mobile-navigation

mobile-navigation is a skill for Claude Code, Codex from makifbaysal/tasktrooper. It costs 48 tokens per session (788 once invoked), scanned A, original, Apache-2.0.

A guide to moving between mobile screens, tabs, and deep links. A deep link is a link that opens a particular screen directly, while a navigation stack records where the user has been.

In plain words
What is it for?
Use it when adding screens, tabs, deep links, login transitions, or back-button and swipe-back handling in Flutter, SwiftUI, or Compose apps.
Why use it?
It helps avoid stale back histories, incorrect deep-link destinations, lost tab state, and user data leaking across an authentication boundary.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when adding screens, tabs, deep links, login transitions, or back-button and swipe-back handling in Flutter, SwiftUI, or Compose apps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/makifbaysal/tasktrooper/mobile-navigation
Install

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.

Any agent
npx skills add makifbaysal/tasktrooper --skill mobile-navigation
Clone the repo
git clone --depth 1 https://github.com/makifbaysal/tasktrooper

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mobile-navigation

README.md
[![agentmods](https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/mobile-navigation/github.svg)](https://agentmods.dev/skills/makifbaysal/tasktrooper/mobile-navigation)
Your own site
<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/mobile-navigation"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/mobile-navigation/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.

agentmods 80×15 button for mobile-navigation

Your own site · 80×15
<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/mobile-navigation"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/mobile-navigation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 788 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00788
Opus 5.5 $0.00019 $0.00315
Sonnet 5.5 $0.00010 $0.00158
Haiku 4.5 $0.00005 $0.00079

Measured 8d ago against content hash e54a09383a09, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mobile-navigation 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 8d 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.

catalog/agents/mobile-developer/skills/mobile-navigation/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mobile Navigation

Overview

Navigation bugs rarely show up in a widget test — they show up as a stale back stack, a deep link that opens the wrong screen, or state from a previous session leaking past login. Use the platform's own navigation stack, not a hand-rolled one, and verify a deep link by actually following it, not by reading the routing table.

Per-stack APIs

  • Flutter: go_router (declarative routing — see flutter-setup-declarative-routing if the repo is adopting it) for stack + deep-link handling. PopScope, not the deprecated WillPopScope, to intercept back.
  • SwiftUI: NavigationStack(path:) + .navigationDestination(for:) for a programmatic, type-safe stack; the Tab API for top-level tab navigation.
  • Compose: Navigation 3 with type-safe routes; NavigationSuiteScaffold to switch a bottom nav bar to a nav rail at the ≥600dp breakpoint (see android-compose-patterns).

Rules

  • Pass IDs, not whole objects, through navigation params — the destination screen re-fetches or reads from the shared state/cache by ID. An object passed by reference goes stale the moment the source list refreshes.
  • Preserve per-tab state across tab switches (scroll position, in-progress form) unless the task says otherwise — switching tabs is not meant to reset a screen.
  • Reset navigation state intentionally at auth boundaries: after logout, clear every stack back to the entry point; after completing a flow (checkout, onboarding), pop back to where it makes sense to land, not back through the flow's own screens.
  • Stack navigators for drill-in flows, tab navigators for top-level sections. Don't nest navigators deeper than the user can reason about (three levels is usually the practical ceiling).
  • Don't hide the tab bar on push on iOS unless the task explicitly asks — losing the tab bar mid-flow disorients the user about where they are in the app.
  • Hardware/predictive back does what the visible back affordance does — never let them diverge (see android-compose-patterns's predictive-back section for why onBackPressed alone is no longer reliable at targetSdk 36).

Read the full file on GitHub · 54 lines

Changes

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.

  1. 8d ago First seen · 54 lines · 48 tokens per session scan A e54a09383a09

Subscribe to this mod's changes

mobile-navigation is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 788 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-05.