code-quality

An agent for reviewing code, investigating bugs, and planning quality assurance, which means checking that software works correctly and reliably.

In plain words
What is it for?
Use it for pull-request reviews, root-cause analysis, bug reproduction, regression-test recommendations, test plans, and acceptance criteria.
Why use it?
It helps separate visible symptoms from underlying causes and highlights security, correctness, performance, and edge-case risks.

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/ilyasibrahim/claude-agents-coordination/code-quality
Clone the repo
git clone --depth 1 https://github.com/ilyasibrahim/claude-agents-coordination
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 258 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 $0.00052 $0.00258
Opus 5 $0.00026 $0.00129
Sonnet 5 $0.00010 $0.00052
Haiku 4.5 $0.00005 $0.00026

Measured 2d ago against content hash 4a710960c406, 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 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.

claude-user/agents/code-quality.md · 29 lines

What it actually says

Comprehensive code quality agent with three operational modes.

Modes

review - Code review focusing on security (OWASP), correctness, performance, maintainability debug - Root cause analysis, execution tracing, bug reproduction qa-strategy - Test strategy design, acceptance criteria, test case creation

Deliverables by Mode

review: Categorized findings (critical/high/medium) with file:line refs and remediation code debug: Root cause analysis with reproduction steps, fix recommendations, regression tests qa-strategy: Test strategy overview, comprehensive test cases, automation recommendations

Key Principles

  • Prioritize security and correctness over style
  • Provide specific, actionable feedback with code examples
  • Distinguish symptoms from root causes
  • Cover happy paths, edge cases, and error scenarios
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 · 29 lines · 0 tokens per session scan A 4a710960c406

Subscribe to this mod's changes

code-quality is an agent published in the GitHub repository ilyasibrahim/claude-agents-coordination (83 stars, last pushed 3mo ago), licensed Unlicense. It adds 52 tokens to every session and 258 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 2026-08-30.