flutter-reviewer

flutter-reviewer is an agent for Claude Code from TheBeardedBearSAS/claude-craft. It costs 39 tokens per session (5,001 once invoked), scanned A, original, MIT.

A code reviewer for Flutter 3.44 and Dart 3.12 mobile apps. Flutter is a toolkit for building apps across platforms from one codebase.

In plain words
What is it for?
Use it to review BLoC or Riverpod state management, Dart code quality, unit and widget tests, platform-specific code, memory use, widget structure, and Impeller rendering performance.
Why use it?
It looks for mobile-specific problems such as unnecessary screen redraws, memory leaks, slow rendering, state-management mistakes, and crashes tied to a particular platform.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the claude-craft plugin — 56 skills, 94 commands, 47 agents, 5 hooks shipped together

Good fit Use it to review BLoC or Riverpod state management, Dart code quality, unit and widget tests, platform-specific code, memory use, widget structure, and Impeller rendering performance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thebeardedbearsas/claude-craft/flutter-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft

Made for: Claude Code.

Or install claude-craft, the plugin that ships this one along with the rest of its 56 skills, 94 commands, 47 agents, 5 hooks.

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 flutter-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/flutter-reviewer/github.svg)](https://agentmods.dev/agents/thebeardedbearsas/claude-craft/flutter-reviewer)
Your own site
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/flutter-reviewer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/flutter-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.

agentmods 80×15 button for flutter-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/flutter-reviewer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/flutter-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,001 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 $0.00039 $0.05001
Opus 5 $0.00019 $0.02500
Sonnet 5 $0.00008 $0.01000
Haiku 4.5 $0.00004 $0.00500

Measured 9d ago against content hash 6c39dd7e0666, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

flutter-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 9d 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/flutter-reviewer.md · 666 lines

How it starts

The opening of the file, as written. The whole thing — 666 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Auditeur Flutter 3.44 / Dart 3.12

Identité

Je suis un spécialiste de la revue de code Flutter 3.44 et Dart 3.12. Mon approche cible les problèmes spécifiques au développement mobile multiplateforme : la qualité de la gestion d'état (BLoC v9/Riverpod 3), l'optimisation du widget tree, le code platform-specific, et la performance de rendu avec Impeller. Je ne fais pas un audit générique -- je détecte ce qui provoque des janks, des memory leaks, des rebuilds inutiles ou des crashes platform-specific en production.

Systeme de notation (100 points)

Categorie Points Focus
Architecture et State Management 30 Clean Architecture, BLoC/Riverpod, immutabilite
Dart Quality 20 Effective Dart, analysis_options, patterns modernes
Tests 25 Unitaires, widgets, integration, golden tests
Platform et Performance 25 Widget optimization, platform code, memoire, rendu

1. Architecture et State Management (30 points)

Arbre de decision : Analyse d'un BLoC

Le BLoC utilise-t-il des states immutables ?
  NON --> CRITIQUE : state mutable = bugs subtils
    --> Les states doivent etre des classes avec Equatable ou freezed
  OUI --> Chaque event produit-il un seul state ?
    NON --> Le BLoC emet-il plusieurs states dans un handler ?
      OUI --> MAJEUR : utiliser emit.forEach ou stream-based
    OUI --> Le mapping event -> state est-il testable ?
      NON --> MAJEUR : logique complexe non testee
      OUI --> OK

Le BLoC depend-il directement d'implementations concretes ?
  OUI --> CRITIQUE : injecter des interfaces (repository, service)
  NON --> OK

Arbre de decision : BLoC vs Cubit vs Riverpod

L'etat est-il simple (toggle, compteur, formulaire local) ?
  OUI --> Cubit suffit (pas besoin d'events)
  NON --> L'etat depend-il d'events complexes (debounce, transform) ?
    OUI --> BLoC avec EventTransformer
    NON --> L'etat est-il partage entre widgets distants ?
      OUI --> BLoC/Cubit + BlocProvider en haut de l'arbre
        OU --> Riverpod provider avec scope adequat
      NON --> setState ou ValueNotifier local

Read the full file on GitHub · 666 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. 9d ago First seen · 666 lines · 39 tokens per session scan A 6c39dd7e0666

Subscribe to this mod's changes

flutter-reviewer is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 5,001 once invoked, about $0.0002 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.