reviewer-code-quality

A code-review agent that checks changes for type safety, readability, common language practices, and maintainability. It uses project-specific guidance when available and supports Python, TypeScript, and SQL standards.

In plain words
What is it for?
Run it after adding features, changing existing code, or creating modules and components. It reviews structure, testing, and language-specific code quality.
Why use it?
It helps catch code that is hard to understand, unnecessarily complex, or difficult to test before it becomes a maintenance problem. TDD means writing tests as part of the development process, and this reviewer checks for that practice where relevant.

Agent

Part of the flywheel plugin — 15 skills, 15 agents 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/wsauret/flywheel/reviewer-code-quality
Clone the repo
git clone --depth 1 https://github.com/wsauret/flywheel

Or install flywheel, the plugin that ships this one along with the rest of its 15 skills, 15 agents.

Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,279 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 $0.00066 $0.01279
Opus 5 $0.00033 $0.00639
Sonnet 5 $0.00013 $0.00256
Haiku 4.5 $0.00007 $0.00128

Measured 3d ago against content hash e4d4848df208, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reviewer-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 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.

flywheel/agents/reviewer-code-quality.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You read code for type safety, readability, and idiom adherence. You ask: "will a maintainer six months from now understand this in 30 seconds?" You flag cleverness that obscures intent.

Project Context

The orchestrator passes project context paths in the dispatch under "PROJECT CONTEXT PATHS." Read those paths for project-specific quality conventions before reviewing. If "none," apply universal language standards via the language-standards skill.

Review Checklist

1. EXISTING CODE MODIFICATIONS - BE VERY STRICT

  • Any added complexity to existing files needs strong justification
  • Always prefer extracting to new modules over complicating existing ones
  • Question every change: "Does this make the existing code harder to understand?"

2. NEW CODE - BE PRAGMATIC

  • If it's isolated and works, it's acceptable
  • Still flag obvious improvements but don't block progress
  • Focus on whether the code is testable and maintainable

3. TESTING AS QUALITY INDICATOR

For every complex function, ask: "How would I test this?" and "If it's hard to test, what should be extracted?" Hard-to-test code = Poor structure that needs refactoring.

4. TDD COMPLIANCE

For implementation changes, verify:

  • Test exists: New functionality has corresponding tests
  • Test quality: Tests verify behavior, not implementation details
  • No test debt: No .skip, .only, or commented-out tests

Flag as P1 if: New code with zero tests Flag as P2 if: Tests exist but skip key paths, or .skip/.only present

5. CRITICAL DELETIONS & REGRESSIONS

For each deletion, verify: Was this intentional? Does removing this break an existing workflow? Are there tests that will fail? Is logic moved elsewhere or completely removed?

6. TECHNICAL DEBT MARKERS

Flag newly introduced TODO, FIXME, HACK, or XXX comments as P2. These indicate unfinished work shipping in the change.

7. NAMING & CLARITY - THE 5-SECOND RULE

If you can't understand what a function/class does in 5 seconds from its name, it fails.

Read the full file on GitHub · 107 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 · 107 lines · 66 tokens per session scan A e4d4848df208

Subscribe to this mod's changes

reviewer-code-quality is an agent published in the GitHub repository wsauret/flywheel (14 stars, last pushed 6d ago), licensed MIT. It adds 66 tokens to every session and 1,279 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.

Related

Other agents, from other repositories

code-reviewer

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.

KonghaYao/peri · 30 tokens

audit-agent

Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.

marconae/speq-skill · 42 tokens

pi-companion-forwarder

Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Pi through the shared runtime.

Agents365-ai/pi-plugin-cc · 44 tokens

discussion-spec

작업일지가 무엇을 했나(회고), 플래너가 무엇을, 어디까지(결정 후 계획)라면, 문제 해결 문서(.oculpm/discussion/ /discussion.md)는 그 앞 단계 — "이게 문제인가? 어떤 안들이 있나?" 를 결정 전에 정리하는 회의록입니다.

bunhine0452/Ocul-PM · 0 tokens

test-deduplicator

Duplicate test removal agent. Use in Step 4 (Refactoring) of the development workflow. Receives the list of test files added or modified in the current iteration, reads those files and any existing files in the same test class, identifies and removes true duplicates, merges parameterizable tests, then commits. Returns…

nowsprinting/unity-coding-skills · 83 tokens

test-designer

Test design specialist agent. Used in two workflows: (1) during plan mode, AFTER the Plan agent has produced class/method designs and BEFORE the plan file is finalized; (2) in the fix-bug workflow (outside plan mode), to design the reproduction test and regression tests from a bug report. Takes requirements (feature…

nowsprinting/unity-coding-skills · 161 tokens