By asherepenko
Expert Android engineering agents, interactive pipelines, and skill for modern Kotlin/Compose/Gradle development
Run pattern detection against the codebase to analyze consistency and recommend approaches
Execute multi-agent Android development pipelines with automated orchestration, validation, and handoff artifacts
Display current pipeline status, completed stages, artifacts, and recovery options
Expert Android architect specializing in scalable app architecture, modular design, MVVM/MVI patterns, and production-grade system design. Writes architecture-blueprint.md handoff artifacts defining module structure, patterns, and constraints for downstream implementation agents. Use when defining architecture, designing module structures, or validating architectural decisions. <example>Use this agent when /aet-pipeline starts a feature-build to design module structure and ADRs, or when reviewing existing architecture for circular dependencies and pattern inconsistencies.</example>
Expert Android developer implementing production-grade Kotlin/Android features using MVVM/MVI, Room, Hilt, and reactive patterns. Reads architecture-blueprint.md and module-setup.md handoffs to implement data layer and ViewModels. Writes implementation-report.md handoffs documenting completed implementations, interfaces for testing, and build requirements. Use when implementing repositories, ViewModels, or data layer logic. <example>Use this agent after android-architect writes the blueprint to implement FeedViewModel, OfflineFirstFeedRepository, Room entities, and API service for a social feed feature.</example>
Expert Android testing specialist focused on test doubles (no mocking), Flow testing with Turbine, and comprehensive test coverage strategies. Reads architecture-blueprint.md, implementation-report.md, and ui-report.md handoffs to create test doubles, unit tests, and Compose UI tests. Writes test-report.md handoffs documenting test failures, coverage gaps, and testability improvements needed. Use when creating test infrastructure or validating implementations. <example>Use this agent after compose-expert completes to create TestFeedRepository, write FeedViewModel unit tests with Turbine, and write Compose UI tests targeting 80%+ coverage.</example>
Expert Jetpack Compose specialist focused on Material 3, adaptive UI, and performance optimization. Reads architecture-blueprint.md and implementation-report.md handoffs to implement Compose UI consuming ViewModels and state types. Writes ui-report.md handoffs documenting implemented composables, semantic properties for testing, and state variations. Use when implementing Jetpack Compose UI, Material 3 components, or adaptive layouts. <example>Use this agent after android-developer completes the ViewModel layer to build FeedScreen, PostCard, and EmptyFeedState composables with Material 3 tokens and phone/tablet adaptive layouts.</example>
Expert Gradle build engineer specializing in convention plugins, version catalogs, and build performance optimization. Reads architecture-blueprint.md handoffs to implement build configuration matching module structure and dependency graph. Writes module-setup.md handoffs documenting convention plugins applied, version catalog entries, and module templates created. Use when configuring build system, creating modules, or managing dependencies. <example>Use this agent in parallel with android-developer after android-architect defines the module structure, to create feature:feed:api and feature:feed:impl modules with convention plugins and version catalog entries.</example>
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Claude Code plugins for multi-agent engineering workflows.
A personal Claude Code plugin marketplace by Andrew Sherepenko.
| Plugin | Description |
|---|---|
android-expert-toolkit | Expert Android engineering agents and skill for modern Kotlin/Compose/Gradle development |
avengers-council | 9-member engineering advisory board that reviews planning decisions, code changes, and plan files through structured debate |
Inside Claude Code, add this repo as a marketplace:
/plugin marketplace add asherepenko/ashforge
Then install the plugins you want:
/plugin install android-expert-toolkit@ashforge
/plugin install avengers-council@ashforge
Enable a plugin (or restart Claude Code) to activate it:
/plugin enable android-expert-toolkit
/plugin enable avengers-council
/plugin marketplace list # show registered marketplaces
/plugin marketplace update ashforge # pull latest plugin definitions
/plugin marketplace remove ashforge # unregister this marketplace
Plugins are cached under ~/.claude/plugins/cache/. Reference plugin assets from hooks/configs via ${CLAUDE_PLUGIN_ROOT} rather than relative paths.
.claude-plugin/
marketplace.json # marketplace manifest (name, owner, plugins[])
plugins/
android-expert-toolkit/
avengers-council/
Each plugin under plugins/ is a self-contained Claude Code plugin with its own .claude-plugin/plugin.json, agents, skills, commands, and hooks.
See individual plugins for license details.
npx claudepluginhub asherepenko/ashforge --plugin android-expert-toolkitExtensible engineering advisory board (8 core + optional domain specialists) that reviews planning decisions, code changes, and plan files through structured multi-round debate with severity-weighted consensus verdicts and domain scoring. Use for comprehensive peer review before merging, shipping, or implementing architectural decisions
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams