Borrowing it
Nothing to install: this file belongs to IgorGanapolsky/openclaw-console. 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/IgorGanapolsky/openclaw-console/develop/.agents/skills/android-agent-workflow/SKILL.mdgit clone --depth 1 https://github.com/IgorGanapolsky/openclaw-consoleWrote 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/igorganapolsky/openclaw-console/android-agent-workflow)<a href="https://agentmods.dev/skills/igorganapolsky/openclaw-console/android-agent-workflow"><img src="https://agentmods.dev/badge/skills/igorganapolsky/openclaw-console/android-agent-workflow/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/igorganapolsky/openclaw-console/android-agent-workflow"><img src="https://agentmods.dev/badge/skills/igorganapolsky/openclaw-console/android-agent-workflow.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 | $0.00043 | $0.00659 |
| Opus 5.5 | $0.00017 | $0.00264 |
| Sonnet 5.5 | $0.00009 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
android-agent-workflow 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 27d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android Agent Workflow
Use this skill when an agent modifies android/, Android launcher icons, Firebase App Distribution, Compose UI, Gradle, Android CI, or Android release metadata.
Goal
Make Android agent work fast, current, and quiet. Agents should use official Android command surfaces and repo guardrails before improvising with Gradle, SDK, emulator, or Compose fixes.
Required Workflow
- Inspect the narrow Android surface touched by the task.
- Run the Android CLI preflight:
python3 scripts/check_android_cli.py- If it reports Android CLI is unavailable, keep working with the repo Gradle/SDK commands and state that fallback explicitly.
- Prefer official Android CLI commands when available:
android sdkfor SDK/component setup.android emulatorfor virtual device creation and lifecycle.android runfor deploy/run loops.android docsfor current Android, Firebase, Google, and Kotlin guidance.android skillsfor official Android task instructions.
- Keep summaries concise: report the changed files, the failing/passing command, and the next concrete fix. Do not paste full Gradle logs unless the exact failing lines are needed.
- Preserve iOS parity before changing Android UI or branding. Android should match the iOS/TestFlight visual source of truth unless the task explicitly says otherwise.
Mandatory Checks
Run the narrowest applicable checks before reporting completion:
python3 scripts/check_android_cli.py
python3 scripts/sync_app_icons.py --check
./scripts/check-brand-parity.sh
cd android && ./gradlew :app:compileDebugKotlin :app:testDebugUnitTest :app:lintDebug --no-daemon
For release, Firebase, or Play changes, also run:
python3 scripts/validate_release_contract.py --platform android
OpenClaw Android Rules
- Package remains
com.openclaw.console. - Use Kotlin + Jetpack Compose + MVVM/repository patterns already present in the repo.
- Keep Composables thin; move logic into ViewModels or pure helpers.
- Use
collectAsStateWithLifecycle(), not rawcollectAsState(), for Flow-backed UI. - Do not use
AndroidViewModelunless a line-level// allow-android-viewmodeljustification exists. - Do not add launcher icon assets by hand. Regenerate from the canonical iOS marketing icon with
scripts/sync_app_icons.py. - Do not add new Android permissions unless the feature requires them and the risk is documented in the PR.
- Keep dangerous action approvals behind biometric verification.
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.
- 27d ago First seen · 66 lines · 43 tokens per session scan A faecf4aa7713
android-agent-workflow is a skill published in the GitHub repository IgorGanapolsky/openclaw-console (6 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 659 once invoked, about $0.0002 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 2026-10-02.
Other skills, from other repositories
flutter-cicd
Set up CI/CD pipelines for Flutter apps. Use when configuring automated testing, build, or deployment workflows with GitHub Actions or Fastlane.
compose-project
Owns project and build-level work for Compose and Compose Multiplatform apps: bootstrapping a new project, adopting the kit in an existing project, adding or extracting a module, convention plugins in build-logic, the version catalog, and CI plus agent hooks. Use when starting a Compose Multiplatform app, adding a…
enforcing-stability-in-ci
Use this skill to set up a CI gate that fails the build when Compose stability silently regresses, using the skydoves/compose-stability-analyzer Gradle plugin (primary) or the j-roskopf/ComposeGuard plugin (alternative for non-Android multiplatform). Covers applying com.github.skydoves.compose.stability.analyzer…
architecture-builder
Use to produce the technical architecture doc and engineering principles for a mobile app. Used primarily by the CTO agent. Triggers on "design the architecture", "pick the stack", or as part of /app-plan.
ci-cd-patterns
CI/CD patterns for mobile - GitHub Actions workflows for Android/iOS, Fastlane integration, code signing, artifact publishing, and automated release.
android-cli
Orchestrates Android development tasks including project creation, deployment, SDK management, and environment diagnostics using the android command-line tool.