The Cross-Vendor Landscape: Your Skills Are Portable
You've spent this entire chapter learning Claude Code. Here's the secret: you weren't just learning one tool.
Every concept you mastered -- CLAUDE.md project instructions, Skills, MCP servers, hooks, subagents, agent teams -- is part of an emerging industry standard. OpenAI's Codex CLI has its own version of each. Google's Gemini CLI has its own version. And in December 2025, several of these vendors created the Agentic AI Foundation (AAIF) under the Linux Foundation, donating key projects to seed open, vendor-neutral standards for agentic AI.
MIT Technology Review named "Generative Coding" one of its 10 Breakthrough Technologies of 2026. AI now writes approximately 30% of Microsoft's code and more than 25% of Google's. The tools you learned in this chapter are not a niche experiment. They are the new baseline for how software gets built.
The Market in March 2026
The agentic coding market has consolidated into two leaders and several strong contenders.
Tier 1: The Two Leaders
Anthropic (Claude Code) Claude Code's run-rate revenue has surpassed $2.5B, more than doubling since January 2026 (Constellation Research). Anthropic's overall ARR has reached $19B (Yahoo Finance). Claude Code accounts for roughly 4% of all public GitHub commits (SemiAnalysis). Claude Opus 4.5 holds the top spot on SWE-bench Verified at 80.9%. The source code is available on GitHub (github.com/anthropics/claude-code) under Anthropic's commercial license (source-available, not OSI-approved open source). Philosophy: developer-in-the-loop, local terminal execution, accuracy-first.
OpenAI (Codex)
Codex CLI is open source, built in Rust, installable via npm i -g @openai/codex (GitHub). GPT-5.4 mini is now available in Codex alongside GPT-5.3-Codex, using 30% of the compute budget of the full model (Codex Changelog). The Codex app is now available on Windows in addition to macOS. Rate limits have doubled across all plans. Codex supports cloud sandbox execution (default for delegated tasks) and also provides local CLI modes. Philosophy: parallel, asynchronous, fire-and-forget delegation.
Tier 2: Strong Contenders
| Tool | Key Stat | Positioning |
|---|---|---|
| Cursor | >$2B ARR, in talks at ~$50B valuation (TechCrunch, Bloomberg) | Doubled revenue in three months. Enterprise now ~60% of revenue. IDE-first experience. |
| GitHub Copilot | 68% developer usage, ~$400M revenue 2025 (a16z) | Custom agents, sub-agents, terminal agent, and JetBrains agentic capabilities now GA (GitHub Blog). Massive distribution via GitHub ecosystem. |
| Google Gemini CLI | Open source (Apache 2.0), free tier (1,000 req/day), 1M token context | Plan Mode on by default, skills on by default, gVisor/LXC sandboxing, HTTP A2A remote agents (Gemini CLI docs). Rapid feature evolution. |
Tier 3: Emerging and Open-Source Players
| Tool | Key Stat | Positioning |
|---|---|---|
| Devin/Windsurf | Cognition acquired Windsurf for ~$250M, inheriting $82M ARR and 350+ enterprise customers (TechCrunch) | Fully autonomous agent (Devin) plus IDE (Windsurf) under one roof. Combined enterprise ARR up 30%+ post-acquisition. |
| Amazon Q Developer | Gartner Magic Quadrant Leader, deep integration across 200+ AWS services | Strong enterprise play with free tier. Notable adoption at BT Group and National Australia Bank. |
| Cline | 5M+ installs across VS Code/JetBrains/Cursor, 58K+ GitHub stars (cline.bot) | Open-source autonomous coding agent running locally in your IDE. Native subagents (v3.58), CLI 2.0. Fork Roo Code also growing. Not mentioned in any vendor's marketing because it competes with everyone. |
| OpenCode | 120K+ GitHub stars, MIT licensed (github.com/opencode-ai/opencode) | Go-based CLI agent, works with 75+ models (Claude, GPT, Gemini, local). Privacy-first, provider-agnostic. Desktop app and VS Code extension also available. Often called "the open-source Claude Code." |
The Concept Mapping Table
This is the most important table in this lesson. Everything you learned in Chapter 14 has equivalents across the industry:
| What You Learned | Claude Code | OpenAI Codex | Google Gemini CLI | Open Standard |
|---|---|---|---|---|
| Project instructions | CLAUDE.md | AGENTS.md | GEMINI.md | AGENTS.md (AAIF) |
| Agent Skills | .claude/skills/SKILL.md | .agents/skills/SKILL.md | .gemini/skills/SKILL.md | Agent Skills spec (agentskills.io) |
| Tool connectivity | MCP servers in settings.json | MCP servers in config.toml | MCP servers in settings.json | MCP (Linux Foundation) |
| Human-in-the-loop control | allowedTools, permissions | Approval modes (suggest / auto-edit / full-auto) | Tool approval prompts | Vendor-specific (no standard yet) |
| Context hierarchy | Global, Project, Directory | Global, Project | Global, Project, Directory | Vendor-specific (no standard yet) |
| Subagents | Task tool with subagent_type | Cloud sandbox tasks | Not yet available | Vendor-specific (no standard yet) |
| Agent Teams | TeamCreate, TaskCreate, SendMessage | macOS app parallel agents | Not yet available | Vendor-specific (no standard yet) |
| Hooks | Pre/Post tool hooks in settings.json | Not yet available | Not yet available | Vendor-specific (no standard yet) |
| IDE integration | VS Code extension | VS Code extension | VS Code extension | Vendor-specific (no standard yet) |
| Desktop app | Claude Desktop / Cowork | Codex macOS app | Not yet available | Vendor-specific (no standard yet) |
The pattern: what you know transfers. The directory name changes (.claude/ vs .agents/ vs .gemini/), but the concepts are the same.
Standards Convergence: The Agentic AI Foundation
In December 2025, the biggest companies in AI did something unusual: they agreed on shared standards.
The Agentic AI Foundation (AAIF) formed under the Linux Foundation and has grown to 146 members as of February 2026. Platinum members include Anthropic, OpenAI, Google, Microsoft, AWS, Block, Bloomberg, and Cloudflare. Gold members added in 2026 include JPMorgan Chase, American Express, Autodesk, Red Hat, UiPath, ServiceNow, Lenovo, and Huawei. David Nalley (AWS) serves as governing board chair. The foundation governs three founding projects:
| Project | Created By | What It Standardizes | Adoption |
|---|---|---|---|
| MCP (Model Context Protocol) | Anthropic (donated) | Tool connectivity -- how agents talk to external services | 10,000+ active public servers, 97M monthly SDK downloads |
| AGENTS.md | OpenAI (donated) | Project instructions -- how agents understand your codebase | 60,000+ open source projects |
| goose | Block (donated) | Open agent runtime -- reference implementation for agentic workflows | Open source agent framework |
A fourth standard, Agent Skills (the SKILL.md format), was created by Anthropic on December 18, 2025, and has been adopted by OpenAI, Microsoft (GitHub Copilot), Cursor, Atlassian, and Figma. The specification lives at agentskills.io.
What this means for you: The Skills you built in this chapter using .claude/skills/ follow the same specification that Codex uses in .agents/skills/ and Gemini CLI uses in .gemini/skills/. Different directory names, same format. Your Skills are largely portable where the SKILL.md spec is followed; vendor-specific metadata and directory paths may differ slightly.
Three Philosophies, One Ecosystem
Each tool reflects a different design philosophy. None is universally "best" -- they excel at different work.
| Claude Code | OpenAI Codex | Gemini CLI | |
|---|---|---|---|
| Philosophy | "Measure twice, cut once" | "Move fast, iterate" | "Open and accessible" |
| Execution | Local terminal | Cloud sandbox + local | Local CLI + cloud inference |
| Strengths | Deep reasoning, accuracy, self-correction | Parallel tasks, async delegation, speed | Free tier, 1M context, open source |
| Best for | Complex refactoring, architecture work | Batch operations, exploration | Budget-conscious teams, large codebases |
| Pricing | Pro $17/mo (annual) or $20/mo; Max $100-$200/mo | $20-$200/month (via ChatGPT) | Free (1,000 req/day) |
| Open source | Source-available on GitHub (commercial license) | CLI is open source (Rust) | Yes (Apache 2.0) |
Professional developers increasingly use multiple tools for different strengths. Claude Code for the careful architecture work. Codex for parallelized bulk tasks. Gemini CLI for quick queries against massive codebases. This is "poly-agentic" development -- choosing the right tool for each task, not committing to one forever.
SWE-bench: The Coding Benchmark
SWE-bench is a benchmark that tests whether AI can solve real software engineering problems pulled from open source GitHub repositories. Unlike artificial coding challenges, SWE-bench tasks require reading existing code, understanding project context, and producing working fixes.
Multiple variants exist with different difficulty levels. SWE-bench Verified uses human-validated problems. SWE-bench Pro is harder, with more complex multi-file problems.
SWE-bench Verified Leaderboard (March 2026, source)
| Rank | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5 | 80.9% |
| 2 | Claude Opus 4.6 | 80.8% |
| 3 | Gemini 3.1 Pro | 80.6% |
| 4 | MiniMax M2.5 | 80.2% |
| 5 | GPT-5.2 | 80.0% |
| 6 | Claude Sonnet 4.6 | 79.6% |
Notable changes since February 2026: Gemini 3.1 Pro jumped from rank 6 to rank 3 at 80.6%. MiniMax M2.5 entered the top tier as the leading open-weight model. Claude Sonnet 4.6, a mid-tier model, nearly matches flagships at 79.6%.
Important caveat: Companies report scores on different benchmark variants, making direct comparisons tricky. GPT-5.3-Codex scores 56.8% on SWE-bench Pro, which is a harder test, not a worse score. When comparing models, always check which variant was used.
Why This Matters for Your Career
The patterns you learned in this chapter are not Claude Code patterns. They are industry patterns.
When you write a CLAUDE.md file, you are practicing the same skill as writing an AGENTS.md file for Codex or a GEMINI.md file for Gemini CLI. When you build a Skill in .claude/skills/, you can port it to Codex or Gemini CLI by moving the SKILL.md file to a different directory. When you connect an MCP server, that same server works with every tool that supports the protocol.
This portability exists because the industry converged. The AAIF ensures that MCP servers, AGENTS.md files, and Agent Skills work the same way regardless of which coding agent you choose. Your investment in learning these patterns compounds across every tool you touch.
The developers who will thrive are not the ones who master one tool. They are the ones who understand the underlying patterns -- context files, skills, tool connectivity, orchestration -- and apply them wherever the work demands. That is what you built in this chapter.
A Note on Security
MCP and agentic tool connectivity expand what agents can do -- but they also expand the attack surface. When an agent can call external servers, read files, and execute commands, the consequences of a compromised or malicious tool server are significant: prompt injection, data exfiltration, and unintended code execution are all real risks.
As you work across tools and connect MCP servers, apply the same caution you would when installing any third-party dependency: review the server code before trusting it, run MCP servers in isolated environments where possible, and prefer servers from verified publishers. The MCP specification includes transport-level security, but the responsibility for evaluating trust ultimately rests with you.
Try With AI
What are the architectural differences between you (Claude Code)
and OpenAI's Codex CLI? Be specific about execution model,
sandboxing, and where each tool runs code.
What you're learning: How to use an AI agent to analyze its own competitive landscape. Claude Code has direct knowledge of its own architecture and can reason about public information on competitors. This develops your ability to gather technical intelligence through AI conversation.
I have a skill at .claude/skills/my-skill/SKILL.md. Show me how
to create an equivalent for OpenAI Codex (in .agents/skills/)
and for Gemini CLI (in .gemini/skills/). What changes are needed
in each version?
What you're learning: Cross-vendor skill porting. The answer reveals how much of the SKILL.md format is universal (most of it) versus vendor-specific (directory path and minor configuration). This is the practical proof that your skills are portable.
Search the web for the latest SWE-bench Verified leaderboard.
How do Claude, GPT, and Gemini models compare? What should I
consider beyond benchmark scores when choosing a coding agent?
What you're learning: Critical evaluation of AI benchmarks. Scores matter, but so do execution model, pricing, context window, and workflow fit. This prompt teaches you to make tool decisions based on multiple factors, not just a single number.
Further Reading
- Agentic AI Foundation (Linux Foundation) -- AAIF founding announcement
- Model Context Protocol (MCP) -- official specification
- Agent Skills specification -- SKILL.md format
- AGENTS.md -- cross-vendor project instructions standard
- OpenAI Codex CLI -- open source repository
- Google Gemini CLI -- open source repository
- SWE-bench Verified leaderboard -- March 2026 snapshot
The AI model and market landscape change rapidly. Figures in this lesson reflect snapshots from March 2026 and are cited to specific public sources. Check the linked references for the latest numbers. Benchmark scores are self-reported by model providers unless independently verified, and different evaluation variants (Verified, Pro, Lite) produce different results for the same models.
What's Next
You know how the tools work and how they compare across vendors. Next up: Business Strategy with AI (Lesson 40) -- 10 MBA-level frameworks (Porter's Five Forces, disruption analysis, financial statements, leadership) applied to your own business using Claude and the StratArts plugin. Then the Chapter Quiz (Lesson 41) tests your understanding across all 40 lessons.