flutter-analyze

flutter-analyze is a command for coding agents from aaronbassett/agent-foundry. It costs 26 tokens per session (1,847 once invoked), scanned A, original, MIT.

A command that checks Flutter and Dart code for problems, project-rule violations, and optionally test coverage. Flutter is Google's toolkit for building apps from one codebase.

In plain words
What is it for?
Use it to analyze a Flutter project, fix issues, check Flutter AI rules, treat warnings as errors, produce JSON output, or include coverage analysis.
Why use it?
It brings several project checks and optional automatic fixes into one health check, with strict output available for continuous integration.

Command

Part of the flutter-core plugin — 3 skills, 4 commands, 5 agents, 1 MCP server shipped together

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 commands/aaronbassett/agent-foundry/flutter-analyze
Clone the repo
git clone --depth 1 https://github.com/aaronbassett/agent-foundry

Or install flutter-core, the plugin that ships this one along with the rest of its 3 skills, 4 commands, 5 agents, 1 MCP server.

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-analyze

README.md
[![agentmods](https://agentmods.dev/badge/commands/aaronbassett/agent-foundry/flutter-analyze.svg)](https://agentmods.dev/commands/aaronbassett/agent-foundry/flutter-analyze)
Your own site
<a href="https://agentmods.dev/commands/aaronbassett/agent-foundry/flutter-analyze"><img src="https://agentmods.dev/badge/commands/aaronbassett/agent-foundry/flutter-analyze.svg" alt="Measured on agentmods" 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 1,847 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 $0.00026 $0.01847
Opus 5 $0.00013 $0.00924
Sonnet 5 $0.00005 $0.00369
Haiku 4.5 $0.00003 $0.00185

Measured 4d ago against content hash ae3b8da96a61, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flutter-analyze 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 4d 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.

plugins/flutter-core/commands/flutter-analyze.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flutter Code Analysis

This command performs comprehensive code quality analysis on your Flutter project, checking for issues, verifying Flutter AI rules compliance, and optionally auto-fixing problems.

Usage

/flutter-analyze [options]

Options

  • --fix - Automatically fix issues where possible
  • --rules - Check compliance with Flutter AI rules (flutter/flutter rules.md)
  • --strict - Use strict analysis options (treat warnings as errors)
  • --format=<json|default> - Output format (default: human-readable)
  • --coverage - Include test coverage analysis

Examples

# Basic health check
/flutter-analyze

# Auto-fix issues
/flutter-analyze --fix

# Check Flutter AI rules compliance
/flutter-analyze --rules

# Strict mode for CI/CD
/flutter-analyze --strict --format=json

# Complete analysis with coverage
/flutter-analyze --fix --rules --coverage

Implementation

When this command runs:

1. Environment Verification

Check Flutter and Dart are available:

flutter --version
dart --version

If not found, guide user to install Flutter SDK.

2. Project Detection

Verify we're in a Flutter project:

# Check for pubspec.yaml
if [ ! -f "pubspec.yaml" ]; then
  echo "Error: Not a Flutter project (no pubspec.yaml found)"
  exit 1
fi

# Check if dependencies are up to date
flutter pub get

3. Run Flutter Analyzer

Execute Flutter's analyzer:

flutter analyze --no-pub

Capture output and parse for:

  • Errors (critical issues)
  • Warnings (potential problems)
  • Info (suggestions)
  • Lints (style violations)

4. Run Dart Analyzer (if --strict flag)

dart analyze --fatal-infos --fatal-warnings

This treats warnings and info messages as errors.

5. Check Flutter AI Rules (if --rules flag)

Verify compliance with Flutter AI rules from https://raw.githubusercontent.com/flutter/flutter/refs/heads/main/docs/rules/rules.md

Check for common violations:

Read the full file on GitHub · 335 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. 4d ago First seen · 335 lines · 26 tokens per session scan A ae3b8da96a61

Subscribe to this mod's changes

flutter-analyze is a command published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 19d ago), licensed MIT. It adds 26 tokens to every session and 1,847 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 2026-08-31.