--- title: Rider Hands AI Agents The Keys To Its Refactoring Engine... description: JetBrains introduces a bundled 'refactoring-code' skill in Rider 2026.2.1 that lets AI coding agents call Rider's own C# refactoring engine directly instead of... canonical: https://daily.dev/posts/rider-hands-ai-agents-the-keys-to-its-refactoring-engine-for-safer-faster-and-cheaper-results-tsvmsygq1 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Rider Hands AI Agents The Keys To Its Refactoring Engine For Safer, Faster, And Cheaper Results | daily.dev og:description: JetBrains introduces a bundled 'refactoring-code' skill in Rider 2026.2.1 that lets AI coding agents call Rider's own C# refactoring engine directly instead of... og:url: https://daily.dev/posts/rider-hands-ai-agents-the-keys-to-its-refactoring-engine-for-safer-faster-and-cheaper-results-tsvmsygq1 og:image: https://api.daily.dev/og/posts/tSVmSYgq1.png og:image:alt: Rider Hands AI Agents The Keys To Its Refactoring Engine For Safer, Faster, And Cheaper Results og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Rider Hands AI Agents The Keys To Its Refactoring Engine For Safer, Faster, And Cheaper Results **[JetBrains .NET Blog](https://daily.dev/sources/jetbrains-dotnet)** · 7 min read · 2 upvotes · 0 comments ## Summary JetBrains introduces a bundled 'refactoring-code' skill in Rider 2026.2.1 that lets AI coding agents call Rider's own C# refactoring engine directly instead of approximating refactors with sed, grep, and repeated dotnet build cycles. In a benchmark of fifteen C# refactoring tasks using gpt-5.5 through Codex CLI, giving the agent access to the skill cut median task time by 83%, cost per solved task by 64%, and tool calls by 63%. A detailed extract-base-class example shows the agent going from 24 tool calls and 336.7 seconds (with 11 build-and-fix cycles) down to 3 calls and 19.8 seconds when it can invoke Rider's structural refactoring directly. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What does the refactoring-code skill in JetBrains Rider 2026.2.1 actually do for AI agents working with C#? It lets AI coding agents invoke Rider's built-in ReSharper-powered C# refactoring engine directly instead of approximating refactors with text edits and sed commands. It ships bundled with Rider 2026.2.1, requires no setup, and activates automatically when an agent is asked to refactor C# code, covering operations like rename, extract method, extract interface, extract base class, change API signature, move type to namespace, and safe delete. _Developers weighing AI agent tooling for large C# codebases can follow releases like this on daily.dev._ ### How much faster and cheaper does AI-driven C# refactoring get with Rider's refactoring-code skill compared to without it? Median task time dropped 83% and cost per solved task dropped 64% across fifteen C# refactoring tasks run with gpt-5.5 through Codex CLI. Total tool calls across the evaluation fell from 2,513 to 926, and dotnet build calls dropped from 163 to 3, because the agent no longer needed to compile repeatedly to check what its guessed text edits had broken. _Anyone tracking real cost and speed gains from AI coding agents can follow measured results like these on daily.dev._ ### Why did an AI coding agent call dotnet build 163 times when refactoring C# code without a dedicated refactoring tool? The agent was not compiling to verify finished work but to discover what its last text-based edit had broken, since correct refactors like renames depend on overload resolution, partial classes, and interface implementations that cannot be reconstructed from a regular expression. Rider's refactoring engine avoids this because it works from a resolved syntax tree that already knows every identifier binding and reference location. _Developers debugging why AI agents loop on build errors during refactors can track solutions like this on daily.dev._ ## Similar posts on daily.dev - [Rider 2026.2: IDE Intelligence for AI Agents, Faster Performance, and Spectacular Game Dev Updates](https://daily.dev/posts/rider-2026-2-ide-intelligence-for-ai-agents-faster-performance-and-spectacular-game-dev-updates-f91cdm3hp) · JetBrains .NET Blog · 1 upvotes · 1 comments - [ReSharper and Rider 2025.3.2 Updates Out Now\!](https://daily.dev/posts/resharper-and-rider-2025-3-2-updates-out-now--6ximwvrel) · JetBrains · 5 upvotes · 0 comments - [Rider 2026.2 Release Candidate Is Out\!](https://daily.dev/posts/rider-2026-2-release-candidate-is-out--uvvylqagt) · JetBrains .NET Blog · 0 upvotes · 0 comments - [Automate Rider Search and Replace Patterns with Agent Skills](https://daily.dev/posts/automate-rider-search-and-replace-patterns-with-agent-skills-lxscamhlj) · We Are .NET · 0 upvotes · 0 comments - [Rider and ReSharper 2025.3.0.4: Important Updates Released](https://daily.dev/posts/rider-and-resharper-2025-3-0-4-important-updates-released-5fve9hxi1) · JetBrains · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#c#](https://daily.dev/tags/c#) [View this post on daily.dev](https://daily.dev/posts/rider-hands-ai-agents-the-keys-to-its-refactoring-engine-for-safer-faster-and-cheaper-results-tsvmsygq1) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Rider Hands AI Agents The Keys To Its Refactoring Engine For Safer, Faster, And Cheaper Results","url":"https://daily.dev/posts/rider-hands-ai-agents-the-keys-to-its-refactoring-engine-for-safer-faster-and-cheaper-results-tsvmsygq1","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/rider-hands-ai-agents-the-keys-to-its-refactoring-engine-for-safer-faster-and-cheaper-results-tsvmsygq1"},"datePublished":"2026-08-19T17:20:18.706Z","dateModified":"2026-09-14T07:06:11.706Z","description":"JetBrains introduces a bundled 'refactoring-code' skill in Rider 2026.2.1 that lets AI coding agents call Rider's own C# refactoring engine directly instead of...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/28aa78158afa5247330561d8931217c1?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/28aa78158afa5247330561d8931217c1?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"JetBrains .NET Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"JetBrains .NET Blog","logo":"https://media.daily.dev/image/upload/s--2Z0xk_Ia--/f_auto,q_auto/v1780213485/logos/jetbrains-dotnet?_a=BAMAMiWQ0","url":"https://daily.dev/sources/jetbrains-dotnet"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/rider-hands-ai-agents-the-keys-to-its-refactoring-engine-for-safer-faster-and-cheaper-results-tsvmsygq1","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,c#","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"JetBrains .NET Blog","item":"https://daily.dev/sources/jetbrains-dotnet"},{"@type":"ListItem","position":3,"name":"Rider Hands AI Agents The Keys To Its Refactoring Engine For Safer, Faster, And Cheaper Results"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/rider-hands-ai-agents-the-keys-to-its-refactoring-engine-for-safer-faster-and-cheaper-results-tsvmsygq1#faq","mainEntity":[{"@type":"Question","name":"What does the refactoring-code skill in JetBrains Rider 2026.2.1 actually do for AI agents working with C#?","acceptedAnswer":{"@type":"Answer","text":"It lets AI coding agents invoke Rider's built-in ReSharper-powered C# refactoring engine directly instead of approximating refactors with text edits and sed commands. It ships bundled with Rider 2026.2.1, requires no setup, and activates automatically when an agent is asked to refactor C# code, covering operations like rename, extract method, extract interface, extract base class, change API signature, move type to namespace, and safe delete. Developers weighing AI agent tooling for large C# codebases can follow releases like this on daily.dev."}},{"@type":"Question","name":"How much faster and cheaper does AI-driven C# refactoring get with Rider's refactoring-code skill compared to without it?","acceptedAnswer":{"@type":"Answer","text":"Median task time dropped 83% and cost per solved task dropped 64% across fifteen C# refactoring tasks run with gpt-5.5 through Codex CLI. Total tool calls across the evaluation fell from 2,513 to 926, and dotnet build calls dropped from 163 to 3, because the agent no longer needed to compile repeatedly to check what its guessed text edits had broken. Anyone tracking real cost and speed gains from AI coding agents can follow measured results like these on daily.dev."}},{"@type":"Question","name":"Why did an AI coding agent call dotnet build 163 times when refactoring C# code without a dedicated refactoring tool?","acceptedAnswer":{"@type":"Answer","text":"The agent was not compiling to verify finished work but to discover what its last text-based edit had broken, since correct refactors like renames depend on overload resolution, partial classes, and interface implementations that cannot be reconstructed from a regular expression. Rider's refactoring engine avoids this because it works from a resolved syntax tree that already knows every identifier binding and reference location. Developers debugging why AI agents loop on build errors during refactors can track solutions like this on daily.dev."}}]} ```