Use Ultracite with Deepagents when you want agentic task chains to inherit the same repo standards your team expects from direct edits. It is a good fit for multi-step work where consistency matters across several sub-tasks.
These values come from the same data Ultracite uses when it creates or updates Deepagents instructions, so the page matches what actually gets written into the repo.
AGENTS.md
Run npx ultracite@latest init --agents deepagents and Ultracite will update this file for the default setup.
Ultracite writes to this exact file when you initialize or update the agent integration.
Existing instructions stay in place and Ultracite appends its rules where the agent expects them.
The generated file starts directly with Ultracite rules and skips an extra heading block.
Deepagents does not use a separate hook configuration in Ultracite.
This preview shows the exact default file content Ultracite writes for Deepagents when you use the standard Biome setup.
If Deepagents supports hooks, the second tab shows the companion hook config that runs after AI-driven edits.
# Ultracite Code StandardsThis project uses **Ultracite**, a zero-config preset that enforces strict code quality standards through automated formatting and linting.## Quick Reference- **Format code**: `npx ultracite fix`- **Check for issues**: `npx ultracite check`- **Diagnose setup**: `npx ultracite doctor`Biome (the underlying engine) provides robust linting and formatting. Most issues are automatically fixable.---## Core PrinciplesWrite code that is **accessible, performant, type-safe, and maintainable**. Focus on clarity and explicit intent over brevity.### Type Safety & Explicitness- Use explicit types for function parameters and return values when they enhance clarity- Prefer `unknown` over `any` when the type is genuinely unknown- Use const assertions (`as const`) for immutable values and literal types- Leverage TypeScript's type narrowing instead of type assertions- Use meaningful variable names instead of magic numbers - extract constants with descriptive names### Modern JavaScript/TypeScript- Use arrow functions for callbacks and short functions- Prefer `for...of` loops over `.forEach()` and indexed `for` loops- Use optional chaining (`?.`) and nullish coalescing (`??`) for safer property access- Prefer template literals over string concatenation- Use destructuring for object and array assignments- Use `const` by default, `let` only when reassignment is needed, never `var`### Async & Promises- Always `await` promises in async functions - don't forget to use the return value- Use `async/await` syntax instead of promise chains for better readability- Handle errors appropriately in async code with try-catch blocks- Don't use async functions as Promise executors### React & JSX- Use function components over class components- Call hooks at the top level only, never conditionally- Specify all dependencies in hook dependency arrays correctly- Use the `key` prop for elements in iterables (prefer unique IDs over array indices)- Nest children between opening and closing tags instead of passing as props- Don't define components inside other components- Use semantic HTML and ARIA attributes for accessibility: - Provide meaningful alt text for images - Use proper heading hierarchy - Add labels for form inputs - Include keyboard event handlers alongside mouse events - Use semantic elements (`<button>`, `<nav>`, etc.) instead of divs with roles### Error Handling & Debugging- Remove `console.log`, `debugger`, and `alert` statements from production code- Throw `Error` objects with descriptive messages, not strings or other values- Use `try-catch` blocks meaningfully - don't catch errors just to rethrow them- Prefer early returns over nested conditionals for error cases### Code Organization- Keep functions focused and under reasonable cognitive complexity limits- Extract complex conditions into well-named boolean variables- Use early returns to reduce nesting- Prefer simple conditionals over nested ternary operators- Group related code together and separate concerns### Security- Add `rel="noopener"` when using `target="_blank"` on links- Avoid `dangerouslySetInnerHTML` unless absolutely necessary- Don't use `eval()` or assign directly to `document.cookie`- Validate and sanitize user input### Performance- Avoid spread syntax in accumulators within loops- Use top-level regex literals instead of creating them in loops- Prefer specific imports over namespace imports- Avoid barrel files (index files that re-export everything)- Use proper image components (e.g., Next.js `<Image>`) over `<img>` tags### Framework-Specific Guidance**Next.js:**- Use Next.js `<Image>` component for images- Use `next/head` or App Router metadata API for head elements- Use Server Components for async data fetching instead of async Client Components**React 19+:**- Use ref as a prop instead of `React.forwardRef`**Solid/Svelte/Vue/Qwik:**- Use `class` and `for` attributes (not `className` or `htmlFor`)---## Testing- Write assertions inside `it()` or `test()` blocks- Avoid done callbacks in async tests - use async/await instead- Don't use `.only` or `.skip` in committed code- Keep test suites reasonably flat - avoid excessive `describe` nesting## When Biome Can't HelpBiome's linter will catch most issues automatically. Focus your attention on:1. **Business logic correctness** - Biome can't validate your algorithms2. **Meaningful naming** - Use descriptive names for functions, variables, and types3. **Architecture decisions** - Component structure, data flow, and API design4. **Edge cases** - Handle boundary conditions and error states5. **User experience** - Accessibility, performance, and usability considerations6. **Documentation** - Add comments for complex logic, but prefer self-documenting code---Most formatting and common issues are automatically fixed by Biome. Run `npx ultracite fix` before committing to ensure compliance.These are the workflows where Ultracite adds the most leverage to Deepagents, based on how the agent reads instructions and how teams typically wire it into day-to-day development.
Keep Deepagents aligned when one task spans research, coding, and several follow-up changes.
Use a committed repo contract while you experiment with Deepagents in real repositories.
Reduce drift by giving every Deepagents run the same durable coding baseline.
These differentiators come from the way Deepagents actually handles repo instructions, file updates, and AI-assisted development work.
Deepagents is built for multi-step agent flows, so explicit repo standards help each step stay aligned with the codebase contract.
Using `AGENTS.md` keeps guidance close to the repo rather than hidden in agent runtime settings.
Committed repo instructions help Deepagents stay consistent across research, planning, and implementation passes.
If Claude Code, Continue, Qoder are close to the way you work, these neighboring integrations are worth comparing too.
Configure Claude Code with Ultracite so terminal-based agent runs follow your TypeScript, React, accessibility, and performance standards from the first edit.
Configure Continue with Ultracite through AGENTS.md so its terminal agent follows your repo's linting, architecture, and framework standards.
Add Ultracite to Qoder through AGENTS.md so its coding CLI follows your repo's linting, architecture, and framework standards.
And used by thousands of open source projects.
Here's what some of the most innovative and forward-thinking developers in the React ecosystem have to say about Ultracite.