By aRustyDev
Build, test, and deploy cross-browser extensions for Chrome, Firefox, Safari, and Edge with support for Manifest V3, WebAssembly integration, and store submission. Includes scaffolding, validation, debugging, and security auditing.
Add a WebAssembly module to a browser extension project with Rust scaffolding, wasm-pack build configuration, and cross-browser loading code.
Scaffold a new cross-browser extension using WXT framework
Validate browser extension for manifest issues, CSP violations, and cross-browser compatibility
Design browser extension architecture including component structure, WASM decisions, cross-browser strategy, and manifest configuration
Debug cross-browser extension issues, analyze errors, and suggest compatibility fixes
Pre-review browser extensions for store compliance before submission to Chrome Web Store, Firefox Add-ons, and Safari App Store
Evaluate WebAssembly suitability for browser extension features and architect module boundaries. Provides data-driven recommendations with performance analysis.
Comprehensive security guide for browser extensions covering CSP, permissions, secure messaging, sandboxing, and threat mitigation
Complete guides for submitting browser extensions to Chrome Web Store, Firefox Add-ons, Safari App Store, and Edge Add-ons
Complete reference for Manifest V3 browser extension development with cross-browser compatibility and migration guidance
Reference for browser extension store APIs for querying extension info, checking compatibility, and tracking submission status
Decision framework for WebAssembly usage in browser extensions including loading patterns, architecture, and performance considerations
Browser automation using accessibility tree for fast, deterministic testing
Chromium-focused browser automation fallback
WASM build integration for browser extensions using wasm-pack and wasm-bindgen
Query browser extension store APIs for version info, compatibility checks, and submission status
Modifies files
Hook triggers on file write and edit operations
Requires secrets
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Needs API keys or credentials to function
Needs API keys or credentials to function
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Reusable Claude Code components: skills, agents, commands, rules, plugins, MCP server configurations, and a universal component management system.
just init # Install deps, init knowledge graph, pull embedding model
just agents --help # CLI tool for component management
content/ Component source of truth
├── skills/ SKILL.md files (130+)
├── agents/ Agent definitions (markdown + frontmatter)
├── commands/ Slash commands (markdown + frontmatter)
├── rules/ Instruction rules (markdown)
├── plugins/ Plugin bundles (.claude-plugin/plugin.json)
├── hooks/ Hook configurations
├── output-styles/ Output formatting templates
└── reference/ Reference documentation
packages/cli/ TypeScript tooling (Bun + Citty)
├── src/
│ ├── bin/agents.ts CLI entrypoint
│ ├── commands/ Command modules (verb-first + legacy noun-first)
│ ├── lib/ Library modules
│ │ ├── component/ Universal component model (7 providers)
│ │ ├── skill-*.ts Skill lifecycle (add/find/list/outdated/update/remove/info/init)
│ │ └── ... Hash, lockfile, output, runtime, schemas, etc.
│ ├── client/ Graph viewer frontend
│ ├── server/ Graph viewer backend
│ └── sql/ SQL query files
└── test/ bun:test suites (900+ tests)
settings/mcp/ MCP server configurations
docs/src/adr/ Architecture Decision Records
just agents skill add owner/repo@skill # Install a skill
just agents skill find "kubernetes" # Search registries
just agents skill list # List installed skills
just agents skill list --agent claude-code # Filter by agent
just agents skill outdated # Check for updates
just agents skill update # Update outdated skills
just agents skill remove skill-name # Remove a skill
just agents skill info skill-name # Detailed metadata
just agents skill init my-skill # Scaffold new skill
just agents mcp search "postgres" # Search Smithery registry
just agents mcp add smithery://ns/server --client cursor # Add to client config
just agents mcp list --client claude-desktop # List in client config
just agents mcp remove server-name --client cursor # Remove from client
just agents mcp info ns/server-name # Server details
just agents mcp publish --name ns/server --url https://...# Publish to Smithery
just agents component search "kubernetes" # Search all types
just agents component list # List all installed
just agents component list --type agent # Filter by type
just agents plugin check <name> # Validate a plugin
just agents skill validate <name> # Validate skill frontmatter
just kg-search "query" # Semantic search (knowledge graph)
All entity types flow through a universal ComponentProvider interface:
| Provider | ID | Entity Types | Backend |
|---|---|---|---|
| LocalProvider | local | skill | Filesystem (wraps skill-* modules) |
| LocalAgentProvider | local-agent | agent | content/agents/**/*.md |
| LocalPluginProvider | local-plugin | plugin | content/plugins/**/.claude-plugin/ |
| LocalRuleProvider | local-rule | rule | content/rules/**/*.md |
| LocalCommandProvider | local-command | command | content/commands/**/*.md |
| LocalOutputStyleProvider | local-output-style | output-style | content/output-styles/**/*.md |
| SmitheryProvider | smithery | mcp-server | registry.smithery.ai API |
The ComponentManager aggregates search across all providers, deduplicates results, and handles pagination.
MCP servers can be installed to 19 AI client config files:
| Client | Method | Format |
|---|---|---|
| Claude Desktop | file | JSON |
| Claude Code | command | claude mcp add |
| Cursor | file | JSON |
| Windsurf | file | JSON |
| VS Code | command | code --add-mcp |
| Cline, Roo Code, Continue, Zed, Goose, OpenCode, ... | file | JSON/YAML/JSONC |
Curated plugins at .claude-plugin/marketplace.json:
| Plugin | Description |
|---|---|
homebrew-dev | Homebrew formula development |
browser-extension-dev | Cross-browser extension development |
blog-workflow | Technical blog post creation |
job-hunting | Job hunting toolkit |
swiftui-dev | SwiftUI development |
design-to-code | Design-to-code conversion |
npx claudepluginhub arustydev/agents --plugin browser-extension-devHomebrew formula development toolkit — research packages, generate formulas from JSON schema, validate with brew audit/style, and batch-create formulas for a custom tap.
Comprehensive SwiftUI development support for UI testing, integration testing, data-driven apps, and interactive development practices
Comprehensive job hunting toolkit — analyze job descriptions, extract resume bullets from career history, identify skill gaps, tailor applications, and research employers with salary data.
Bridge design tools and code generation, enabling seamless translation of design files into production-ready UI code across multiple frameworks.
Multi-phase blog content creation with personas, templates, and iterative review. Supports tutorials, deep dives, research summaries, and development journals.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.