Borrowing it
Nothing to install: this file belongs to JuanCF/scrcpy-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JuanCF/scrcpy-mcp/main/.opencode/skills/scrcpy-gotchas/SKILL.mdgit clone --depth 1 https://github.com/JuanCF/scrcpy-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/juancf/scrcpy-mcp/scrcpy-gotchas)<a href="https://agentmods.dev/skills/juancf/scrcpy-mcp/scrcpy-gotchas"><img src="https://agentmods.dev/badge/skills/juancf/scrcpy-mcp/scrcpy-gotchas/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/juancf/scrcpy-mcp/scrcpy-gotchas"><img src="https://agentmods.dev/badge/skills/juancf/scrcpy-mcp/scrcpy-gotchas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.05676 |
| Opus 5 | $0.00024 | $0.02838 |
| Sonnet 5 | $0.00010 | $0.01135 |
| Haiku 4.5 | $0.00005 | $0.00568 |
Grade A, and why
scrcpy-gotchas 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 9d 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scrcpy-mcp Gotchas
Coordinate systems: always use native coordinates
scrcpy_tap, scrcpy_swipe, scrcpy_long_press, and scrcpy_scroll take device-native coordinates — the same space that scrcpy_ui_dump / scrcpy_ui_find_element report in their bounds and tapX/tapY, and the same space adb shell input tap uses. So the reliable workflow needs no scaling math:
// Find the element (returns native tapX/tapY), then tap them straight through
const el = scrcpy_ui_find_element({ text: "<label>" }) // → { tapX, tapY }
scrcpy_tap({ x: el.tapX, y: el.tapY })
The input tools scale native → video-frame coordinates internally before sending the touch to the scrcpy server, so you never compute a scale factor yourself.
Don't tap screenshot pixels
scrcpy_screenshot returns a downscaled image (e.g. 576×1024 at maxSize=1024), not the native frame. Tapping a pixel coordinate read off the screenshot lands in the wrong place. Always source coordinates from ui_dump / ui_find_element (native), never from the screenshot.
Why internal scaling is required: the scrcpy server's touch protocol is not resolution-independent — the touch message's screen size must exactly match the encoder's video-frame size, or the server silently drops the event. The tools handle this conversion; you just supply native coords.
ui_find_element matching rules
The four search criteria have different matching behaviors:
| Criterion | Match type | Case sensitivity |
|---|---|---|
text |
Partial substring (includes) |
Case-insensitive |
contentDesc |
Partial substring (includes) |
Case-insensitive |
resourceId |
Exact equality (===) |
Case-sensitive |
className |
Exact equality (===) |
Case-sensitive |
All criteria are combined with AND logic — an element must satisfy every supplied criterion.
// text: case-insensitive substring — "bater" matches "Batería"
scrcpy_ui_find_element({ text: "bater" }) // ✓
// resourceId: exact match only — must be full string
scrcpy_ui_find_element({ resourceId: "android:id/title" }) // must match exactly
// className: full qualified name — "Button" won't match "android.widget.Button"
scrcpy_ui_find_element({ className: "android.widget.Button" }) // full name required
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.
- 9d ago First seen · 375 lines · 48 tokens per session scan A be75ce374bb8
scrcpy-gotchas is a skill published in the GitHub repository JuanCF/scrcpy-mcp (91 stars, last pushed 18d ago), licensed MIT. It adds 48 tokens to every session and 5,676 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 2026-08-30.
Other skills, from other repositories
crash-triage
Using logcat to surface the real "Caused by:" root cause hidden behind a generic UI error, plus app lifecycle tools for reproducing failures. Use when an app crashes, shows a generic error dialog, or a task needs to find why a native call failed.
scrcpy-mcp
Professional Android automation agent for device interaction, UI testing, and app management. Use for: (1) interacting with Android apps, (2) filling inputs, (3) structural UI inspection via XML/axtree, (4) complex multi-step mobile tasks. Prefer XML/axtree over screenshots — images are expensive tokens.
flog-inspect
Use when a user asks an agent to inspect Flutter app logs, network traffic, SSE/WebSocket streams, current page state, screenshots, or debugging context through flog instead of copying from the TUI.
rn-agent-observer
Runtime observability for React Native/Expo apps on Android. Use when debugging RN UI, performance (FPS, JS blocking), network, re-renders, or runtime errors on a running app — understand the current screen and UI findings, capture screenshots, UI trees, ref snapshots, per-request network, CDP console/heap/CPU…
rn-expo
The RN/Expo dev-build recipe for adb-mcp — adbreverse before launching (or the dev client silently runs its embedded bundle), appstate to confirm it is on Metro, on the RIGHT Metro, and not serving stale JavaScript after a git checkout, then reloadapp. Use whenever driving a React Native or Expo dev build, or when…
driving
The core observe→locate→act→re-observe loop for driving an Android UI with adb-mcp — true-pixel coordinates, and gotchas like overlays eating taps, keyboards covering buttons, and settle delays. Use whenever tapping, swiping, typing, or otherwise interacting with an Android screen.