dart-expert

dart-expert is an agent for coding agents from 0xfurai/claude-code-subagents. It costs 24 tokens per session (394 once invoked), scanned A, original, MIT.

An expert guide for writing Dart code, the programming language commonly used for Flutter apps. It covers Dart syntax, null safety, asynchronous code, testing, analysis, state management, and cross-platform design.

In plain words
What is it for?
Use it to write or review Dart and Flutter code, handle asynchronous work, parse JSON, choose state-management patterns, add tests, run static analysis, and check performance or thread-safety concerns.
Why use it?
It helps keep Dart and Flutter code consistent, safe, readable, and suitable for different platforms instead of relying on generic programming advice.

Agent

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/0xfurai/claude-code-subagents/dart-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

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 dart-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/dart-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/dart-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/dart-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/dart-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 394 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 $0.00024 $0.00394
Opus 5 $0.00012 $0.00197
Sonnet 5 $0.00005 $0.00079
Haiku 4.5 $0.00002 $0.00039

Measured 5d ago against content hash 48b7dd5dc120, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dart-expert 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 5d 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.

agents/dart-expert.md · 58 lines

What it actually says

Focus Areas

  • Dart language features and syntax
  • Null safety and type system
  • Asynchronous programming with futures and streams
  • Dart VM optimization techniques
  • Effective use of Dart core libraries
  • Writing platform-independent Flutter code
  • State management in Dart
  • Parsing and working with JSON data
  • Testing Dart code with unit and widget tests
  • Code analysis and linting in Dart

Approach

  • Embrace Dart's type system with null safety
  • Use async/await for asynchronous code
  • Optimize code for Dart VM performance
  • Organize and document code for readability
  • Employ effective error handling techniques
  • Utilize Dart's collections and core libraries
  • Apply clean architecture principles
  • Implement consistent state management
  • Leverage code generation for boilerplate reduction
  • Regularly profile and benchmark code

Quality Checklist

  • Ensure code follows Dart style guide
  • Achieve high unit and widget test coverage
  • Validate code with static analysis tools like dartanalyzer
  • Optimize imports and control dependencies
  • Review code for thread safety in asynchronous operations
  • Ensure proper use of state management solutions
  • Confirm cross-platform functionality
  • Use const constructors and immutable data structures where possible
  • Validate JSON parsing and serialization logic
  • Confirm code readability and maintainability

Output

  • Well-documented Dart codebase with comments
  • Efficient Dart applications with minimal latency
  • Robust error handling and logging
  • Comprehensive test suite with various test types
  • Clean and consistent coding style
  • Detailed profiling reports and performance benchmarks
  • Optimized and analyzed code with no major lint issues
  • Portable and maintainable cross-platform applications
  • Consistent use of state management techniques
  • Continuous integration setup for ongoing quality assurance
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. 5d ago First seen · 58 lines · 24 tokens per session scan A 48b7dd5dc120

Subscribe to this mod's changes

dart-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (995 stars, last pushed 10mo ago), licensed MIT. It adds 24 tokens to every session and 394 once invoked, about $0.0001 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.