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 skills/evolplus/talos/flutter-implementationnpx skills add evolplus/talos --skill flutter-implementationgit clone --depth 1 https://github.com/evolplus/talosWhat 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 | $0.00051 | $0.01004 |
| Opus 5 | $0.00026 | $0.00502 |
| Sonnet 5 | $0.00010 | $0.00201 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
flutter-implementation 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter Implementation
When to use
Use this after fe-framework-coding-standard selects Flutter for the task surface. This is the default Flutter implementation skill for widgets, pages, state, theming, navigation, accessibility, instrumentation, and normal unit/widget test work.
For platform channels, permissions, flavors, deep links, app lifecycle, native files, or secure storage, also load flutter-platform-integration. For rebuild, list, image, animation, startup, memory, or jank work, also load flutter-performance.
Inputs and outputs
- Inputs: task file, SRS
Frontend-Framework:and §3.4.5 source layout, §3.4.6 frontend env keys, design handoff, Design Element Manifest, visual spec, instrumentation contract, API contracts, current Flutter source tree. - Outputs: Flutter code that fits the existing app architecture, implements every manifest row, uses declared runtime config, exposes stable keys/semantics, preserves accessibility, and updates relevant unit/widget tests.
Procedure
- Identify the app architecture:
- feature/module layout under
lib/; - state approach: Bloc/Cubit, Riverpod, Provider, ValueNotifier,
setState, or project wrapper; - navigation: Navigator, GoRouter, AutoRoute, or project wrapper;
- theming:
ThemeData, extensions, generated tokens, shared widgets.
- feature/module layout under
- Keep boundaries clean:
- pages/screens own navigation, async state, permissions, and orchestration;
- widgets render manifest sections and emit typed callbacks;
- repositories/services stay outside widgets when the project has a data layer.
- Implement from the Design Element Manifest:
- render every field, label, placeholder, action, state copy, list/card item, and dialog/snackbar row;
- preserve Figma order unless product behavior requires a documented deviation;
- include initial, loading, data, empty, validation error, recoverable error, denied permission, disabled, and refreshing states where applicable.
- Use Dart and state safely:
- keep null safety and strong types;
- convert external data into typed models quickly;
- avoid
dynamicexcept at explicit untyped boundaries; - dispose controllers, focus nodes, animation controllers, streams, and subscriptions.
- Build adaptive mobile UI:
- use constraints,
LayoutBuilder, adaptive widgets, and scroll behavior; - respect safe areas, keyboard insets, text scaling, platform navigation, and orientation;
- keep fixed dimensions limited to controls whose format requires them.
- use constraints,
- Add accessibility and instrumentation:
- add
Keyvalues andSemantics(identifier: ...)only fromdocs/instrumentation-contract.md; - use semantic labels, hints, roles, and focus order when visible UI is insufficient;
- keep minimum touch targets at least 48 x 48 logical pixels unless the project standard is stricter.
- add
- Test and verify:
- update widget tests for rendering, validation, and state transitions;
- update unit tests for blocs/notifiers/repositories when logic changes;
- update Patrol/Maestro integration tests only when the task changes a critical flow, following
ui-test-execution; - run
dart format,flutter analyze, relevant unit/widget tests, and platform build checks when touched files require it.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 71 lines · 51 tokens per session scan A 071d55165b5e
flutter-implementation is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,004 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.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
speckit-analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
add-sample
Create a SamplesApp sample page with correct theming and attributes. Use when adding UI samples for controls.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…