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.
npx agentmods add instructions/zakariaf/flutter-skills/agents-mdgit clone --depth 1 https://github.com/zakariaf/Flutter-SkillsWrote 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.
[](https://agentmods.dev/instructions/zakariaf/flutter-skills/agents-md)<a href="https://agentmods.dev/instructions/zakariaf/flutter-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/zakariaf/flutter-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01096 | $0.01096 |
| Opus 5 | $0.00548 | $0.00548 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
Flutter-Skills AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for any AI coding agent (Claude Code, Codex, Cursor, Copilot, Gemini CLI, Windsurf, Cline, OpenCode, Antigravity, …) working in a Flutter/Dart project that has these skills installed.
These skills follow the Agent Skills open standard, so they work with any agent that can read Markdown instructions — not only Claude Code.
What these skills are
Each skill is a short playbook at skills/<name>/SKILL.md (or .claude/skills/<name>/SKILL.md once
installed into a project) that encodes the non-negotiable rules for one area of Flutter engineering:
architecture, state (Riverpod 3.x), widgets, async safety, testing, persistence, i18n/RTL,
accessibility, navigation, forms, performance, and the codegen/CI/migration runbooks.
The description in each skill's YAML frontmatter says when it applies. Some skills bundle
references/ (deep-dives), examples/ (complete .dart samples), and scripts/ (runnable checks).
How to use them
- Before writing or reviewing Flutter/Dart code, check whether a skill applies — match the task
to a skill
description. If one matches, read thatSKILL.md(and any reference it points to) and follow it. Do not improvise a different approach when a skill governs the area. - Follow the skill fully, including its Non-negotiable rules, Anti-patterns, and Definition of
done. Run any bundled
scripts/*.shthe skill tells you to before opening a PR. flutter-conventions-indexis the front door — its routing table maps each task to the right deep-dive skill and gives a recommended build order. Start there when unsure.
Intent → skill map
| When you are… | Consult |
|---|---|
| Structuring a project / deciding where code goes | flutter-architecture, project-structure-and-packages |
| Adding a feature / screen | scaffold-feature-module, then the state/widget/nav skills |
| Managing state or dependency injection | state-management-riverpod |
| Building or refactoring UI | widget-composition, adaptive-layout, design-system-structure |
| Loading / empty / error states, snackbars, dialogs, Undo | ui-states-and-feedback |
| Wiring navigation / routes / deep links | navigation-and-routing |
| Building a form or handling input | forms-and-input |
| Handling errors / async | error-handling-typed-results, async-safety |
| Storing data locally | persistence-drift, value-objects-money-and-units |
| Exporting, backing up, sharing, or restoring user data | data-export-and-restore |
| Wiring a side effect or native channel | service-boundary-and-native |
| Localizing / RTL | i18n-rtl-l10n |
| Accessibility | accessibility-as-code |
| Writing tests | testing-strategy, widget-golden-and-a11y-testing |
| Performance / jank | flutter-performance |
| Naming / Dart idioms / docs / lint | naming-conventions, dart3-idioms-and-coding-standards, dartdoc-conventions, lint-and-style-config |
| Codegen / CI / dependencies | codegen-and-toolchain, run-codegen, ci-pipeline-and-gates, dependency-hygiene |
| Applying a schema migration | run-migration |
| Re-baselining golden images | run-goldens-rebaseline |
| End-of-build design/QA review | design-review-workflow |
| Animating, adding haptics, or designing a success/error moment | motion-and-haptics |
| Generating reproducible content from a seed or date | seeded-determinism-and-golden-vectors |
| Cutting a release, signing, store declarations, rollout | release-and-store-shipping |
| Adding ads, a paywall, or an entitlement gate | ads-and-iap-monetization |
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.
- 5d ago First seen · 68 lines · 1,096 tokens per session scan A 170251461e40
Flutter-Skills AGENTS.md is an instructions file published in the GitHub repository zakariaf/Flutter-Skills (2 stars, last pushed 7d ago), licensed MIT. It adds 1,096 tokens to every session, about $0.0055 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.
Other instructions, from other repositories
vgv-ai-flutter-plugin CLAUDE.md
Claude Code instructions for VeryGoodOpenSource/vgv-ai-flutter-plugin, covering hooks, sessionstart hooks, pretooluse hooks and posttooluse hooks.
compose-doctor CLAUDE.md
Instructions for rotemmiz/compose-doctor, covering compose-doctor, status, architecture, scoring and conventions.
compose-doctor AGENTS.md
Instructions for rotemmiz/compose-doctor, covering agents.md — compose-doctor, what compose-doctor is, the fix loop, integrity (non-negotiable) and writing good compose in the first place.
vgv-ai-flutter-plugin AGENTS.md
AGENTS.md instructions for VeryGoodOpenSource/vgv-ai-flutter-plugin, covering vgv ai flutter plugin, project overview, repository structure, skill file format and writing conventions.
android-ai-skills copilot-instructions.md
Instructions for RanaNadeemAslam/android-ai-skills, covering android ai skills — github copilot, architecture, layered architecture, ui layer & state management and viewmodel.
android-finance-spec AGENTS.md
Instructions for brycegao/android-finance-spec: When generating, editing, reviewing, or refactoring this repository, follow all Android finance specs.