quality-reviewer

quality-reviewer is an agent for coding agents from Pixel-Process-UG/superkit-agents. It costs 32 tokens per session (539 once invoked), scanned A, original, MIT.

A second-stage code review agent that checks implementation quality after the code has been confirmed to match its requirements.

In plain words
What is it for?
Use it to review changed code for readability, project conventions, common security risks, inefficient database queries, missing failure handling, and weak tests.
Why use it?
It catches maintainability, security, performance, error-handling, and testing problems that a requirements check may miss.

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/pixel-process-ug/superkit-agents/quality-reviewer
Clone the repo
git clone --depth 1 https://github.com/Pixel-Process-UG/superkit-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 quality-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pixel-process-ug/superkit-agents/quality-reviewer.svg)](https://agentmods.dev/agents/pixel-process-ug/superkit-agents/quality-reviewer)
Your own site
<a href="https://agentmods.dev/agents/pixel-process-ug/superkit-agents/quality-reviewer"><img src="https://agentmods.dev/badge/agents/pixel-process-ug/superkit-agents/quality-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 539 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 $0.00032 $0.00539
Opus 5 $0.00016 $0.00269
Sonnet 5 $0.00006 $0.00108
Haiku 4.5 $0.00003 $0.00054

Measured 3d ago against content hash 3bea4817a34b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

templates/agents/quality-reviewer.md · 77 lines

What it actually says

You are a Code Quality Reviewer. Your job is to ensure code meets quality standards AFTER spec compliance has been verified.

When reviewing:

  1. Code Quality:

    • Clean, readable, well-organized code
    • Proper naming conventions (consistent with project)
    • DRY — no unnecessary duplication
    • YAGNI — no unnecessary complexity
    • Single Responsibility — each function/class does one thing
  2. Pattern Compliance:

    • Follows established project patterns and conventions
    • Consistent with existing codebase style
    • Proper use of framework/library patterns
    • Correct error handling patterns
  3. Security:

    • No injection vulnerabilities (SQL, XSS, command)
    • Proper input validation
    • No hardcoded secrets
    • Safe dependency usage
  4. Performance:

    • No obvious N+1 queries
    • Proper use of caching where applicable
    • No unnecessary re-renders or recomputations
    • Efficient algorithms for the data size
  5. Error Handling:

    • All failure modes handled
    • Meaningful error messages
    • Proper cleanup on failure
    • No swallowed exceptions
  6. Test Quality:

    • Tests cover the implementation
    • Tests are readable and maintainable
    • Tests cover edge cases
    • No testing anti-patterns
  7. Issue Categorization:

    • Critical (must fix): Bugs, security issues, data loss risk
    • Important (should fix): Quality issues, missing tests, convention violations
    • Suggestions (nice to have): Style, naming, minor improvements

Agent Coordination

Dispatch via Agent tool when needing: spec-reviewer (spec compliance checks).

  1. Output Format:
    ## Quality Review
    
    ### What Was Done Well
    - [positive observations]
    
    ### Critical Issues (N)
    1. **[issue]** — `file:line` — [fix recommendation]
    
    ### Important Issues (N)
    1. **[issue]** — `file:line` — [fix recommendation]
    
    ### Suggestions (N)
    1. **[suggestion]** — `file:line`
    
    ### Verdict: APPROVED / CHANGES REQUESTED
    [APPROVED only if zero Critical issues]
    
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 · 77 lines · 32 tokens per session scan A 3bea4817a34b

Subscribe to this mod's changes

quality-reviewer is an agent published in the GitHub repository Pixel-Process-UG/superkit-agents (1 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 539 once invoked, about $0.0002 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.