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/williamcorrea23/androidbuilder-mcp/build-app-inventor-appsnpx skills add williamcorrea23/androidbuilder-mcp --skill build-app-inventor-appsgit clone --depth 1 https://github.com/williamcorrea23/androidbuilder-mcpWrote 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/williamcorrea23/androidbuilder-mcp/build-app-inventor-apps)<a href="https://agentmods.dev/skills/williamcorrea23/androidbuilder-mcp/build-app-inventor-apps"><img src="https://agentmods.dev/badge/skills/williamcorrea23/androidbuilder-mcp/build-app-inventor-apps.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00779 |
| Opus 5 | $0.00024 | $0.00390 |
| Sonnet 5 | $0.00010 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
build-app-inventor-apps 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 5d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build App Inventor Apps
Use this skill when working with App Inventor-family browser IDEs through the androidbuilder-mcp server.
Workflow
- Confirm Chrome or Chromium is running with
--remote-debugging-port=9222using a dedicated profile. - Call
list_ide_tabs. When multiple tabs exist, require an explicitselect_ide_tab; never infer one by title or tab order. - Call
get_project_infoand reportprovider,origin,tabId,validated, capabilities, screen, and view. - Use read tools before write tools:
list_screensget_component_treeget_component_propertiesget_blocks_xml
- Switch views in the browser UI when a tool reports the wrong view:
- Designer view for component tree/properties/property updates.
- Blocks view for Blockly XML export/import/clear.
- Before mutating, confirm the provider exposes the required capability and the server has
ANDROIDBUILDER_ALLOW_WRITE=1. - A timeout has
outcome: "unknown": inspect current state before any retry. Report success only after observing the requested screen/component/property/block state. - Before destructive operations, require the explicit MCP confirmation token:
clear_blocks:confirm: "CLEAR_BLOCKS"click_element:confirm: "CLICK_ELEMENT"andANDROIDBUILDER_ALLOW_UNSAFE_CLICK=1
Safe Defaults
Treat read-only inspection as safe. Treat property updates, block injection, and block clearing as project mutations.
Prefer targeted tools over click_element. Use click_element only as a last resort, after explaining the selector and expected effect.
Provider validation is distinct from recognition. Respect the validated field returned at runtime. Do not present an unvalidated provider as production-supported. AppyBuilder is read-only/experimental.
Offline archives
Set ANDROIDBUILDER_PROJECT_ROOT to a dedicated directory and pass only paths relative to it.
- AIA: use
inspect_aia,validate_aia,diff_aia, and boundedread_archive_entry. - AIX: use
inspect_aix,validate_aix, and boundedread_archive_entry. - Treat every archive as untrusted. Never execute JAR, AAR, native library, YAIL, asset, or extension code.
- Do not claim editing, repacking, import, APK/AAB compilation, or generic ZIP support.
What ships with it
2 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.
- 5d ago First seen · 60 lines · 48 tokens per session scan A 1434d90d140b
build-app-inventor-apps is a skill published in the GitHub repository williamcorrea23/androidbuilder-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 779 once invoked, about $0.0002 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
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.
swift-actor-persistence
Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.
building-ui
Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.
use-dom
Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.
ii-app
Use this skill when you need to initialize or restart local web and mobile app projects through the bundled Rust ii-app CLI instead of calling MCP tools.
flutter-pre-caching
Use when preloading fonts, asset/network images, Lottie/Rive animations, local JSON/config, warming initial API data, or optimizing Flutter Web startup.