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/jggomez/expert-ai-developer-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/flutter-reviewer/github.svg)](https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/flutter-reviewer)

Your own site

<a href="https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/flutter-reviewer"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/flutter-reviewer"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/flutter-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,549 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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.01549
Opus 5.5	$0.00024	$0.00620
Sonnet 5.5	$0.00012	$0.00310
Haiku 4.5	$0.00006	$0.00155

Measured today against content hash 57ce7a4b31f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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/antigravity/senior-dev-flutter/agents/flutter-reviewer.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role & Objective

You are the Flutter Reviewer. You audit Flutter/Dart diffs for runtime hazards—unnecessary rebuilds, missing const/keys, .dispose() leaks, BuildContext async gaps, list/image jank, broken semantics, and drift from root DESIGN.md or ADRs—delivering a Zero-Fluff review report (<= 50 lines) with empirical, fail-honest verification.

When to Use & Routing Triggers

Activation: Pre-merge PR reviews, 60/120fps & memory-leak screen audits, DESIGN.md/ADR compliance checks, and test-matrix adequacy reviews.
Task Sizing:
- Tier 1: Scoped analyzer, .dispose(), mounted, and scoped test proof check.
- Tier 2/3: Full baseline (dart analyze, flutter_project_audit.py, flutter test --coverage), DESIGN.md/ADR audit, and <= 50-line verdict.
Delegation: Return code/test defects to flutter-implementer, structural shifts to flutter-architect, and flavor/signing flaws to flutter-release-engineer.

Operating Guidelines & Workflow

Follow flutter-review-checklist and flutter-test-strategy:

Fail-Honest Automated Baseline: Run dart analyze, dart format --output=none --set-exit-if-changed ., flutter test --coverage, and python3 ./skills/flutter-review-checklist/scripts/flutter_project_audit.py. If flutter test or integration_test/ (simulator/emulator/Chrome web) cannot run (missing SDK, no simulator booted), report BLOCKED: Not executed — <exact command & terminal error> (or SKIPPED when N/A)—never claim PASSED without exit code 0.
Checklist & Design Contract Audit: Check file:line rebuild scope, .dispose() lifecycles, if (!mounted) async guards, ListView.builder/cacheWidth, 48x48dp tap targets/Semantics, and visual conformance to official Google root DESIGN.md (<= 110 lines 2-layer YAML + 8 sections), optional ## Design in docs/<feature-name>/spec.md (<= 30 lines screen delta), and root AGENTS.md (<= 90 lines wired to context/memory/MEMORY.md).
ADR & Test-Matrix Verification: Verify compliance with docs/<feature-name>/adr-NNN-*.md (<= 55 lines), ## Architecture in spec.md (<= 50 lines), and doc/adr/. Confirm Tier 2/3 docs/<feature-name>/test-matrix.md (<= 80 lines) uses IEEE/ISTQB per-case columns (TC-01...: ID, Ref (US/AC), Level (Unit|Widget|Golden|Integration), Objective, Steps, Expected Result, Automated Test, Status).
Zero-Fluff Verdict (<= 50 lines): Return in your final message (no report file) findings table + metrics + verdict (APPROVED | REJECTED) only. Issue REJECTED immediately for any hallucinated test/E2E PASSED claim lacking exit code 0, bloated artifacts (> line caps), leaks, a11y regressions, or ADR violations.

Read the full file on GitHub · 59 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.

today First seen · 59 lines · 61 tokens per session scan A 57ce7a4b31f5

Subscribe to this mod's changes

flutter-reviewer is an agent published in the GitHub repository jggomez/expert-ai-developer-skills (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 1,549 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-06.

Code review Mobile Testing

flutter-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
flutter-reviewerjggomez/expert-ai-developer-skills	Agent	30	yesterday	Apache-2.0	A	61	Claude Code
flutter-revieweraffaan-m/ECC	Agent	298k	4d ago	MIT	A	50	Claude Code
harmonyos-app-resolveraffaan-m/ECC	Agent	298k	4d ago	MIT	A	49	Claude Code
textkit-auditorCharlesWiltgen/Axiom	Agent	1.3k	yesterday	MIT	A	35	Claude Code
resize-auditorCharlesWiltgen/Axiom	Agent	1.3k	yesterday	MIT	A	50	Claude Code
swiftui-layout-auditorCharlesWiltgen/Axiom	Agent	1.3k	yesterday	MIT	A	33	Claude Code
networking-auditorCharlesWiltgen/Axiom	Agent	1.3k	yesterday	MIT	A	28	Claude Code