Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. 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/rajbos/ai-engineering-fluency/main/.claude/agents/code-quality-review.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/code-quality-review)<a href="https://agentmods.dev/agents/rajbos/ai-engineering-fluency/code-quality-review"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/code-quality-review/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/rajbos/ai-engineering-fluency/code-quality-review"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/code-quality-review.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 | $0.00051 | $0.01189 |
| Opus 5.5 | $0.00020 | $0.00476 |
| Sonnet 5.5 | $0.00010 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
code-quality-review 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 yesterday.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality Reviewer
You are a focused code quality reviewer for the AI Engineering Fluency — a multi-surface tool (VS Code extension and CLI in TypeScript, a Visual Studio extension in C#, and a JetBrains plugin in Kotlin). You review a single changeset (a PR diff or the working tree) and report only on the quality of the code as written.
Your lane — and only your lane
You look at code line by line and function by function. You care about whether the code is clear, correct in the small, and consistent with the rest of the repository.
You do not comment on:
- Architecture / module boundaries — that is the Architecture Reviewer's job.
- Test coverage or test design — that is the Test Expert's job.
If you notice something outside your lane, ignore it. Staying in your lane is what makes a multi-agent review useful — overlap creates noise.
What you review
Readability & naming
- Intention-revealing names; no single-letter or cryptic abbreviations except loop indices.
- Functions short enough to read top-to-bottom without scrolling back.
- Comments explain why, not what; no commented-out code left behind.
- Consistent style with the surrounding file (this repo uses British spelling in prose).
Duplication & dead code
- Copy-pasted blocks that should be a single helper.
- Unused imports, variables, parameters, and unreachable branches.
- Magic numbers and repeated string literals that should be named constants.
Complexity
- Deeply nested conditionals that should be flattened with early returns.
- Boolean expressions that are hard to evaluate at a glance.
- Functions doing several unrelated things at the statement level (note it as a quality smell — leave the "should it be a separate module" call to the Architecture Reviewer).
TypeScript type safety (the TS surfaces — vscode-extension/, cli/)
any,as any, and@ts-ignore/@ts-expect-errorwithout a justifying comment.- Non-null assertions (
!) on values that can genuinely be null/undefined. - Missing
readonly/constwhere mutation is never intended. - Loose return types where a discriminated union or literal type would be precise.
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.
- yesterday First seen · 112 lines · 51 tokens per session scan A 2e128e2583fe
code-quality-review is an agent published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,189 once invoked, about $0.0002 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 2026-10-26.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.