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 skills add ComeOnOliver/skillshub --skill axiom-app-compositiongit clone --depth 1 https://github.com/ComeOnOliver/skillshubWrote 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/skills/comeonoliver/skillshub/axiom-app-composition)<a href="https://agentmods.dev/skills/comeonoliver/skillshub/axiom-app-composition"><img src="https://agentmods.dev/badge/skills/comeonoliver/skillshub/axiom-app-composition/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.
<a href="https://agentmods.dev/skills/comeonoliver/skillshub/axiom-app-composition"><img src="https://agentmods.dev/badge/skills/comeonoliver/skillshub/axiom-app-composition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.09289 |
| Opus 5 | $0.00036 | $0.04645 |
| Sonnet 5 | $0.00015 | $0.01858 |
| Haiku 4.5 | $0.00007 | $0.00929 |
Grade A, and why
axiom-app-composition scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
item = await ItemService.fetch(itemID) How it starts
The opening of the file, as written. The whole thing — 1,464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Composition
When to Use This Skill
Use this skill when:
- Structuring your @main entry point and root view
- Managing authentication state (login → onboarding → main)
- Switching between app-level states without flicker
- Handling scene lifecycle events (scenePhase)
- Restoring app state after termination
- Deciding when to split into feature modules
- Coordinating between multiple windows (iPad, axiom-visionOS)
Example Prompts
| What You Might Ask | Why This Skill Helps |
|---|---|
| "How do I switch between login and main screens?" | AppStateController pattern with validated transitions |
| "My app flickers when switching from splash to main" | Flicker prevention with animation coordination |
| "Where should auth state live?" | App-level state machine, not scattered booleans |
| "How do I handle app going to background?" | scenePhase lifecycle patterns |
| "When should I split my app into modules?" | Decision tree based on codebase size and team |
| "How do I restore state after app is killed?" | SceneStorage and state validation patterns |
Quick Decision Tree
What app-level architecture question are you solving?
│
├─ How do I manage app states (loading, auth, main)?
│ └─ Part 1: App-Level State Machines
│ - Enum-based state with validated transitions
│ - AppStateController pattern
│ - Prevents "boolean soup" anti-pattern
│
├─ How do I structure @main and root view switching?
│ └─ Part 2: Root View Switching Patterns
│ - Delegate to AppStateController (no logic in @main)
│ - Flicker prevention with animation
│ - Coordinator integration
│
├─ How do I handle scene lifecycle?
│ └─ Part 3: Scene Lifecycle Integration
│ - scenePhase for session validation
│ - SceneStorage for restoration
│ - Multi-window coordination
│
├─ When should I modularize?
│ └─ Part 4: Feature Module Basics
│ - Decision tree by size/team
│ - Module boundaries and DI
│ - Navigation coordination
│
└─ What mistakes should I avoid?
└─ Part 5: Anti-Patterns + Part 6: Pressure Scenarios
- Boolean-based state
- Logic in @main
- Missing restoration validation
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.
- 6d ago First seen · 1,464 lines · 73 tokens per session scan A d4d5b5d50cbc
axiom-app-composition is a skill published in the GitHub repository ComeOnOliver/skillshub (63 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 9,289 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
swift-actor-persistence
Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.
swift-protocol-di-testing
Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing.
field-service
Build ServiceNow Field Service Management — wmorder work orders, wmtask tasks, wmresource technicians with skills/territories, dispatch/auto-assignment, mobile status updates, and time entries.
mobile-development
Configure ServiceNow Mobile (Now Mobile/Agent) — syssgmobileapp screens, card builders, push notifications, offline sync rules, mobile actions for barcode/GPS, and offline-queue change processing.
cmd_flutter_build
Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.
cmd_flutter_review
Review Flutter/Dart code for idiomatic patterns, widget best practices, state management, performance, accessibility, and security. Invokes the flutter-reviewer agent.