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 skydoves/android-testing-skills --skill finding-nodes-by-tag-text-contentgit clone --depth 1 https://github.com/skydoves/android-testing-skillsWrote 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/skydoves/android-testing-skills/finding-nodes-by-tag-text-content)<a href="https://agentmods.dev/skills/skydoves/android-testing-skills/finding-nodes-by-tag-text-content"><img src="https://agentmods.dev/badge/skills/skydoves/android-testing-skills/finding-nodes-by-tag-text-content/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/skydoves/android-testing-skills/finding-nodes-by-tag-text-content"><img src="https://agentmods.dev/badge/skills/skydoves/android-testing-skills/finding-nodes-by-tag-text-content.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 | $0.00185 | $0.03241 |
| Opus 5 | $0.00093 | $0.01621 |
| Sonnet 5 | $0.00037 | $0.00648 |
| Haiku 4.5 | $0.00018 | $0.00324 |
Grade A, and why
finding-nodes-by-tag-text-content 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finding Nodes by Tag, Text, or Content Description — Tag From Production, Find by Tag From Tests
Every Compose UI test starts by locating a semantics node. This skill picks the right finder, reasons about the count contract, and decides when to flip useUnmergedTree. Use it whenever the developer is staring at a "Reason: Expected exactly '1' node but could not find any node that satisfies …" error.
When to use this skill
- The developer reports "no node matched" / "multiple nodes matched" / "tag not found" / "ambiguous match" from
SemanticsNodeInteraction. - The developer asks how to locate a
Button,Text,Icon,IconButton,Switch, or any other composable inside a test. - The developer mentions
onNodeWithTag,onNodeWithText,onNodeWithContentDescription,onAllNodesWith*, oronRoot. - A test passes locally but is brittle to copy edits or i18n rotation of the UI strings.
- The developer asks about
useUnmergedTree, the merged tree, or "why does my inner Text not exist".
When NOT to use this skill
- The right node is found but assertions fail — see
../../assertions/asserting-node-state-and-text/SKILL.md(state) or../../assertions/asserting-bounds-and-dimensions/SKILL.md(geometry). - The finder returns one node but custom predicates are needed — see
../composing-semantics-matchers/SKILL.md. - The right node exists but only as a child/sibling/descendant — see
../traversing-the-semantics-tree/SKILL.md. - The semantics tree itself needs inspection — see
../../debug/printing-the-semantics-tree/SKILL.md.
Prerequisites
androidx.compose.ui:ui-test-junit4(or v2) wired up. See../../setup/configuring-test-dependencies/SKILL.mdifcreateComposeRuleis unresolved.- A
ComposeTestRuleorComposeUiTestis in scope. See../../setup/choosing-test-rule-vs-runtest/SKILL.md. - The composable under test calls
setContent { … }before the finder runs. Finders are lazy and re-evaluate on every operation.
Workflow
- 1. Default to
onNodeWithTag(SomeTag). Add aModifier.testTag(SomeTag)in the production source under aconst val SomeTag = "Some". Tests find by tag, not by text. Skydoves hot take #1: inandroidx/material3itself,onNodeWithTagoutnumbersonNodeWithTextroughly 4:1 (1825 vs 424) andonNodeWithContentDescription40:1 (1825 vs 46). Text finders churn with copy edits and break on locale rotation.
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 · 223 lines · 185 tokens per session scan A 8d7ac2337105
finding-nodes-by-tag-text-content is a skill published in the GitHub repository skydoves/android-testing-skills (319 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 185 tokens to every session and 3,241 once invoked, about $0.0009 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
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.
agent-device
Automates Apple-platform apps (iOS, tvOS, macOS), Android devices, and Amazon Vega OS TV apps in Vega Virtual Devices. Use when navigating apps, taking snapshots/screenshots where supported, driving TV remotes, tapping, typing, scrolling, extracting UI info, collecting evidence, or planning agent-device CLI commands.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
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
EAS service (paid). 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…