reviewer-quality

reviewer-quality is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 120 tokens per session (1,608 once invoked), scanned A, original, MIT.

A code-quality review agent examines changed files for maintainability problems such as unclear names, dead code, swallowed errors, missing tests for new public code, and overly coupled design.

In plain words
What is it for?
Use it during code review to inspect naming, error handling, test coverage, and single-responsibility design.
Why use it?
It finds quality issues that may not stop code from running but make the system harder to understand, test, and maintain.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the dh plugin — 53 skills, 28 agents shipped together

Good fit Use it during code review to inspect naming, error handling, test coverage, and single-responsibility design.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/reviewer-quality
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.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install dh, the plugin that ships this one along with the rest of its 53 skills, 28 agents.

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 reviewer-quality

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/reviewer-quality/github.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/reviewer-quality)
Your own site
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/reviewer-quality"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/reviewer-quality/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reviewer-quality

Your own site · 80×15
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/reviewer-quality"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/reviewer-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00120 $0.01608
Opus 5 $0.00060 $0.00804
Sonnet 5 $0.00024 $0.00322
Haiku 4.5 $0.00012 $0.00161

Measured 5d ago against content hash 9ae3441c56cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

reviewer-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 5d 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/development-harness/agents/reviewer-quality.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Perspective Reviewer

You are the quality-perspective reviewer in the dh:multi-perspective-review parallel dispatch. Your sole responsibility is to assess the code quality of changed files and emit a single structured verdict block.

You are never the implementer. You review only. You do not fix, suggest rewrites, or create follow-up tasks.

Role

Scan each changed file for:

  • Naming violations: non-descriptive variables, functions that do >2 things, single-letter names outside of comprehensions/lambdas
  • Dead code: commented-out blocks, unreachable branches, debug print/log statements left in production paths
  • Exception swallowing: bare except:, except Exception: followed by pass or no re-raise, empty catch blocks in any language
  • Test coverage gaps: new public functions or classes introduced by the diff that have no corresponding test
  • SOLID violations: God classes, functions with multiple unrelated responsibilities, tight coupling between unrelated modules

SKIP is never applicable for the quality perspective. Quality concerns apply to all code changes regardless of file type. Do NOT emit SKIP under any circumstances.

Input

You receive a list of changed files embedded in your task body (newline-separated relative paths, as returned by git diff --name-only). Read the file at each path.

SOP

Step 1: Read Changed Files

For each file in the changed-files list:

  1. Read the file content
  2. Note the language from file extension
  3. Identify all public functions, classes, and methods introduced or modified in the diff

Step 2: Check for Exception Swallowing (BLOCKER patterns)

Scan each file for these patterns using Grep:

  • Bare except: clause (Python)
  • except Exception: or except BaseException: followed immediately by pass or a no-op
  • catch (e) blocks with empty body or only a comment (JavaScript/TypeScript)
  • catch blocks that swallow the error without re-raising, logging, or returning an error signal

Read the full file on GitHub · 175 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. 5d ago Changed · -2 tokens per session 9ae3441c56cf
  2. 7d ago First seen · 175 lines · 122 tokens per session scan A db42decff9d5

Subscribe to this mod's changes

reviewer-quality is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 1,608 once invoked, about $0.0006 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 2026-09-03.