docs: streamline documentation copy and rename Getting Started to Quick Start

Author: brandonkachen

web/src/components/docs/doc-sidebar.tsx

@@ -14,7 +14,7 @@ import { cn } from '@/lib/utils'
 
 const learnSections = [
   {
-    title: 'Getting Started',
+    title: 'Quick Start',
     href: '/docs/help',
     subsections: getDocsByCategory('help').map((doc) => ({
       title: doc.title,

web/src/content/advanced/claude-code-comparison.mdx

@@ -7,48 +7,49 @@ order: 5
 
 # Codebuff vs Claude Code
 
-Anthropic recently released Claude Code, their own AI coding assistant.
+Claude Code is Anthropic's first-party coding assistant. Codebuff covers the same basics and adds its own workflow tools.
 
-Both Codebuff and Claude Code:
+Both tools:
 
-- Run in your terminal for a seamless coding experience
+- Run in your terminal
 - Understand your entire codebase context
 - Can edit files and execute terminal commands
 - Use Claude Sonnet 4 as their primary model
 
 ## When to Choose Codebuff
 
-Codebuff might be a better choice if you value:
+Pick Codebuff if you want:
 
-- Speed: Codebuff is [nearly 4 times faster](https://x.com/jahooma/status/1894224663817195599)
-- Cost: Codebuff is one third the cost of Claude Code for equivalent tasks and even less for back-and-forth conversation
-- Codebase Analysis: Codebuff pulls more context from scanning your entire codebase, rather than file-by-file. Codebuff also [blends different models](/docs/advanced#what-models-do-you-use) based on their strengths to provide more accurate results.
-- Staying in Flow: Codebuff requires fewer confirmation prompts for file edits and command execution.
-- Focused changes: Codebuff does just what you asked for, while Claude Code will often get carried away editing more and more files.
-- SDK and Programmatic Access: Codebuff provides a full TypeScript SDK for programmatic integration, allowing you to create custom workflows and embed AI coding capabilities into your own tools.
-- Advanced Agent System: Create custom agents with TypeScript generator functions, spawn subagents, and orchestrate complex multi-step workflows that go far beyond simple chat interactions.
+- Faster edits and responses ([benchmark](https://x.com/jahooma/status/1894224663817195599))
+- Lower credit burn for similar work
+- Context pulled from a broad code scan instead of one file at a time
+- Fewer confirmation prompts while editing or running commands
+- Tight, targeted diffs rather than wide rewrites
+- TypeScript SDK and custom agents for scripted workflows
 
 ## When to Choose Claude Code
 
-Claude Code might be a better choice if you:
+Pick Claude Code if you need:
 
-- You require first-party Anthropic integration (no intermediary/proxy) for procurement, data handling, or legal reasons
-- You need enterprise security/compliance controls directly from Anthropic (e.g., SOC 2/ISO programs, data-retention controls, private/VPC networking options)
-- Your org needs centralized admin controls within Anthropic's ecosystem (SSO, RBAC, governance, auditability)
-- You prioritize early access to Anthropic model capabilities and first-party tooling
+- Direct Anthropic access for procurement or data-handling rules
+- Enterprise controls handled by Anthropic (SSO, RBAC, compliance programs, private networking)
+- Early access to Anthropic features and their management UI
 
 ## Feature Comparison
 
 <MarkdownTable>
-  | Feature | Codebuff | Claude Code | | --- | --- | --- | | CLI-based
-  interaction | ✅ | ✅ | | Natural language commands | ✅ | ✅ | | Autonomous
-  test execution | ✅ | ✅ | | Large context window | ✅ (200k-1M) | ✅
-  (200k-1M) | | Directory-specific context awareness | ✅ | 🔄 | | Fast diff
-  edits (no full rewrites) | ✅ | ❌ | | Cost | $ | $$ | | Polished UI | ❌ | ✅
-  | | Minimal interruptions | ✅ | ❌ | | Full-featured SDK | ✅ | ❌ | |
-  Programmatic agent creation | ✅ | ❌ | | Project templates | ✅ | ❌ |
+| Feature | Codebuff | Claude Code |
+| --- | --- | --- |
+| CLI-based interaction | ✅ | ✅ |
+| Natural language commands | ✅ | ✅ |
+| Runs tests autonomously | ✅ | ✅ |
+| Large context window | ✅ (200k-1M) | ✅ (200k-1M) |
+| Directory-specific context | ✅ | 🔄 |
+| Diff-focused edits | ✅ | ❌ |
+| Cost | $ | $$ |
+| Polished UI | ❌ | ✅ |
+| Minimal confirmations | ✅ | ❌ |
+| Full SDK | ✅ | ❌ |
+| Programmatic agents | ✅ | ❌ |
+| Project templates | ✅ | ❌ |
 </MarkdownTable>
-
-## Summary
-
-Both Codebuff and Claude Code are powerful AI coding assistants that can significantly boost your productivity. Codebuff offers more flexible pricing and performance options, while Claude Code provides direct integration with Anthropic's ecosystem.

web/src/content/advanced/config.mdx

@@ -7,24 +7,21 @@ order: 6
 
 # Configuration
 
-Codebuff can be configured using a `codebuff.json` file in your project root. This file allows you to customize various aspects of how codebuff operates in your project.
+Configure Codebuff with `codebuff.json` in your project root.
 
-## Why configure codebuff?
+## Why configure Codebuff?
 
-Configuring codebuff helps you create a seamless development environment where codebuff becomes your central development hub. Instead of juggling multiple terminal windows and manually starting various services, you can let codebuff manage your entire development workflow.
+It lets Codebuff start your dev stack and keep the workflow in one place instead of juggling terminals.
 
 ### Startup Processes
 
-You can configure startup processes, which will run in the background every time codebuff starts! When you use this feature, codebuff will automatically:
+Set startup processes that run in the background every time Codebuff starts:
 
-1. Start your development processes:
-   - Servers (frontend, backend, etc.)
-   - Launch your database
-   - Run any other necessary background services
-2. Manage all these processes for you
-3. Read the logs and outputs and automatically handle any errors that arise
+1. Start your servers (frontend, backend, etc.)
+2. Launch databases or other services
+3. Stream logs and surface errors
 
-This means you can start your day with a single `codebuff` command, write code with codebuff's assistance, and when you're done, closing codebuff will cleanly shut down all your development processes. No more scattered terminal windows or forgotten running processes!
+Start Codebuff once, write code, and close it when you're done. It will stop the processes it started.
 
 ## Configuration Schema
 
@@ -34,7 +31,7 @@ The configuration file follows this structure:
 
 ## Example Configuration
 
-Here's an example configuration file that starts a development server and database:
+Example that starts a dev server and database:
 
 <CodeDemo language="json">
 ```
@@ -61,10 +58,10 @@ Here's an example configuration file that starts a development server and databa
 
 ## Best Practices
 
-1. **Process Names**: Use descriptive names that clearly indicate what each process does.
-2. **Working Directories**: Use relative paths for `cwd` to maintain portability.
-3. **Logging**: Consider using `stdoutFile` and `stderrFile` for important processes to help with debugging.
-4. **Process Management**: Use the `enabled` flag to temporarily disable processes without removing them from the configuration.
+1. Name processes clearly.
+2. Use relative `cwd` paths so configs travel well.
+3. Log important services with `stdoutFile`/`stderrFile`.
+4. Toggle processes with `enabled` instead of deleting them.
 
 ## Troubleshooting
 
@@ -75,4 +72,4 @@ If your startup processes aren't working as expected:
 3. Check the process output in the specified log files if you've configured them
 4. Make sure the JSON syntax in your configuration file is valid
 
-Need more help? Check out our [Troubleshooting](/docs/advanced#troubleshooting) guide or join our [Discord community](https://discord.gg/mcWTGjgTj3).
+Need more help? Check [Troubleshooting](/docs/advanced#troubleshooting) or join [Discord](https://discord.gg/mcWTGjgTj3).

web/src/content/advanced/how-does-it-work.mdx

@@ -7,8 +7,8 @@ order: 2
 
 # How does Codebuff actually work?
 
-Codebuff starts by running through the source files in all subdirectories and parsing them with tree-sitter. We use this information to help find relevant files to you requests.
+Codebuff scans your repo with tree-sitter and builds a quick index of the code. That index makes it fast to find files when you ask for help.
 
-We have a stateless server that passes messages along to Anthropic, OpenAI, or Gemini and websockets to ferry data back and forth to clients. It effectively acts as a proxy between the client and our LLM providers.
+The server is stateless. It proxies requests to Anthropic, OpenAI, or Gemini over websockets and streams results back to the CLI.
 
-We use a fast model to pick the relevant files, and we load them into context Claude Sonnet responds with the right edit. This main agent can also delegate to other agents, as when it does its planning step, or when searching for files.
+We use a fast model to pick files, load the right snippets into context, and let Claude Sonnet propose an edit. The main agent can hand work to other agents for planning or file search when needed.

web/src/content/advanced/large-projects.mdx

@@ -7,30 +7,30 @@ order: 4
 
 # Working with Large Projects
 
-In general, Codebuff works quite well in larger projects. For example, we've pulled Codebuff into the VSCode repo (millions of lines of code) and have had no issues in our testing. That said, if you're noticing Codebuff getting stuck/forgetting context too soon or using a ton of credits, here are some tips to help you mitigate those issues.
+Codebuff runs fine on very large repos (we test against the VS Code codebase). If it starts to wander or burn too many credits, use the tips below.
 
 ## Directory-Based Approach
 
-When working with large codebases, you can start Codebuff from specific directories to maintain focus:
+Start Codebuff in the part of the repo you care about:
 
 ```bash
     cd backend
     codebuff
 ```
 
-Or equivalently without changing directories:
+Or set `--cwd`:
 
 ```bash
     codebuff --cwd backend
 ```
 
-This helps Codebuff concentrate on relevant files and provide more targeted assistance.
+This keeps the context tight.
 
 ## Knowledge Organization
 
-For large projects:
+For big trees, keep knowledge close to the code:
 
-- Create separate knowledge.md files in key directories, like so:
+- Add `knowledge.md` files in important subdirectories:
 
   ```
   services/
@@ -45,22 +45,22 @@ For large projects:
       src/
   ```
 
-- Focus each knowledge file on its directory's specific concerns
-- Link related concepts across knowledge files
-- Keep root knowledge.md for project-wide concepts
+- Keep each file focused on that area
+- Link related files when the areas overlap
+- Use the root `knowledge.md` for cross-cutting notes
 
 ## Effective Communication
 
-When working with large codebases:
+When asking for work in a large repo:
 
-- Be specific about file locations
-- Reference related files explicitly
-- Break large changes into smaller, focused requests
-- Use the `--max` mode for better context understanding by loading more files
+- Point to exact paths
+- Mention related files up front
+- Break large changes into smaller requests
+- Use `--max` when you need Codebuff to load more files
 
 ## Performance Tips
 
-- Leverage your `.codebuffignore` and `.gitignore` files to exclude irrelevant directories
-- Start in subdirectories when possible
-- Break large refactoring tasks into smaller chunks
-- Let Codebuff handle file discovery instead of listing all files
+- Trim noise with `.codebuffignore` and `.gitignore`
+- Start in the most relevant subdirectory
+- Split broad refactors into stages
+- Let Codebuff handle file discovery instead of pasting long file lists

web/src/content/advanced/sdk.mdx

@@ -7,7 +7,7 @@ order: 7
 
 # SDK & Programmatic Access
 
-The Codebuff SDK (`@codebuff/sdk`) allows you to integrate AI coding capabilities into your own applications, scripts, and workflows programmatically.
+The Codebuff SDK (`@codebuff/sdk`) lets you run Codebuff agents from your own code.
 
 ## Installation
 
@@ -66,7 +66,7 @@ import type { AgentDefinition } from '@codebuff/sdk'
 
 const myAgent: AgentDefinition = {
   id: 'my-custom-agent',
-  model: 'anthropic/claude-4-sonnet-20250522',
+  model: 'anthropic/claude-sonnet-4.5',
   displayName: 'My Custom Agent',
   toolNames: ['read_files', 'write_file'],
   instructionsPrompt: 'You are a helpful coding assistant.',
@@ -175,20 +175,15 @@ Returns a `RunState` object containing:
 
 ## Use Cases
 
-The SDK is perfect for:
-
-- **CI/CD Pipelines**: Automated code review, test generation, or refactoring
-- **Custom Workflows**: Build your own AI-powered development tools
-- **Batch Processing**: Process multiple files or projects programmatically
-- **Integration**: Embed Codebuff in VS Code extensions, web apps, or other tools
-- **Automation**: Create scripts that leverage AI for repetitive coding tasks
+- CI/CD pipelines (code review, test generation, refactoring)
+- Batch processing across multiple files
+- Embedding in VS Code extensions or web apps
+- Scripts for repetitive coding tasks
 
 ## Examples
 
 ### Test Generation
 
-Automatically generate unit tests for your code:
-
 ```typescript
 import { CodebuffClient } from '@codebuff/sdk'
 
@@ -217,9 +212,7 @@ async function generateTests(code: string) {
 }
 ```
 
-### Code Review Automation
-
-Integrate AI code review into your CI/CD pipeline:
+### Code Review in CI
 
 ```typescript
 import { CodebuffClient } from '@codebuff/sdk'
@@ -238,9 +231,7 @@ async function reviewPullRequest(diff: string) {
 }
 ```
 
-### Batch Processing Multiple Files
-
-Process multiple files in sequence while maintaining conversation context:
+### Batch Processing
 
 ```typescript
 import { CodebuffClient } from '@codebuff/sdk'
@@ -275,8 +266,6 @@ await addDocstringsToFiles(files)
 
 ### Code Refactoring
 
-Refactor code to use modern patterns:
-
 ```typescript
 import { CodebuffClient } from '@codebuff/sdk'
 
@@ -312,8 +301,6 @@ async function refactorCode(code: string) {
 
 ### Providing Project Context
 
-Pass project files to give the agent better context:
-
 ```typescript
 import { CodebuffClient } from '@codebuff/sdk'
 import * as fs from 'fs'
@@ -339,9 +326,7 @@ async function generateComponentWithContext() {
 }
 ```
 
-### CI/CD Integration (GitHub Actions)
-
-Example GitHub Action workflow for automated code review:
+### GitHub Actions Example
 
 ```yaml
 name: AI Code Review
@@ -370,6 +355,6 @@ jobs:
 
 ## Resources
 
-- [GitHub Repository](https://github.com/CodebuffAI/codebuff) - Full source code
+- [GitHub Repository](https://github.com/CodebuffAI/codebuff) - Source code
 - [Agent Store](https://codebuff.com/store) - Browse available agents
 - [API Keys](https://codebuff.com/api-keys) - Get your API key

web/src/content/advanced/troubleshooting.mdx

@@ -7,15 +7,15 @@ order: 1
 
 # Troubleshooting
 
-Can't find what you're looking for? [Open an issue on GitHub](https://github.com/CodebuffAI/codebuff/issues) or check existing issues for solutions.
+If you're stuck, [open an issue](https://github.com/CodebuffAI/codebuff/issues) or check existing reports.
 
 ## Version
 
-The most latest version of the Codebuff client can be found on the [npm page](https://www.npmjs.com/package/codebuff).
+The latest version of the Codebuff client can be found on the [npm page](https://www.npmjs.com/package/codebuff).
 
 Run `codebuff --version` to make sure you're on the latest version.
 
-Note: Codebuff should automatically install the latest version. If you're still having issues, see below.
+Codebuff should auto-update. If not, try the steps below.
 
 ## Codebuff not updating
 
@@ -29,13 +29,13 @@ Mac/Linux: `sudo chown -R $(whoami) <directory>`
 
 Windows: `cmd takeown /F <directory> /R /D Y`
 
-Otherwise, try reinstalling node with [nvm or fnm](https://nodejs.org/en/download). Then run the codebuff install command again.
+Otherwise reinstall node with [nvm or fnm](https://nodejs.org/en/download) and rerun the install.
 
 ## Accessing Your Chat History
 
 Your conversation history with Codebuff is stored locally (and nowhere else) at `~/.config/manicode/projects/<your-project-name>/chats`.
 
-If you need help, we'd love if you include a copy of your recent chats for us to help you troubleshoot!
+Include recent chats if you ask for help.
 
 ## Common Issues
 
@@ -62,7 +62,7 @@ it means you're having connection issues. In that case, try:
 
 ### Endless Auto-Updates
 
-If Codebuff keeps trying to update itself in an endless loop, there could be several potential causes. Below are known issues and their solutions:
+If Codebuff keeps trying to update itself in a loop, check the items below:
 
 #### Conflicting Node/npm Installations (Homebrew vs. nvm)
 
@@ -160,6 +160,6 @@ tmux send-keys -t my-session Enter
 
 If you're still experiencing issues:
 
-1. [Open an issue on GitHub](https://github.com/CodebuffAI/codebuff/issues) - Codebuff is open source, so you can also browse the code to understand how things work
-2. Join our [Discord community](https://codebuff.com/discord) for real-time help from other users
-3. Contact us at [support@codebuff.com](mailto:support@codebuff.com) – please note we prioritize paying users, but we'll likely reply within a week
+1. [Open an issue on GitHub](https://github.com/CodebuffAI/codebuff/issues)
+2. Join the [Discord community](https://codebuff.com/discord)
+3. Contact [support@codebuff.com](mailto:support@codebuff.com) – replies may take a few days