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 gaelic-ghost/socket --skill choose-project-shapegit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/choose-project-shape)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/choose-project-shape"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/choose-project-shape/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/gaelic-ghost/socket/choose-project-shape"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/choose-project-shape.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 | $0.00077 | $0.01321 |
| Opus 5.5 | $0.00031 | $0.00528 |
| Sonnet 5.5 | $0.00015 | $0.00264 |
| Haiku 4.5 | $0.00008 | $0.00132 |
Grade A, and why
choose-project-shape 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 1mo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Choose Android Project Shape
Purpose
Pick the smallest correct Android-owned shape before code changes begin.
The practical decision is whether the work belongs in an Android app, Android library, multi-module Android project, Kotlin-first implementation, Java-only maintenance, UI workflow, Gradle/AGP maintenance pass, test/lint pass, release-readiness pass, or a handoff to server-side JVM guidance.
Source Check
Use repo-local files, checked-out dependency sources, and Dash.app docsets opportunistically when they cover the exact Android-adjacent surface, especially Gradle, Java, or command-line reference material. Treat current official Android and Google documentation as authoritative for Android-specific behavior, APIs, release policy, permissions, privacy, Play delivery, and version-sensitive guidance:
- Android Developers documentation
- Android build and Android Gradle Plugin documentation
- Jetpack Compose documentation
- Gradle User Manual
- Kotlin documentation
- Java documentation
Translate documentation into the concrete module, command, or implementation decision it changes.
Classification Workflow
- Inspect the repository shape:
settings.gradle,settings.gradle.kts,build.gradle,build.gradle.ktsgradle/libs.versions.toml,gradle.properties,gradlewAndroidManifest.xmlsrc/main/java,src/main/kotlin,src/main/ressrc/test,src/androidTest- Compose markers such as
androidx.compose,@Composable, or Compose compiler configuration - XML view markers such as
layout/, AppCompat, fragments, view binding, or data binding - CI, signing, lint, release, and Play delivery files
- Identify the user-visible job:
- Android app
- Android library
- multi-module Android project
- Kotlin-first app or library
- Java-only app or library
- mixed Kotlin and Java app
- Compose UI implementation
- XML/AppCompat UI implementation
- AndroidX library maintenance
- Gradle/AGP, dependency, test, lint, signing, or release work
- Route non-Android JVM work away from this plugin:
- backend services
- shared non-Android JVM libraries
- server frameworks
- Maven or SBT backend workflows
- Choose language posture:
- Preserve existing repository language choices.
- Prefer Kotlin for new Android work when no repo default conflicts.
- Preserve Java-only Android codebases unless the user asks for migration.
- Ask before large Kotlin/Java migrations.
- Explain interop when APIs cross Kotlin and Java.
- Choose validation:
- Gradle wrapper commands from the affected module first.
test,lint,assemble,bundle, or connected-device tasks only when they match the change.- Emulator/device validation as a handoff to the Android testing plugin, not duplicated here.
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.
- 1mo ago First seen · 115 lines · 77 tokens per session scan A 7ebea6a64dad
choose-project-shape is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,321 once invoked, about $0.0003 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
app-store-optimization
Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.
flutter-screenshots
Automate App Store & Google Play screenshot generation for Flutter apps. Scans routing and screens, scores high-value marketing screens, generates self-contained mock harness, runs native simulator captures (iPhone 6.9", iPad 13", Android Phone/Tablet), strips alpha channels, and validates exact store resolutions.
flutter-ui
Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.
flutter-dart-code-review
Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.