vlist: Agent for Claude Code

.claude/agents/code-review.md

code-review is an agent for Claude Code from floor/vlist. It costs 26 tokens per session (573 once invoked), scanned A, original, MIT.

A code-review guide for checking changes against the rules and conventions of the vlist project. It reports problems without editing the code and calls for extra performance review on specified frequently used files.

In plain words
What is it for?
Use it to review staged or unstaged changes, check TypeScript practices, inspect project-specific rules, and identify files that need performance analysis.
Why use it?
It helps catch style, correctness, and performance issues before changes are committed.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions subagents.

This is floor/vlist's own configuration. It tells Claude Code how to work on vlist itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vlist configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/floor/vlist/main/.claude/agents/code-review.md
Clone the repo
git clone --depth 1 https://github.com/floor/vlist

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 code-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/floor/vlist/code-review/github.svg)](https://agentmods.dev/agents/floor/vlist/code-review)
Your own site
<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.

agentmods 80×15 button for code-review

Your own site · 80×15
<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>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 573 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 $0.00026 $0.00573
Opus 5.5 $0.00010 $0.00229
Sonnet 5.5 $0.00005 $0.00115
Haiku 4.5 $0.00003 $0.00057

Measured 1mo ago against content hash 69841ca184bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

.claude/agents/code-review.md · 65 lines

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.ts
  • src/rendering/renderer.ts, src/rendering/sizes.ts, src/rendering/scale.ts, src/rendering/viewport.ts
  • src/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, suggest unknown or proper interface
  • Explicit types on all function parameters and return values
  • const over let unless mutation is required
  • Early returns over deep nesting
  • Pure functions over stateful classes

Dimension-agnostic design

  • No height/width/scrollTop/scrollLeft in generic code
  • Use orientation-neutral terms: getSize(), scrollPosition, containerSize
  • Check resolvedConfig.horizontal for 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> with name, 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.

Read the full file on GitHub · 65 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. 1mo ago First seen · 65 lines · 26 tokens per session scan A 69841ca184bc

Subscribe to this mod's changes

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.

Related

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.

growthxai/output · 43 tokens

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.…

costajohnt/oss-autopilot · 243 tokens

silent-failure-hunter

Hunts down silent failures and inadequate error handling with zero tolerance.

pablo-albaladejo/kaiord · 18 tokens

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.

wahidyankf/ose-public · 39 tokens

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.

wahidyankf/ose-public · 50 tokens

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.

wahidyankf/ose-public · 46 tokens