claude-agent-sdk plugins

by Alex Newman

Memory compression system for Claude Code - persist context across sessions

by Alex Newman

Memory compression system for Claude Code - persist context across sessions

by Nowledge Labs

Personal knowledge graph for Proma — saves Proma conversations, writes startup context into CLAUDE.md, and keeps nmem tools available during work

by Trustabl

Self-audit AI agent, tool, and MCP-server code for security and reliability misconfigurations with Trustabl, the agent reliability scanner for the OpenAI Agents SDK, Claude Agent SDK, Google ADK, and MCP. Ships two skills: trustabl-scan scans your agent code with Trustabl (via a bundled MCP server) right after you write or change it, before you commit — optionally matching your declared dependencies against the OSV database for known CVEs — and trustabl-enrich applies the scan findings directly to your source files as targeted code edits.

by Trustabl

Self-audit AI agent, tool, and MCP-server code for security and reliability misconfigurations with Trustabl, the agent reliability scanner for the OpenAI Agents SDK, Claude Agent SDK, Google ADK, and MCP. Ships two skills: trustabl-scan scans your agent code with Trustabl (via a bundled MCP server) right after you write or change it, before you commit — optionally matching your declared dependencies against the OSV database for known CVEs — and trustabl-enrich applies the scan findings directly to your source files as targeted code edits.

by Matt Corbett

AI agent-engineering team — agents (agentic-systems-architect, agent-implementation-engineer) for BUILDING production agentic systems: hard TRIAGE (most tasks win as a fixed workflow or a single LLM call, not an agent), single-vs-multi-agent topology, framework selection (LangGraph / OpenAI Agents SDK / CrewAI / AutoGen / Claude Agent SDK), tool & function design, context/memory/state management, planning & reflection loops, human-in-the-loop, guardrails, cost/latency budgets, tracing/observability, and agent EVALS (trajectory, tool-use, task-completion). skills, a knowledge bank, and templates. Engineering judgment, not a demo; the framework/model/API landscape is volatile — every version carries a retrieval date + [verify-at-use]. Distinct from ai-rag-engineering (retrieval), prompt-engineering (single-call prompt craft), llm-evaluation-engineering (general eval harnesses), and claude-app-engineering (Claude product apps). Needs ravenclaude-core.

by Matt Corbett

Claude app-engineering specialist team — agents (claude-solution-architect, prompt-and-context-engineer, mcp-and-server-tools-engineer, agent-sdk-engineer, eval-engineer, claude-app-ops-engineer) for building production applications on the Claude API, the Claude Agent SDK, and MCP. Covers the build-surface decision (Messages API / Agent SDK / Managed Agents), model right-sizing (Opus 4.8 / Sonnet 4.6 / Haiku 4.5, 1M context), prompt caching, tool use + structured output, MCP server authoring + Anthropic-hosted server tools (computer use, code execution, Files API, memory), evals (golden sets, LLM-as-judge), and FinOps + reliability (batch, model routing, backoff, observability). dated-and-cited knowledge bank, templates, an advisory hook (house opinions). Seams: prompt-as-artifact, security, and cross-domain architecture escalate to ravenclaude-core. Requires ravenclaude-core@>=0.7.0.

by duyet

A single skill that builds AI-agent applications end-to-end — interview or detect the stack, then scaffold UI/UX, agent APIs, tools, tracking and gateways across 13+ agent frameworks including LangGraph, the Vercel AI SDK, the OpenAI and Claude Agent SDKs, Google ADK, Mastra, Pydantic AI, and more — always verifying against live docs before writing code.