By plaited
UI patterns for templates, behavioral elements, and styling with Plaited. Covers form controls, cross-island communication, and component testing via stories.
npx claudepluginhub joshuarweaver/cascade-code-general-misc-3 --plugin plaited-plaitedTransport-agnostic MCP integration patterns. Explains session API, transport choices, and how to use the framework's shared MCP library surface.
Scaffold protected remote MCP skills for generic tool execution using repo-native auth config, env or Varlock-resolved secrets, and optional external refresh-material storage.
Generate MCP-backed skills from remote MCP servers (Streamable HTTP). Covers discovery, wrapper generation, skill scaffolding, and authentication seams for HTTP endpoints.
TSDoc standards for TypeScript/JavaScript code. Automatically invoked when writing, reviewing, or editing any TSDoc comments, code documentation, or API documentation. (project)
Common code pattern genome for agents. Reference implementations of pure utility functions showing preferred coding style, testing patterns, and TypeScript conventions. Use when writing utility functions, implementing deep equality, async helpers, or similar standalone patterns.
MSS/module architectural review checklist delegating deterministic analysis and flow evidence to plaited-context.
SQLite-backed Plaited codebase search and context assembly. Use before implementing, reviewing, or updating docs to gather source-grounded files, symbols, patterns, tests, skills, and prior findings.
Guide for writing eval-compatible adapter scripts that emit TrialResult artifacts. Use when integrating external agents or scripts into the Plaited eval pipeline.
Trial runner and strategy comparison CLI for the Plaited framework. Use when running evals against agent adapters, computing pass@k metrics, or comparing two eval runs.
Plaited runtime doctrine for behavioral coordination, MSS/module boundaries, projection semantics, and generated module actor rules. Use with plaited-context for source-grounded implementation and review.
Build and test Plaited's server-driven UI stack. Use when working on `src/ui`, controller islands, controller protocol schemas, SSR templates, CSS helpers, dynamic controller modules, or UI test fixtures.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Search the Agent Client Protocol documentation. Use when implementing ACP clients or servers, understanding the protocol, or checking transport details.
Search the AgentSkills specification. Use when creating, validating, structuring skills, or understanding the SKILL.md format.
Search the Bun documentation. Use when answering questions about Bun APIs, runtime features, bundler, test runner, or package manager configuration.
Search the Cline documentation and read Cline docs pages through the Cline MCP endpoint. Use when answering questions about Cline features, configuration, MCP integration, or CLI/extension behavior.
Search the Model Context Protocol specification. Use when implementing MCP clients or servers, understanding the protocol, or checking transport details.
Search the Varlock documentation for AI-safe environment configuration. Use when working with .env.schema files, secret providers, leak detection, or understanding how Varlock integrates with node provisioning.
Type-aware TypeScript/JavaScript codebase analysis. Provides hover info, references, definitions, symbols, exports, workspace symbol search, and workspace audit operations via a single unified CLI.
Use You.com Search, conditional livecrawl/contents, and narrow Research API follow-ups through the official client first, with direct HTTP only as fallback. - MANDATORY TRIGGERS: You.com, youdotcom, YDC, YDC API, You.com API, livecrawl, contents, research lite, research deep, cited web research, direct API integration - Use when: web-grounded search or extraction is needed, or when a repo script should call You.com programmatically
Sovereign agent nodes first. Framework details second.
Plaited is a framework for building local-first sovereign agents.
The current direction is:
src/agentskills/ and workspace installs under .agents/skillsPlaited's shipped runtime is centered on:
The core owns:
Higher-level orchestration belongs in modules.
src/ — shipped framework codeskills/ — published and reference skillsdocs/ — wiki-first documentationdev-research/ — retired research tombstone and historical artifactsNotable skill surfaces:
Requirements:
>= v1.2.9gitUseful commands:
# Typecheck
bun --bun tsc --noEmit
# Full test suite
bun test
# Bootstrap a local deployment scaffold
bun run ./bin/plaited.ts bootstrap '{"targetDir":".","name":"my-agent"}'
# CLI schema discovery
bun run ./bin/plaited.ts --schema
Skills are the portable agent-facing extension surface.
skills/.agents/skills/Repo planning is prompt-driven and maintainer-reviewed. Agent-authored work should start from
fresh origin/dev worktrees unless the task says otherwise.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Automates browser interactions for web testing, form filling, screenshots, and data extraction
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.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.