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 sparesparrow/mcp-project-orchestrator --skill android-testgit clone --depth 1 https://github.com/sparesparrow/mcp-project-orchestratorWrote 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/sparesparrow/mcp-project-orchestrator/android-test)<a href="https://agentmods.dev/skills/sparesparrow/mcp-project-orchestrator/android-test"><img src="https://agentmods.dev/badge/skills/sparesparrow/mcp-project-orchestrator/android-test/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/sparesparrow/mcp-project-orchestrator/android-test"><img src="https://agentmods.dev/badge/skills/sparesparrow/mcp-project-orchestrator/android-test.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 | $0.00104 | $0.01786 |
| Opus 5.5 | $0.00042 | $0.00714 |
| Sonnet 5.5 | $0.00021 | $0.00357 |
| Haiku 4.5 | $0.00010 | $0.00179 |
Grade A, and why
android-test 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 10d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
android-test: build in CI, test on the phone
Generic, project-agnostic. Device control and rooting live in the adb skill (and mcp__adb__* tools); this skill is the test loop on top of it. $ARGUMENTS: a profile name or OWNER/REPO APP_ID, e.g. mia or sparesparrow/cliphist-android com.clipboardhistory.debug.
Paths are relative to this skill directory (~/.claude/skills/android-test/ or .claude/skills/android-test/ in a project).
Why CI builds, the phone tests
The dev host can be too small for Gradle (this one: 2 cores, 7 GB RAM, ~1.6 GB free disk, no SDK). GitHub Actions builds; the phone installs and tests. Nothing here builds locally.
Tools
| Tool | Use |
|---|---|
scripts/phone_ci.sh --repo OWNER/REPO --pkg APP_ID [--ref B] [--run-id N] [--release TAG|latest] [--dispatch] [--timeout S] [--dry-run] |
Download APKs from the newest successful workflow run (artifact device-apks) or a GitHub release; adb install -r -g -t app + androidTest APK; am instrument -w; save instrument.txt, logcat.txt, final-screen.png; print verdict: PASS/FAIL/UNKNOWN (tests=N failed=M). Exit 0 only on OK (N tests) with N > 0. |
scripts/run_scenario.sh --profile profiles/X.env --scenario NAME [--serial S] [--out DIR] (--list) |
UI scenario on the installed app: grants permissions, clears logcat, runs scenario_NAME, collects logs + failure screenshot, fails on any FATAL EXCEPTION. Built-ins: launch (stays alive 5 s), nav-all (opens every tab in TABS, screenshots each). |
scripts/ui_lib.sh |
Sourceable helpers: ui_launch, ui_grant_permissions, ui_find/ui_tap_text/ui_wait/ui_open_tab (uiautomator text lookup, real pixels, no scale factor), ui_shot, ui_diagnostics. |
scripts/install_into.sh REPO_DIR --profile X [--android-dir DIR] |
Vendor this skill into a project's .claude/skills/android-test and write .github/workflows/device-apks.yml if missing. Never commits. |
profiles/*.env, profiles/template.env |
Per project: PKG, MAIN_ACTIVITY, REPO, CI_WORKFLOW, TABS, plus custom scenario_*() functions. |
references/device-apks.yml |
Workflow template (builds assembleDebug assembleDebugAndroidTest, uploads device-apks). |
What ships with it
11 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.
- profiles/bzeed-mobility.env 310 B
- profiles/cliphist-android.env 300 B
- profiles/LimeApp.env 281 B
- profiles/mia.env 543 B
- profiles/rtp-midi.env 171 B
- profiles/template.env 372 B
- references/device-apks.yml 1.7 KB
- scripts/install_into.sh 2.3 KB runs code
- scripts/phone_ci.sh 5.9 KB runs code
- scripts/run_scenario.sh 2.7 KB runs code
- scripts/ui_lib.sh 4.6 KB runs code
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.
- 10d ago First seen · 64 lines · 104 tokens per session scan A 60d9a762d57d
android-test is a skill published in the GitHub repository sparesparrow/mcp-project-orchestrator (17 stars, last pushed 5d ago), licensed MIT. It adds 104 tokens to every session and 1,786 once invoked, about $0.0004 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 2026-10-08.
Other skills, from other repositories
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
android_ui_verification
Automated end-to-end UI testing and verification on an Android Emulator using ADB.
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.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
eas-simulator
Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Read before running any eas simulator: commands - it has the current syntax for this experimental API. Use whenever the user needs a simulator they can't run locally - 'run my app on a cloud simulator', 'use eas simulator to…
mobile-automation
Control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take screenshots, read the accessibility tree. Use when a task involves a mobile device or app, mobile UI testing, or reproducing a bug on a phone.