# Agent composability > Why artificial intelligence (AI) agent systems should be built from parts you can swap, with sources and with the objections. The site also gives a sourced definition of agent composability, the open standards layer, and a dated matrix of which agents support Agent Skills, AGENTS.md, two Model Context Protocol (MCP) extensions and Agent2Agent (A2A). - Definition: Agent composability is the ability to build an AI agent system from separate parts (models, tools, skills, sub-agents and other agents) that connect through open, shared interfaces. You can then replace one part without rebuilding the others. - Composability is a design property. Orchestration and chaining are runtime patterns: they describe how the parts run. - Matrix legend: "Listed" means that an official source names the client as supporting the standard. "Not listed" means that the source does not name the client. It makes no claim either way. - Last check: 2026-10-21. Each matrix cell has its own source URL and check date in matrix.json. - Language: English. License: CC BY 4.0 (cite agentcomposability.com and the source of each fact). ## When to use this site - To define agent composability, with sources. - To see which agents an official source lists for Agent Skills, AGENTS.md, the MCP Apps extension, the Skills over MCP extension and A2A, with the date of each check. - Do not use "Not listed" as proof that a client has no support. It makes no claim. - For the newest state, follow the source link of each cell. ## Pages - [Why composable agents](https://agentcomposability.com/index.md): the essay. Why AI agent systems built from swappable parts with open interfaces are the right design for this era, with the honest objections. - [Standards and compatibility matrix](https://agentcomposability.com/standards.md): the open standards layer (AGENTS.md, MCP, A2A, Agent Skills) and which agents support each one. - [For agents](https://agentcomposability.com/agents.md): every machine interface of this site, including the MCP server. - [Work with us](https://agentcomposability.com/work.md): the studio behind this site designs composable agent systems for US companies. - [Sources](https://agentcomposability.com/sources.md): every source, with publication and check dates. ## Data and tools - [Compatibility matrix as JSON](https://agentcomposability.com/matrix.json): one entry per client, with the status, the source URL and the check date of each cell. License: CC BY 4.0. - [MCP server](https://agentcomposability.com/mcp): read-only, Streamable HTTP, no sign-in. Tools: define_agent_composability, get_compatibility_matrix, list_standards, read_page. Server card: https://agentcomposability.com/mcp/server-card. - Markdown: send `Accept: text/markdown` to any page URL, or add .md to the path (/index.md for the home page). ## Matrix, checked 2026-10-21 - Claude Code. Agent Skills: listed; AGENTS.md: listed (source: Claude Code Docs: AGENTS.md); MCP Apps: not listed; Skills over MCP: not listed; A2A: not listed. - ChatGPT and Codex. Agent Skills: listed; AGENTS.md: listed; MCP Apps: listed; Skills over MCP: listed, partial; A2A: not listed. - Cursor. Agent Skills: listed; AGENTS.md: listed; MCP Apps: listed; Skills over MCP: not listed; A2A: not listed. - GitHub Copilot and VS Code. Agent Skills: listed; AGENTS.md: listed; MCP Apps: listed; Skills over MCP: not listed; A2A: not listed. - Gemini CLI. Agent Skills: listed; AGENTS.md: listed; MCP Apps: not listed; Skills over MCP: not listed; A2A: listed (source: Gemini CLI docs: Remote Subagents). - goose. Agent Skills: listed; AGENTS.md: listed; MCP Apps: listed; Skills over MCP: not listed; A2A: not listed. Column sources: - Agent Skills: [Agent Skills: Client Showcase](https://agentskills.io/clients) - AGENTS.md: [AGENTS.md: One AGENTS.md works across many agents](https://agents.md/) - MCP Apps: [Model Context Protocol: Extension Support Matrix](https://modelcontextprotocol.io/extensions/client-matrix) - Skills over MCP: [Model Context Protocol: Extension Support Matrix](https://modelcontextprotocol.io/extensions/client-matrix) - A2A: the documentation of each client (see matrix.json) ## Questions - What is agent composability? Agent composability is the ability to build an AI agent system from separate parts that connect through open, shared interfaces. You can replace one part without rebuilding the others. Amazon Web Services describes composability as “the act of combining modular components to create a flexible, scalable solution that can adapt to change.” - Why is composability the right design for AI agents now? Because the parts change faster than the systems. Epoch AI measured model price declines “ranging from 9x to 900x per year”, depending on the task, and most teams upgrade their model within months. A system built from parts with open interfaces takes each new model, tool or standard as a configuration change instead of a rewrite. - Does a composable agent system mean many agents? No. A composable system can have one agent. What makes it composable is that its model, tools, context and skills are separate parts behind shared interfaces. When a system does use several agents, the designs that work keep one coordinator that owns the writes: Cognition reports that what works is “where agents contribute intelligence while writes stay single-threaded.” - What does “composable agents” mean? Composable agents are agents that you build as independent units, so that you can combine, swap and reuse them. Amazon Web Services states the goal like this: “Let me build agents like I build services – modular and testable, so that they can be composed and orchestrated as needed.” In practice, an orchestrator agent can split a task and send the parts to specialized sub-agents. - Is composability the same as interoperability? No, but the two are linked. Interoperability lets independent agents discover one another, communicate and exchange work across systems. Composability is the design property that uses this: you build a system from parts that you can combine and replace. - How do MCP and A2A differ? MCP connects an agent to tools, data sources, applications and services. A2A connects agents to other agents, so that they can discover one another, delegate tasks and exchange results. The A2A project calls the two protocols complementary: “A2A connects the agents to each other; MCP connects each agent to its own tools.” - What are Agent Skills? Agent Skills are “a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows.” A skill is a folder with a SKILL.md file that holds metadata and instructions, and it can also hold scripts and other resources. At startup, an agent loads only the name and description of each skill, and it reads the full instructions when a task needs them. ## Sources - [Amazon Web Services (AWS) Prescriptive Guidance: Focus area 2: Design for composability and collaboration](https://docs.aws.amazon.com/prescriptive-guidance/latest/strategy-operationalizing-agentic-ai/focus-areas-composability-collaboration.html) - [Atlan: What Is Agent Composability?](https://atlan.com/know/ai-agent/agent-composability/) - [Anthropic: Building effective agents](https://www.anthropic.com/engineering/building-effective-agents) - [Agentic AI Foundation (AAIF): Linux Foundation Announces the Formation of the Agentic AI Foundation (AAIF)](https://aaif.io/news/linux-foundation-announces-formation-of-aaif) - [Agentic AI Foundation (AAIF): A2A joins AAIF’s open agentic stack](https://aaif.io/blog/a2a-joins-aaif) - [Agent Skills: Agent Skills Overview](https://agentskills.io/home) - [Agent Skills: Client Showcase](https://agentskills.io/clients) - [AGENTS.md: One AGENTS.md works across many agents](https://agents.md/) - [Model Context Protocol: Extension Support Matrix](https://modelcontextprotocol.io/extensions/client-matrix) - [Model Context Protocol: MCP Apps](https://modelcontextprotocol.io/extensions/apps/overview) - [Model Context Protocol: Skills](https://modelcontextprotocol.io/extensions/skills/overview) - [Model Context Protocol: The MCP Registry](https://modelcontextprotocol.io/registry/about) - [The GitHub Blog: Meet the GitHub MCP Registry: The fastest way to discover MCP Servers](https://github.blog/ai-and-ml/github-copilot/meet-the-github-mcp-registry-the-fastest-way-to-discover-mcp-servers/) - [The Linux Foundation: Linux Foundation Welcomes the AGNTCY Project to Standardize Open Multi-Agent System Infrastructure and Break Down AI Agent Silos](https://www.linuxfoundation.org/press/linux-foundation-welcomes-the-agntcy-project-to-standardize-open-multi-agent-system-infrastructure-and-break-down-ai-agent-silos) - [Model Context Protocol on GitHub: MCP Conformance Test Framework](https://github.com/modelcontextprotocol/conformance) - [A2A project on GitHub: A2A Protocol Technology Compatibility Kit (TCK)](https://github.com/a2aproject/a2a-tck) - [A2A Protocol: A2A and MCP](https://a2a-protocol.org/latest/topics/a2a-and-mcp/) - [Claude Code Docs: How Claude remembers your project: AGENTS.md](https://code.claude.com/docs/en/memory#agents-md) - [Gemini CLI documentation: Remote Subagents](https://geminicli.com/docs/core/remote-agents/) - [Claude Code Docs: Claude Code documentation](https://code.claude.com/docs/en/overview) - [ChatGPT Learn: ChatGPT and Codex documentation](https://learn.chatgpt.com/docs) - [OpenAI Developers: OpenAI developer documentation](https://developers.openai.com/) - [Cursor Docs: Cursor documentation](https://cursor.com/docs) - [GitHub Docs: GitHub Copilot documentation](https://docs.github.com/en/copilot) - [Visual Studio Code documentation: Build with AI in VS Code](https://code.visualstudio.com/docs/agents/overview) - [goose documentation: goose documentation](https://goose-docs.ai/docs/quickstart/) - [Anthropic: Equipping agents for the real world with Agent Skills](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills) - [Anthropic: Effective context engineering for AI agents](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents) - [Anthropic: Demystifying evals for AI agents](https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents) - [Anthropic: How we built our multi-agent research system](https://www.anthropic.com/engineering/multi-agent-research-system) - [Anthropic: Writing effective tools for AI agents](https://www.anthropic.com/engineering/writing-tools-for-agents) - [OpenAI Agents SDK documentation: Agent orchestration](https://openai.github.io/openai-agents-python/multi_agent/) - [OpenAI Agents SDK documentation: Handoffs](https://openai.github.io/openai-agents-python/handoffs/) - [Cloudflare: AI Gateway overview](https://developers.cloudflare.com/ai-gateway/) - [Vercel: Vercel AI Gateway: models, routing, and observability](https://vercel.com/docs/ai-gateway) - [Model Context Protocol: Authorization (specification version 2025-06-18)](https://modelcontextprotocol.io/specification/2025-06-18/basic/authorization) - [OpenTelemetry: Generative AI semantic conventions](https://opentelemetry.io/docs/specs/semconv/gen-ai/) - [Amazon Web Services (AWS): Make agents a reality with Amazon Bedrock AgentCore: now generally available](https://aws.amazon.com/blogs/machine-learning/amazon-bedrock-agentcore-is-now-generally-available/) - [iTWire, reporting Forrester's 2026 predictions: Forrester 2026 predictions for AI and tech leadership](https://itwire.com/it-industry-news/strategy/forrester-unveils-2026-predictions-for-ai-and-tech-leadership.html) - [W.Media, reporting a Gartner press release: Over 40 percent of agentic AI projects could face the axe by end of 2027: Gartner](https://w.media/over-40-percent-of-agentic-ai-projects-could-face-the-axe-by-end-of-2027-gartner/) - [Andreessen Horowitz (a16z): How 100 enterprise CIOs are building and buying gen AI in 2025](https://a16z.com/ai-enterprise-2025/) - [Menlo Ventures: 2025 mid-year LLM market update: foundation model landscape and economics](https://menlovc.com/perspective/2025-mid-year-llm-market-update/) - [goose blog (Block): MCP in the enterprise: real world adoption at Block](https://goose-docs.ai/blog/2025/04/21/mcp-in-enterprise) - [Stripe: Minions: Stripe's one-shot, end-to-end coding agents](https://stripe.dev/blog/minions-stripes-one-shot-end-to-end-coding-agents) - [Shopify Engineering: Building production-ready agentic systems: lessons from Shopify Sidekick](https://shopify.engineering/building-production-ready-agentic-systems) - [InfoQ (talk by LinkedIn engineers): Lessons learned from building LinkedIn’s first agent: Hiring Assistant](https://www.infoq.com/presentations/LinkedIn-agent-hiring-assistant/) - [The GitHub Blog: Introducing Agent HQ: any agent, any way you work](https://github.blog/news-insights/company-news/welcome-home-agents/) - [Bell System Technical Journal (transcription by Dan Luu): M. D. McIlroy, E. N. Pinson and B. A. Tague, “UNIX Time-Sharing System: Foreword”, volume 57, number 6](https://danluu.com/mcilroy-unix/) - [Communications of the ACM: D. L. Parnas, “On the criteria to be used in decomposing systems into modules”, volume 15, number 12](https://doi.org/10.1145/361598.361623) - [University of California, Irvine: Roy T. Fielding, dissertation, chapter 5: Representational State Transfer (REST)](https://ics.uci.edu/~fielding/pubs/dissertation/rest_arch_style.htm) - [martinfowler.com: James Lewis and Martin Fowler, “Microservices”](https://martinfowler.com/articles/microservices.html) - [Berkeley Artificial Intelligence Research (BAIR) blog: The shift from models to compound AI systems](https://bair.berkeley.edu/blog/2024/02/18/compound-ai-systems/) - [Epoch AI: LLM inference prices have fallen rapidly but unequally across tasks](https://epoch.ai/data-insights/llm-inference-price-trends) - [Stanford Institute for Human-Centered AI (HAI): The 2025 AI Index Report](https://hai.stanford.edu/ai-index/2025-ai-index-report) - [Cognition: Don’t build multi-agents](https://cognition.ai/blog/dont-build-multi-agents) - [Cognition: Multi-agents: what’s actually working](https://cognition.ai/blog/multi-agents-working) - [arXiv: Cemri and others, “Why do multi-agent LLM systems fail?”](https://arxiv.org/abs/2503.13657) - [Google Research: Towards a science of scaling agent systems: when and why agent systems work](https://research.google/blog/towards-a-science-of-scaling-agent-systems-when-and-why-agent-systems-work/) - [Invariant Labs: MCP security notification: tool poisoning attacks](https://invariantlabs.ai/blog/mcp-security-notification-tool-poisoning-attacks) - [Simon Willison: The lethal trifecta for AI agents: private data, untrusted content, and external communication](https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/) - [Rich Sutton: The bitter lesson](http://www.incompleteideas.net/IncIdeas/BitterLesson.html) - [Anthropic: Donating MCP to the Agentic AI Foundation](https://www.anthropic.com/news/donating-the-model-context-protocol-and-establishing-of-the-agentic-ai-foundation) - [Microsoft Learn (Azure Architecture Center): AI agent orchestration patterns](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/ai-agent-design-patterns) ## Optional - [Every page in one file](https://agentcomposability.com/llms-full.txt) - [This domain is for sale](https://agentcomposability.com/domain.md) - [Sitemap](https://agentcomposability.com/sitemap.xml)