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/launch52-ai/flutter-template/plannpx skills add launch52-ai/flutter-template --skill plangit clone --depth 1 https://github.com/launch52-ai/flutter-templateWhat 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 | $0.00050 | $0.01825 |
| Opus 5 | $0.00025 | $0.00912 |
| Sonnet 5 | $0.00010 | $0.00365 |
| Haiku 4.5 | $0.00005 | $0.00183 |
Grade A, and why
plan 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan - Feature Planning & Specification
Comprehensive feature planning that understands the WHOLE feature before any implementation begins. Creates a specification document that provides full context to all other skills.
Why Planning First?
Without planning, each skill works in isolation:
/feature-initcreates scaffolds without knowing API structure/apicreates data layer without knowing what UI needs- Screens get built without knowing what data is available
- Result: Mismatches, rework, incomplete interfaces
With planning:
- Domain models match both API structure AND UI needs
- Repository interfaces have exactly the methods required
- Data sources are properly identified upfront
- Implementation order prevents circular dependencies
- Result: Clean, complete, working feature
When to Use This Skill
- Always before creating a new feature
- When adding significant functionality to existing features
- When the feature involves multiple data sources
- When the feature has complex user flows
- User asks to "plan", "design", or "architect" a feature
Workflow
Phase 1: Discovery
Ask comprehensive questions covering:
- Overview (name, purpose, users)
- Domain model (entities, fields, relationships)
- Data sources (API, Supabase, local storage)
- User flows (screens, navigation, actions)
- Business rules (validation, computed properties)
- Edge cases (empty, offline, cancelled)
See: questions.md for the complete question bank.
Phase 2: Design
Based on discovery, design each layer:
Domain Layer:
- Define entities with all fields and types
- Define repository interface with all needed methods
- Identify enums and value objects
Data Layer:
- Identify all data sources
- Design DTOs/Models for each source
- Plan error handling strategy
- Design caching/offline strategy if needed
Presentation Layer:
- Define each screen's purpose and data requirements
- Define state types for each screen
- Define provider methods
- Plan navigation flow
- Add "Notes for Design" with constraints (NOT layout)
What ships with it
4 files 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 · 234 lines · 50 tokens per session scan A 8dfcf58ff389
plan is a skill published in the GitHub repository launch52-ai/flutter-template (2 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 1,825 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
merge-seed
Merge upstream React Starter Kit updates (the seed remote) into main, preserving this project's identity, scope, and behavior. Use when asked to sync, pull, or merge the seed / starter kit / upstream template.
update-store
ストア情報の更新自動化 — スクリーンショット撮影（シミュレーター × モック画面 × Marionette MCP）とメタデータテキスト更新。ストア更新、スクショ更新、App Store / Google Play のメタデータ更新、リリースノート作成の際に使用すること。.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
effective-dart
Use when writing Dart code, reviewing for style, refactoring naming, adding doc comments, structuring imports, or enforcing type annotations.
flutter-app-architecture
Use when scaffolding a project, refactoring into layers, creating view models/repositories, configuring dependency injection, or implementing unidirectional data flow (MVVM).
firebase-app-check
Use when implementing app attestation, configuring App Check providers, setting up debug tokens, enabling backend enforcement, or managing token refresh.