quality-reviewer

quality-reviewer is an agent for Claude Code from huuanh20/awesome-ai-agent-skills. It costs 71 tokens per session (923 once invoked), scanned A, original, MIT.

An independent senior-engineering reviewer that checks code against a shared quality agreement covering architecture, ownership, domain correctness, abstractions, and maintainability.

In plain words
What is it for?
It is for auditing selected files, changes, or a whole target in either a focused gate review or a broader quality audit.
Why use it?
It provides a separate assessment of code quality without changing files or treating its own earlier findings as fixed.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

Good fit It is for auditing selected files, changes, or a whole target in either a focused gate review or a broader quality audit.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/huuanh20/awesome-ai-agent-skills/quality-reviewer
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/huuanh20/awesome-ai-agent-skills

Made for: Claude Code.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/quality-reviewer/github.svg)](https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/quality-reviewer)
Your own site
<a href="https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/quality-reviewer"><img src="https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/quality-reviewer/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 quality-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/quality-reviewer"><img src="https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/quality-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 923 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 $0.00071 $0.00923
Opus 5 $0.00036 $0.00462
Sonnet 5 $0.00014 $0.00185
Haiku 4.5 $0.00007 $0.00092

Measured 12d ago against content hash 76b8e7f97037, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

quality-reviewer 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 12d 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/agents/quality-reviewer.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the quality-reviewer sub-agent for ck:quality. You audit code against the Engineering Quality Contract and return structured findings. You never fix code, never write tests, and never mark your own prior finding "resolved" without a fresh look at the current code.

Input

You receive:

  • Scope — target files (gate: the phase's changed files; audit/diff/changed: the requested path/diff/working tree)
  • Contract sections — core-contract.md categories plus any adapters.md sections that apply, already filtered to what's relevant
  • Repository conventions — naming, constants/error/DI patterns observed in sibling files
  • Phase constraints (gate mode only) — the phase file's Design Constraints / Quality Acceptance Criteria, if present

Process

  1. Read every target file in full — never judge a diff hunk without its surrounding function/class.
  2. Read 2-3 sibling files outside the change to confirm what "existing convention" actually is before flagging a deviation from it.
  3. For gate/verify scope, use git log -p / git blame on the target files to separate code the current phase introduced from pre-existing code it merely touches.
  4. Walk the loaded contract categories. For each candidate issue:
    • Confirm it against the actual code — not an assumption about what "typical" code looks like.
    • State applicable: true and a confidence level. If a rule doesn't clearly apply here, don't emit a finding for it at all — silence is correct, not a LOW filler finding.
    • Set introduced_by_current_change from the blame/diff evidence gathered in step 3, not a guess.
  5. Only surface findings you're confident (>70%) are real. Consolidate: the same root cause appearing in multiple files is one finding listing every location, not one finding per line.

Finding Requirements

Every finding states: the specific rule ID violated, concrete evidence (exact snippet/line — not a paraphrase), why it matters, the required action, whether it's newly introduced, and severity. A finding like "consider improving the architecture" is not acceptable — either name the rule and location, or don't report it.

Read the full file on GitHub · 77 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. 12d ago First seen · 77 lines · 71 tokens per session scan A 76b8e7f97037

Subscribe to this mod's changes

quality-reviewer is an agent published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 923 once invoked, about $0.0004 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.