next-reviewer

next-reviewer is an agent for Claude Code from toffyui/ccteams. It costs 55 tokens per session (785 once invoked), scanned A, original, MIT.

A reviewer and quality checker for Next.js App Router and TypeScript changes. It checks server-versus-browser code placement, types, caching, accessibility, and whether the project passes its checks and build.

In plain words
What is it for?
Use it before declaring a Next.js change complete, especially after editing routes, server actions, data fetching, or client components.
Why use it?
It can catch defects that a normal code review or compiler may miss, including unsafe server actions, inconsistent browser output, leaked secrets, and incorrect data caching.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths.

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/toffyui/ccteams/next-reviewer
Clone the repo
git clone --depth 1 https://github.com/toffyui/ccteams

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 next-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/toffyui/ccteams/next-reviewer.svg)](https://agentmods.dev/agents/toffyui/ccteams/next-reviewer)
Your own site
<a href="https://agentmods.dev/agents/toffyui/ccteams/next-reviewer"><img src="https://agentmods.dev/badge/agents/toffyui/ccteams/next-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 785 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 5.1 $0.00055 $0.00785
Opus 5 $0.00028 $0.00392
Sonnet 5 $0.00011 $0.00157
Haiku 4.5 $0.00006 $0.00078

Measured 6d ago against content hash 76e9db89cbba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

next-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 6d 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.

teams/next-ts/agents/next-reviewer.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You review and verify Next.js (App Router) + TypeScript changes. You do not implement — you find what is wrong and report it precisely, then confirm when it is right.

FIRST ACTION: Read .claude/skills/next-ts-playbook/SKILL.md and follow it. If the file is absent, apply the rules below. Non-negotiable minimums from it: trace the Server/Client boundary by hand and flag any "use client" sitting above the smallest interactive leaf (tooling won't catch a directive that is merely too high); audit every "use server" export for input validation, authorization, and a revalidatePath/ revalidateTag after the write; confirm every fetch in the diff carries explicit cache intent and flag implicit defaults with the 14-vs-15 note; sweep changed files for hydration nondeterminism (Date.now/Math.random/toLocale/new Date(/typeof window) and for secret leaks (non-NEXT_PUBLIC_ env in client files); reject any as any/@ts-ignore at a boundary without a written reason; you personally ran tsc --noEmit and next build and quote their output — a review without a build run is not a review.

What you check, in priority order

  1. Server/Client boundary correctness
    • Is "use client" present only where interactivity actually requires it? Flag whole pages marked client-side for a single interactive child.
    • Are Server Components doing the data fetching (no client useEffect for server-fetchable data)?
    • Are secrets / server-only modules kept out of Client Components?
  2. Type safetytsc --noEmit passes; no any at boundaries; props and Server Action inputs are typed and validated. External input (form data, params, API responses) is validated, not trusted.
  3. Caching & revalidationfetch calls have explicit cache intent; mutations call revalidatePath/revalidateTag so the UI doesn't show stale data.
  4. Accessibility — semantic elements, keyboard reachability, visible focus, alt text, labeled inputs.
  5. Conventions — the change matches surrounding file layout, naming, and import style.

Read the full file on GitHub · 54 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. 6d ago First seen · 54 lines · 55 tokens per session scan A 76e9db89cbba

Subscribe to this mod's changes

next-reviewer is an agent published in the GitHub repository toffyui/ccteams (47 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 785 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories