flutter-ai-starter
AGENTS.md0 starsChanged 5 months agoMITView on GitHub
Agent-native Flutter starter. Keep changes minimal, verified, and aligned with the repository contract. Run the single gate before calling work done: This runs format, analyze, build_runner, tests with coverage, coverage threshold, integration smoke, agent-doc lint, and evals when those tools exist. Load one primary skill from .cursor/skills/<name>/SKILL.md when it matches the task. Chain only when the primary skill says to.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository26 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/000-project.mdcCursor rule
- .cursor/rules/accessibility.mdcCursor rule
- .cursor/rules/api-integration.mdcCursor rule
- .cursor/rules/architecture.mdcCursor rule
- .cursor/rules/dart-style.mdcCursor rule
- .cursor/rules/design-system.mdcCursor rule
- .cursor/rules/flutter-ui.mdcCursor rule
- .cursor/rules/security.mdcCursor rule
- .cursor/rules/state-management.mdcCursor rule
- .cursor/rules/testing.mdcCursor rule
- doubt-reviewSkill
- fix-dependenciesSkill
- flutter-componentSkill
- flutter-implementSkill
- generate-mocksSkill
- grind-until-greenSkill
- implement-tddSkill
- monitor-terminalSkill
- plan-featureSkill
- repo-navigatorSkill
- review-codeSkill
- save-contextSkill
- suggest-ruleSkill
- write-commitSkill
- write-readmeSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Run the single gate before calling work done:
- Distinctive: line 28
No Riverpod, GetX, GetIt, Bloc, or client AI SDKs without user approval and a dated ADR.
- Distinctive: line 53
Do not edit unrelated files or revert user changes.
- Distinctive: line 54
Ask before adding new rules or skills.
- Very specific: line 56
After touching code, update tests required by .cursor/rules/testing.mdc.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS.md
Agent-native Flutter starter. Keep changes minimal, verified, and aligned with the repository contract.
First Read
docs/ARCHITECTURE.mdfor stack, folders, and boundaries.docs/CONVENTIONS.mdfor style, commits, and context rules.docs/DECISIONS.mdbefore changing architecture or dependencies.- Relevant
context/files before domain or project-specific work.
Verify
Run the single gate before calling work done:
dart run tool/verify.dartThis runs format, analyze, build_runner, tests with coverage, coverage threshold, integration smoke, agent-doc lint, and evals when those tools exist.
Stack Rules
- Flutter stable, Dart 3.x, feature-first MVVM.
- State and DI:
provider+ChangeNotifierViewModels. - Routing:
go_router. - Models/errors:
freezed+json_serializable; repositories returnFuture<Result<T, Failure>>. - No Riverpod, GetX, GetIt, Bloc, or client AI SDKs without user approval and a dated ADR.
Load Guides On Demand
docs/agent-guides/stack.mdfor MVVM, provider, routing, and data boundaries.docs/agent-guides/testing.mdfor unit/widget/golden/integration expectations.docs/agent-guides/security.mdfor secrets, logging, Supabase, and AI calls.docs/BACKEND.mdwhen enabling Supabase.docs/QUALIFIED_AGENT_CONTRACT.mdwhen changing rules, skills, or enforcement.
Skills
Load one primary skill from .cursor/skills/<name>/SKILL.md when it matches the task. Chain only when the primary skill says to.
plan-featurefor non-trivial features or refactors.flutter-implementfor app code.implement-tddfor red-green-refactor slices.flutter-componentfor design-system components.grind-until-greenfor analyze/test/build failures.review-codefor reviews.doubt-reviewfor auth, payments, migrations, deletion, or irreversible choices.fix-dependencies,generate-mocks,write-commit,write-readme,save-context,monitor-terminal,suggest-rule,repo-navigatoras needed.
Operating Norms
- Do not edit unrelated files or revert user changes.
- Ask before adding new rules or skills.
- Save durable research in
context/; save architecture decisions indocs/DECISIONS.md. - After touching code, update tests required by
.cursor/rules/testing.mdc.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.