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 FoneClaw-AI/foneclaw-android --skill openappgit clone --depth 1 https://github.com/FoneClaw-AI/foneclaw-androidWrote 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/foneclaw-ai/foneclaw-android/openapp)<a href="https://agentmods.dev/skills/foneclaw-ai/foneclaw-android/openapp"><img src="https://agentmods.dev/badge/skills/foneclaw-ai/foneclaw-android/openapp/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/foneclaw-ai/foneclaw-android/openapp"><img src="https://agentmods.dev/badge/skills/foneclaw-ai/foneclaw-android/openapp.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 | $0.00027 | $0.01691 |
| Opus 5.5 | $0.00011 | $0.00676 |
| Sonnet 5.5 | $0.00005 | $0.00338 |
| Haiku 4.5 | $0.00003 | $0.00169 |
Grade A, and why
OpenAppSkill 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 26d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open App Skill
Skill Name
Open App
Description
Use this skill when the user asks to open, launch, enter, or use an Android app. The core goal is to bring the user-specified app to the foreground. Only when the app is not installed, or the user explicitly asks to download/install it, do you enter the Google Play lookup and install flow.
This skill must fail fast. Do not, on failure, try other apps, other regional variants, third-party app stores, or fuzzy substitutes unless the user explicitly asks.
Required Tools
launch_app: Open a launchable app by Android package name or installed app display name.web_search: Query official Google Play links, package names, and regional variant information when needed.play_store_check_app: Check whether an app exists on Google Play using an exact package name.play_store_install: Open the Google Play detail page for an exact package name, tap Install, and wait for installation to finish.
Intent Rules
- When the user says "open," "launch," "enter," "use," "open," "launch," or "go to," treat it as an open intent.
- When the user says "download," "install," "get," "install," or "download," treat it as an install intent.
- When the user asks to "install then open," after a successful install you must call
launch_app. - When the user explicitly says "install only," "download only," or "do not open," stop after installation; do not open the app.
- When the user provides neither an app name nor a package name, first ask which app to open.
Main Workflow
1. Open First For Open Intent
- For an open intent, call
launch_appfirst, using the app name or package name from the user's current request. - If
launch_appcompletes normally, the task is complete. Do not infer success from a text prefix. - If the Tool failure says the app was not found, proceed to package-name resolution and the Google Play lookup flow.
- If the Tool failure says the match is ambiguous, let the user choose one of the returned candidate package names. Do not install any app before the user confirms.
- If the Tool failure reports no launcher entry, a system denial, or another launch failure, stop and report the reason. Do not treat Google Play as a universal fix.
- Only skip this step when the user explicitly asks to "download only / install only."
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.
- 26d ago Changed · -1 lines 7897de4a5e49
- 1mo ago First seen · 123 lines · 27 tokens per session scan A bab4c57d9305
OpenAppSkill is a skill published in the GitHub repository FoneClaw-AI/foneclaw-android (16 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 1,691 once invoked, about $0.0001 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.
Other skills, from other repositories
navigate
Call the runintent tool with the following exact parameters.
earllm-build
Build, maintain, and extend the EarLLM One Android project — a Kotlin/Compose app that connects Bluetooth earbuds to an LLM via voice pipeline.
mobile-design
Mobile UX patterns, touch interactions, gesture design, mobile-first principles, app navigation, and mobile performance.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
analyzing-android-malware-with-apktool
Perform static analysis of Android APK malware using apktool for resource decompilation, jadx for Java source recovery, and androguard for manifest inspection, dangerous permission-combination detection, and identification of obfuscated code, dynamic code loading, and reflection-based API calls. Use to statically…
omh-apple-design
This is an OMH apple-design workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).