[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-ai-coding-agents-compared-en":3,"seo:pack:ai-coding-agents-compared:en":68},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":67},"ai-coding-agents-compared","⚖️","#475569","stable","Stable","AI Coding Agents Compared","Side-by-side: Claude Code vs Cursor vs Codex vs Windsurf. Includes leaked system prompts and the 2026 landscape guide.",[16,28,35,43,53,60],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},644,"59436371-30d6-4a51-9f9b-1b1986873728","ai-coding-agents-compared-2026-landscape-guide-59436371","AI Coding Agents Compared — 2026 Landscape Guide","Comprehensive comparison of AI coding agents in 2026: Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, Aider, and more. Features, pricing, model support, and use case recommendations.","Prompt Lab",449,0,"en","prompt","Prompt",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":22,"view_count":34,"vote_count":24,"lang_type":25,"type":26,"type_label":27},804,"a4647a34-1fb8-406e-8809-ef1509e08b4b","cursor-vs-claude-code-vs-codex-ai-coding-compared-a4647a34","Cursor vs Claude Code vs Codex — AI Coding Compared","In-depth comparison of the three leading AI coding tools in 2026. Covers pricing, context window, MCP support, agent capabilities, and best use cases for each platform.",501,{"id":36,"uuid":37,"slug":38,"title":39,"description":40,"author_name":41,"view_count":42,"vote_count":24,"lang_type":25,"type":26,"type_label":27},841,"b3a901fe-8380-4bfc-a631-c57f8d5b51f0","ai-coding-agent-comparison-2026-complete-guide-b3a901fe","AI Coding Agent Comparison 2026 — Complete Guide","Comprehensive comparison of all AI coding agents in 2026. Covers Claude Code, Cursor, Codex, Gemini CLI, Cline, Roo Code, Windsurf, and Aider with feature matrices and recommendations.","Agent Toolkit",382,{"id":44,"uuid":45,"slug":46,"title":47,"description":48,"author_name":49,"view_count":50,"vote_count":24,"lang_type":25,"type":51,"type_label":52},23,"ca000374-f5d8-4d75-a30c-460fda0b6b0e","awesome-cursor-rules-ai-coding-standards-30-stacks-ca000374","Awesome Cursor Rules — AI Coding Standards for 30+ Stacks","Curated .cursorrules files for 30+ tech stacks. Drop into your project root so Cursor AI follows your coding standards automatically.","TokRepo精选",1780,"skill","Skill",{"id":54,"uuid":55,"slug":56,"title":57,"description":58,"author_name":22,"view_count":59,"vote_count":24,"lang_type":25,"type":26,"type_label":27},507,"7d697443-cf7f-4e71-8fd7-45431e5ff685","awesome-ai-system-prompts-32-tool-prompts-revealed-7d697443","Awesome AI System Prompts — 32+ Tool Prompts Revealed","Curated collection of extracted system prompts from 32+ production AI tools including ChatGPT, Claude, Cursor, v0, Manus, Devin, Windsurf, and Perplexity. MIT license, 5,700+ stars.",333,{"id":61,"uuid":62,"slug":63,"title":64,"description":65,"author_name":22,"view_count":66,"vote_count":24,"lang_type":25,"type":26,"type_label":27},34,"6f1ca496-3956-4b11-b736-b13572fc53a0","system-prompts-extracted-30-ai-coding-tools-6f1ca496","System Prompts — Extracted from 30+ AI Coding Tools","Full system prompts extracted from Claude Code, Cursor, Devin, Windsurf, Replit, v0, and 25+ more AI tools. See exactly how they work.",303,"tokrepo install pack\u002Fai-coding-agents-compared",{"pageType":69,"pageKey":8,"locale":25,"title":70,"metaDescription":71,"h1":13,"tldr":72,"bodyMarkdown":73,"faq":74,"schema":90,"internalLinks":99,"citations":111,"wordCount":124,"generatedAt":125},"pack","Claude Code vs Cursor vs Codex CLI vs Windsurf: 2026 Compared","Side-by-side comparison of Claude Code, Cursor, Codex CLI and Windsurf. Includes leaked system prompts and the 2026 AI-coding landscape guide on TokRepo.","A side-by-side of Claude Code vs Cursor vs Codex CLI vs Windsurf, plus the leaked system-prompt collection of 30+ AI coding tools and a 2026 landscape map.","## What's in this pack\n\nThe AI-coding-agent space had four real contenders by mid-2026: Claude Code, Cursor, Codex CLI, Windsurf. They all do \"agent edits your code\", but they make very different bets on UI surface, agent autonomy, and cost. This pack compiles the assets that let you decide which one to install — without writing the comparison yourself.\n\n| Asset | What it gives you |\n|---|---|\n| Cursor rules pack | The default `.cursorrules` setup most production users start from |\n| Claude Code core install | Settings, hooks, and the CLAUDE.md template Anthropic ships with |\n| Codex CLI quickstart | OpenAI's official CLI agent — what comes in the box |\n| Windsurf cascade flow | How Codeium's autonomous mode actually behaves on a multi-file edit |\n| Leaked system prompts (30+ tools) | The verbatim prompts behind Claude Code, Cursor, GitHub Copilot, Cline, Replit and more |\n| 2026 AI coding landscape | TokRepo's evergreen map of the four-host taxonomy |\n\n## How they actually differ\n\n| Dimension | Claude Code | Cursor | Codex CLI | Windsurf |\n|---|---|---|---|---|\n| Surface | Terminal CLI | Forked VS Code IDE | Terminal CLI | Forked VS Code IDE |\n| Default agent autonomy | Medium (asks before destructive actions) | Low–Medium (composer mode) | High (loops by default) | High (cascade mode) |\n| MCP support | Yes (native) | Yes (native) | Yes (native) | Yes |\n| Subagent system | Yes (`.claude\u002Fagents\u002F`) | Rules-only | AGENTS.md | Limited |\n| Free tier | Pro plan | Free + Pro | OpenAI Pro\u002FPlus | Free + Pro |\n| Best for | Headless \u002F CI \u002F long tasks | Tight IDE feedback loop | OpenAI ecosystem | \"Just do it\" autonomy |\n\nThe split is roughly: **CLI for headless and long-running**, **forked-IDE for tight loops with visible diffs**.\n\n## Why the leaked system prompts matter\n\nA 30-tool leaked-prompt repo (x1xhlol\u002Fsystem-prompts-and-models-of-ai-tools) sits in this pack because the prompts reveal each tool's actual model of \"how to be helpful\". Reading Claude Code's system prompt next to Cursor's next to Cline's makes their UX decisions legible — and lets you author your own CLAUDE.md \u002F .cursorrules with the same calibration the vendors used.\n\n## Install in one command\n\n```bash\ntokrepo install pack\u002Fai-coding-agents-compared\n```\n\nThis installs the rules \u002F settings \u002F templates for all four agents at once, so you can A\u002FB them in the same project.\n\n## Picking one\n\n| If you... | Pick |\n|---|---|\n| Live in the terminal | Claude Code |\n| Live in VS Code, want diffs | Cursor |\n| Are deep in the OpenAI ecosystem | Codex CLI |\n| Want maximum autonomy out of the box | Windsurf |",[75,78,81,84,87],{"q":76,"a":77},"Is Claude Code better than Cursor in 2026?","They're solving different problems. Claude Code is a terminal-first agent — best for headless tasks, CI, and long-running refactors where you want the agent to keep going without ceremony. Cursor is a forked VS Code IDE optimized for tight loops with visible diffs. Most production teams use both; the question is which one for which task.",{"q":79,"a":80},"Are the leaked system prompts in this pack legal to use?","The repository (x1xhlol\u002Fsystem-prompts-and-models-of-ai-tools) contains prompts extracted from each tool's runtime. They're educational reference, not a license to redistribute. Use them to *understand* how each tool calibrates its agent — not as a base for a clone.",{"q":82,"a":83},"What's the difference between Claude Code subagents and Cursor rules?","Claude Code subagents are full sub-agents with their own system prompt that the host dispatches to based on task description. Cursor rules (.cursorrules \u002F .mdc) are static instruction files appended to every conversation. Subagents give you compositional capability; rules give you global behavior shaping.",{"q":85,"a":86},"Does TokRepo host the actual binaries?","No — TokRepo is a registry of *configurations* (rules, prompts, subagents, slash commands). The TokRepo CLI fetches and places config files into your project. The actual Claude Code \u002F Cursor \u002F Codex CLI \u002F Windsurf binaries are installed from each vendor.",{"q":88,"a":89},"Which one has the best MCP support?","All four support MCP natively in 2026. Claude Code's MCP integration is the most polished (built by Anthropic themselves); Cursor and Windsurf added it in 2025 and reach feature parity for most servers; Codex CLI has the most permissive default tool list. See our MCP Server Stack pack for what to install in any of them.",{"@context":91,"@type":92,"name":13,"description":93,"numberOfItems":94,"publisher":95},"https:\u002F\u002Fschema.org","CollectionPage","Side-by-side comparison: Claude Code vs Cursor vs Codex vs Windsurf.",6,{"@type":96,"name":97,"url":98},"Organization","TokRepo","https:\u002F\u002Ftokrepo.com",[100,104,107],{"url":101,"anchor":102,"reason":103},"\u002Fen\u002Ftools\u002Fclaude-code","Claude Code","tool deep-dive",{"url":105,"anchor":106,"reason":103},"\u002Fen\u002Ftools\u002Fcursor","Cursor",{"url":108,"anchor":109,"reason":110},"\u002Fen\u002Fpacks\u002Fmcp-server-stack","MCP Server Stack","all hosts share this layer",[112,116,120],{"claim":113,"source_name":114,"source_url":115},"Leaked system prompts of 30+ AI coding tools","x1xhlol\u002Fsystem-prompts-and-models-of-ai-tools","https:\u002F\u002Fgithub.com\u002Fx1xhlol\u002Fsystem-prompts-and-models-of-ai-tools",{"claim":117,"source_name":118,"source_url":119},"Claude Code, Cursor, Codex CLI, Windsurf official pages","Vendor docs","https:\u002F\u002Fdocs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code",{"claim":121,"source_name":122,"source_url":123},"2026 AI coding landscape","TokRepo featured guide","https:\u002F\u002Ftokrepo.com\u002Fen\u002Ffeatured",460,"2026-05-02T14:00:00Z"]