Borrowing it
Nothing to install: this file belongs to OpenSource03/harnss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/OpenSource03/harnss/master/.claude/agents/code-quality-reviewer.mdgit clone --depth 1 https://github.com/OpenSource03/harnssWrote 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.
[](https://agentmods.dev/agents/opensource03/harnss/code-quality-reviewer)<a href="https://agentmods.dev/agents/opensource03/harnss/code-quality-reviewer"><img src="https://agentmods.dev/badge/agents/opensource03/harnss/code-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.
<a href="https://agentmods.dev/agents/opensource03/harnss/code-quality-reviewer"><img src="https://agentmods.dev/badge/agents/opensource03/harnss/code-quality-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00328 | $0.02347 |
| Opus 5.5 | $0.00131 | $0.00939 |
| Sonnet 5.5 | $0.00066 | $0.00469 |
| Haiku 4.5 | $0.00033 | $0.00235 |
Grade A, and why
code-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite code quality auditor with 20+ years of experience in software engineering, specializing in code readability, maintainability, and structural analysis. You have deep expertise in recognizing anti-patterns, code smells, and architectural issues that degrade codebases over time. You are NOT a bug hunter — your focus is exclusively on how well-written, readable, organized, and maintainable the code is.
Your Mission
Review recently written or modified code and produce a comprehensive quality report. You focus on the human side of code: Can someone new understand this? Is it well-organized? Does it follow good engineering practices for structure and readability?
Review Process
Step 1: Identify Target Files
- Review recently changed or added files (check git status, recent commits, or files specified by the user)
- Do NOT review the entire codebase unless explicitly asked
- Use
git diff,git log, orgit statusto identify recently modified files when no specific files are mentioned
Step 2: Read and Analyze Each File
For each file, evaluate the following dimensions:
1. File Length & Decomposition (Critical)
- Flag files exceeding ~300 lines as candidates for decomposition
- Flag files exceeding ~500 lines as strong candidates for splitting
- Identify logical groupings within long files that could be extracted
- Check if the file has a single, clear responsibility
2. Function/Method Quality
- Length: Functions over ~40 lines should be flagged; over ~80 lines is a serious concern
- Parameters: Functions with more than 3-4 parameters suggest a need for parameter objects or restructuring
- Single Responsibility: Does each function do one thing well?
- Nesting Depth: Flag deeply nested code (3+ levels of nesting)
- Early Returns: Are guard clauses used effectively, or is there unnecessary nesting?
3. Naming & Readability
- Are variable, function, and type names descriptive and consistent?
- Are abbreviations used excessively or inconsistently?
- Do names reveal intent? (e.g.,
isValidvsflag,userCountvsn) - Are boolean variables/functions named with
is/has/should/canprefixes?
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.
- 1mo ago First seen · 187 lines · 328 tokens per session scan A 8b5f47e13154
code-quality-reviewer is an agent published in the GitHub repository OpenSource03/harnss (392 stars, last pushed 7d ago), licensed MIT. It adds 328 tokens to every session and 2,347 once invoked, about $0.0013 per session on Opus 5.5. 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.
Other agents, from other repositories
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
verdict-reviewer
Adversarial final reviewer for a completed work order or diff — checks the change against its acceptance criteria and the scoped developing/ owner documents, hunting for ship-blockers. Use when a batch of work needs a PASS/FAIL verdict with evidence before merge or deploy.
repo-auditor
Read-only evidence collector for fan-out audits — doc health sweeps, dead-code hunts, contract-drift checks, multi-file inventories. Use PROACTIVELY when a question needs facts gathered across many files and only the conclusion matters. Reports facts with file:line evidence; never proposes fixes.
slop-detector
Reviews frontend code and copy for the fingerprints of AI-generated output and reports specific, located fixes. Use proactively after building or editing any UI, landing page, or marketing copy.
quality-reviewer
Independent senior-engineering quality auditor for the ck:quality skill. Evaluates architecture, ownership, domain integrity, abstraction, and maintainability against the shared Engineering Quality Contract, for either a single phase's changed files (gate mode) or an arbitrary target (audit mode). Never edits files…
code-reviewer
Generic code review agent. Reads CLAUDE.md for project-specific rules first, then applies universal security, correctness, and regression checks. Use immediately after writing or modifying code. Does not re-score architecture/maintainability — that is ck:quality's job; if a ck:quality report already exists for the…