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 kelvinkosbab/AppBootstrapAI --skill xml-to-compose-migration-progit clone --depth 1 https://github.com/kelvinkosbab/AppBootstrapAIWrote 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/kelvinkosbab/appbootstrapai/xml-to-compose-migration-pro)<a href="https://agentmods.dev/skills/kelvinkosbab/appbootstrapai/xml-to-compose-migration-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/xml-to-compose-migration-pro/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/kelvinkosbab/appbootstrapai/xml-to-compose-migration-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/xml-to-compose-migration-pro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00078 | $0.01559 |
| Opus 5.5 | $0.00031 | $0.00624 |
| Sonnet 5.5 | $0.00016 | $0.00312 |
| Haiku 4.5 | $0.00008 | $0.00156 |
Grade A, and why
xml-to-compose-migration-pro 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 2mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review and assist the migration from XML-based Android UI (Fragments + layouts + RecyclerViews) to Jetpack Compose. Migration is incremental by default — ComposeView / AndroidView make it possible to ship a hybrid screen-by-screen without a big-bang rewrite. Report only genuine migration issues; don't nitpick the existing XML where it doesn't need to change.
Review process:
- Frame the migration scope using
references/interop-strategy.md— incremental vs all-at-once, where to put interop boundaries. - Translate layouts using
references/layout-migration.md—LinearLayout/ConstraintLayout/FrameLayout/RelativeLayoutto Compose equivalents. - Translate RecyclerViews using
references/recyclerview-to-lazy.md— including stable keys, item-content separation, and DiffUtil → automatic recomposition. - Translate Fragments using
references/fragment-to-composable.md— lifecycle ownership, ViewBinding → parameters, animations. - Translate Navigation Component using
references/navigation-migration.md—NavGraphXML →NavHostKotlin DSL. - Bridge ViewModels using
references/viewmodel-bridge.md— existing ViewModels stay; only the View layer changes. - Translate themes using
references/themes-styles.md—styles.xml→MaterialTheme(colorScheme, typography, shapes).
If doing a partial review, load only the relevant reference files.
Core Instructions
- Migrate incrementally. A full XML-to-Compose rewrite of a non-trivial app is months of work; an incremental screen-by-screen migration ships value continuously.
ComposeViewin an XML layout (orAndroidViewin a Composable) makes it possible. - Existing ViewModels stay. Compose works with
ViewModel+StateFlow+LiveDatawithout changes. The migration is a View-layer concern, not a state-layer one. - Don't preserve XML idioms in Compose. A
LinearLayout(orientation = horizontal)becomes aRow— not aColumnwithModifier.fillMaxWidth().wrapContentHeight(). A literal translation produces awkward Compose. - Test parity before deleting XML. Snapshot tests, manual QA, or feature-flag the new screen alongside the old. Don't delete the XML in the same PR that introduces the Composable.
- Use semantic
testTagfor tests, not preservedandroid:idvalues. XML view IDs (R.id.submit_button) don't carry over; Compose usesModifier.testTag(...)andModifier.semantics { contentDescription = ... }. AndroidView { factory: ... update: ... }is for one-way binding from Compose state to aView. Don't try to round-trip — if state needs to flow back, lift it.
What ships with it
7 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.
- 2mo ago First seen · 98 lines · 78 tokens per session scan A 2d0a6232c329
xml-to-compose-migration-pro is a skill published in the GitHub repository kelvinkosbab/AppBootstrapAI (8 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,559 once invoked, about $0.0003 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 2026-08-31.
xml-to-compose-migration-pro compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xml-to-compose-migration-prokelvinkosbab/AppBootstrapAI | Skill | 8 | yesterday | MIT | A | 78 | Claude Code |
| kmp-glassmorphism-uiAks-4125/kmp-glassmorphism-skill | Skill | 5 | 3mo ago | MIT | A | 81 | Claude Code, Codex |
| argent-react-native-app-workflowsoftware-mansion/argent | Skill | 3.2k | today | Apache-2.0 | A | 46 | Claude Code, Codex |
| mobile-automationmobile-next/mobile-mcp | Skill | 10k | today | Apache-2.0 | A | 58 | Claude Code, Codex |
| argent-react-native-optimizationsoftware-mansion/argent | Skill | 3.2k | today | Apache-2.0 | A | 71 | Claude Code, Codex |
| sceneviewsceneview/sceneview | Skill | 1.4k | today | Apache-2.0 | A | 156 | Codex |
| argent-settings-permissionssoftware-mansion/argent | Skill | 3.2k | today | Apache-2.0 | A | 140 | Claude Code, Codex |