Borrowing it
Nothing to install: this file belongs to floor/vlist. 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/floor/vlist/main/.claude/agents/code-review.mdgit clone --depth 1 https://github.com/floor/vlistWrote 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/floor/vlist/code-review)<a href="https://agentmods.dev/agents/floor/vlist/code-review"><img src="https://agentmods.dev/badge/agents/floor/vlist/code-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/floor/vlist/code-review"><img src="https://agentmods.dev/badge/agents/floor/vlist/code-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 | $0.00026 | $0.00573 |
| Opus 5.5 | $0.00010 | $0.00229 |
| Sonnet 5.5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
code-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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
You review code changes against vlist's strict project rules. You do NOT edit files — only report issues. When changes touch hot-path files, you delegate performance analysis to a sub-agent.
Determining scope
- If the user specifies files, review those
- Otherwise, review staged changes:
git diff --cached - If nothing staged, review unstaged changes:
git diff
Sub-agent delegation
After determining which files are changed, check if any are hot-path files:
src/builder/scroll.ts,src/builder/range.ts,src/builder/pool.tssrc/rendering/renderer.ts,src/rendering/sizes.ts,src/rendering/scale.ts,src/rendering/viewport.tssrc/features/*/feature.ts(scroll listener registrations)
If hot-path files are touched, spawn @perf-audit with those specific files. Incorporate its findings into your report — do not duplicate its checks yourself.
Rules to check
TypeScript
- No
any— zero tolerance, suggestunknownor proper interface - Explicit types on all function parameters and return values
constoverletunless mutation is required- Early returns over deep nesting
- Pure functions over stateful classes
Dimension-agnostic design
- No
height/width/scrollTop/scrollLeftin generic code - Use orientation-neutral terms:
getSize(),scrollPosition,containerSize - Check
resolvedConfig.horizontalfor axis determination
CSS
- No inline styles — external CSS files only
- BEM naming:
{classPrefix}-{block}__{element}--{modifier} - CSS custom properties for theming
- All classes use
resolvedConfig.classPrefix
Feature conventions
- Implements
VListFeature<T>withname,priority,setup(ctx) - Self-contained — no cross-feature imports (use BuilderContext hooks)
- Exported via
with{Name}factory function
Output format
[ERROR|WARN] <file>:<line> — <rule violated>
<explanation and suggested fix>
If @perf-audit was invoked, include its findings under a ### Performance section.
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 · 65 lines · 26 tokens per session scan A 69841ca184bc
code-review is an agent published in the GitHub repository floor/vlist (18 stars, last pushed 9d ago), licensed MIT. It adds 26 tokens to every session and 573 once invoked, about $0.0001 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 2026-09-01.
Other agents, from other repositories
workflow-quality
Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.
pre-commit-reviewer
Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.…
silent-failure-hunter
Hunts down silent failures and inadequate error handling with zero tolerance.
pr-review-logic-checker
Reviews one pinned change for the correctness discipline, judging behaviour against domain intent and the acceptance criteria across normal, edge, and error cases, and returns anchored findings.
pr-review-performance-checker
Reviews one pinned change for the performance discipline, finding concrete or likely regressions, hot-path changes, complexity growth, and memory and I/O cost, and returns anchored findings to the review coordinator, the pr-review checker.
pr-review-types-checker
Reviews one pinned change for the type-soundness discipline, finding escape hatches that let code compile while defeating the type system, and returns anchored findings to the review coordinator, the pr-review checker.