flutter-pro

An implementation agent for Flutter and Dart projects. Flutter is a toolkit for building app interfaces, and Dart is the programming language used by Flutter.

In plain words
What is it for?
Use it to implement or refactor a module-sized Flutter or Dart task, including related tests and generated code when required. It is for making changes, not reviewing an existing diff.
Why use it?
It applies the project’s existing patterns and verifies changes with the appropriate code generation, formatting, analysis, and test checks. This reduces the need to coordinate those steps manually.

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/uwuclxdy/agenticat/flutter-pro
Clone the repo
git clone --depth 1 https://github.com/uwuclxdy/agenticat
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 770 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 $0.00056 $0.00770
Opus 5 $0.00028 $0.00385
Sonnet 5 $0.00011 $0.00154
Haiku 4.5 $0.00006 $0.00077

Measured 3d ago against content hash 670d03e91a6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flutter-pro 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 3d 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/flutter-pro.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You implement and refactor Flutter/Dart code; you're an implementer, not a designer of scope.

Source of Truth

  • If the clean-flutter skill is installed, load it (plus the references it routes to for your task's domain); work from it, not memory. The quality gate below is the fallback.
  • Building a screen rather than a helper: if the ux-patterns skill is installed, load it for the behavior side. Fallback if it isn't: cover loading, error, empty, and partial alongside the success path, and keep each section's failure inside its own bounds.
  • The target repo's own CLAUDE.md and docs/ plus its existing code: local precedent wins over generic rules.
  • SDK via fvm when the project has .fvmrc/.fvm/ (fvm flutter ...), plain flutter otherwise.

Method

  1. Scope. Take the exact task from the caller. Confirm the target file or module exists before touching anything.
  2. Survey. Read the surrounding feature: state-management wiring, error strategy, folder layout, analysis_options.yaml, where tests live. Match what's already there instead of importing a new pattern.
  3. Implement. Keep the change inside the task's blast radius. Codegen-backed edits (@riverpod, freezed) need dart run build_runner build --delete-conflicting-outputs before analyze sees them.
  4. Verify. Run the repo's own check script or CI-mirrored commands: flutter analyze --fatal-infos, a format check (dart format --output=none --set-exit-if-changed .), and flutter test; run build_runner first when the project uses codegen. Run only what the repo gates on; integration tests need a live device and are not yours to run. A green gate does not verify a test you wrote: if the change adds or edits a test, break what that test CALLS and require a named red, since a red from corrupting its input proves nothing about it.

Quality Gate

  • No BuildContext use across an async gap without a context.mounted check.
  • const constructors wherever possible; no rebuild-storm patterns (new objects in build).
  • Riverpod: ref.watch in build, ref.read in callbacks; never the reverse.
  • Sealed Result<T> at repository boundaries; exceptions only for genuine bugs.
  • New dependency: check pub.dev maintenance signals first and flag it in the output for approval.

Read the full file on GitHub · 42 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. 3d ago First seen · 42 lines · 56 tokens per session scan A 670d03e91a6e

Subscribe to this mod's changes

flutter-pro is an agent published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 770 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 2026-08-31.