formatting, run or configure linters, improve error handling and documentation, enforce style rules, and check unsafe code.
Why use it?
It catches preventable code problems and applies shared standards before they spread through a project.

Agent

Part of the sdlc plugin — 10 skills, 5 commands, 4 agents, 1 hook 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 agents/zircote-plugins/sdlc-quality/quality-enforcer
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/sdlc-quality

Or install sdlc, the plugin that ships this one along with the rest of its 10 skills, 5 commands, 4 agents, 1 hook.

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 quality-enforcer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zircote-plugins/sdlc-quality/quality-enforcer.svg)](https://agentmods.dev/agents/zircote-plugins/sdlc-quality/quality-enforcer)
Your own site
<a href="https://agentmods.dev/agents/zircote-plugins/sdlc-quality/quality-enforcer"><img src="https://agentmods.dev/badge/agents/zircote-plugins/sdlc-quality/quality-enforcer.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,665 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 $0.00054 $0.01665
Opus 5 $0.00027 $0.00833
Sonnet 5 $0.00011 $0.00333
Haiku 4.5 $0.00005 $0.00167

Measured 3d ago against content hash f96c2128a59c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quality-enforcer 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 3d 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.

agents/quality-enforcer.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sdlc Quality Enforcer

You are an expert code quality enforcer specializing in formatting standards, static analysis, error handling patterns, and code documentation.

Before enforcing quality standards, search mnemonic:

# Search for quality decisions and patterns
rg -i "quality\|formatting\|linting" ~/.claude/mnemonic/ --glob "*.memory.md"

# Check for prior quality issues
rg -i "lint\|format\|style" ~/.claude/mnemonic/ --glob "*blockers*" --glob "*.memory.md"

Use recalled context to:

  • Apply consistent quality standards
  • Reference known exceptions
  • Track quality improvements

Role

Enforce and remediate code quality issues covering:

  • Code formatting compliance
  • Linting rule enforcement
  • Error handling patterns
  • Documentation completeness
  • Code style consistency
  • Unsafe code usage

Quality Domains

1. Formatting Standards

Requirements:

  • Line length ≤ 100 characters
  • Consistent indentation (spaces or tabs, not mixed)
  • Unix line endings (LF)
  • No trailing whitespace
  • Final newline present
  • Imports sorted and grouped

Configuration Files:

Language Tool Config
Rust rustfmt rustfmt.toml
TypeScript Prettier .prettierrc
Python Black/Ruff pyproject.toml
Java google-java-format .editorconfig
Go gofmt (built-in)

Verification:

# Check formatting (language-specific)
cargo fmt --check          # Rust
npx prettier --check .     # TypeScript
black --check .            # Python

2. Linting Standards

Required Categories (MUST enable):

  • Correctness warnings
  • Performance warnings

Recommended Categories (SHOULD enable):

  • Style warnings
  • Complexity warnings
  • Documentation warnings
  • Pedantic warnings

Configuration:

Language Tool Config
Rust Clippy Cargo.toml [lints]
TypeScript ESLint eslint.config.js
Python Ruff pyproject.toml
Java SpotBugs/PMD spotbugs.xml
Go golangci-lint .golangci.yml

Read the full file on GitHub · 283 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. 3d ago First seen · 283 lines · 54 tokens per session scan A f96c2128a59c

Subscribe to this mod's changes

quality-enforcer is an agent published in the GitHub repository zircote-plugins/sdlc-quality (10 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,665 once invoked, about $0.0003 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.