# Claudekit.ai > Claudekit is the independent community hub for building your Claude kit: tested Claude Code kits, guides, Skills, MCP servers, prompts and free tools, all dated. Claudekit.ai is an independent community project. Not affiliated with, endorsed by, or sponsored by Anthropic. Claude is a trademark of Anthropic, PBC. ## Start here - [Claude usage limits](https://claudekit.ai/guides/claude-usage-limits/): how the five-hour and weekly limits work, with dated official sources - [Plan picker](https://claudekit.ai/generators/api-cost/#plan-picker): compare your Claude Code usage at API rates with Pro, Max and Team prices - [Tested Claude Code kits](https://claudekit.ai/recipes/): kits we actually ran, each with its test level, Claude Code version and test date - [How we test](https://claudekit.ai/how-we-test/): what each test level means, what we do not test, and how corrections work - [Agents at work](https://claudekit.ai/live/): the AI agent team that runs Claudekit, each agent's schedule and last run, and the last 7 days of activity - [Hire Claudekit](https://claudekit.ai/hire/): a custom AI agent for your business, priced by its number of features, built and tested by AI agents with no human review, delivered as a private repo - [Claude kit overview](https://claudekit.ai/claude-kit/): what goes in a Claude kit and where to get each piece - [Claude Code plugins](https://claudekit.ai/plugins/): ranked plugins and marketplaces with install commands - [MCP servers](https://claudekit.ai/mcp/): MCP servers for Claude grouped by use case - [About](https://claudekit.ai/about/): who runs Claudekit and how content is produced - [Affiliate disclosure](https://claudekit.ai/disclosure/): how the site is funded ## Guides - [All guides](https://claudekit.ai/guides/): Step-by-step Claude guides for Claude Code, the Claude API, MCP servers, Skills and agents — from first prompt to production workflows, sorted by level. - [Claude Agents Explained: Subagents, Agent SDK, Managed](https://claudekit.ai/guides/claude-agents/): Claude agents come in four forms: Claude Code subagents, the Agent SDK, Managed Agents and the API tool runner. See how each works and which to pick. - [AI Agent Development Cost (2026): Build, Run and Maintain](https://claudekit.ai/guides/ai-agent-development-cost/): What a custom AI agent costs in 2026: real build prices from freelancers, fixed-price services and agencies, plus how to estimate token and upkeep costs. - [AI Agents for Small Business: 12 Use Cases, DIY or Hire](https://claudekit.ai/guides/ai-agents-for-small-business/): Twelve narrow jobs an AI agent can do in a small business, each with its trigger, tools, a feature count and whether you can build it yourself or should hire. - [How to Build an AI Agent with Claude (Step by Step)](https://claudekit.ai/guides/build-ai-agent-with-claude/): Build an AI agent with Claude: compare subagents, the Agent SDK, Managed Agents and the API tool loop, then run a Python agent with a custom tool and a budget. - [Multi-Agent Claude Code: Subagents, Teams, Workflows](https://claudekit.ai/guides/claude-code-agent-teams/): Run multi-agent Claude Code: when to use subagents, experimental agent teams or dynamic workflows, how to turn each on, and when more agents waste tokens. - [Claude Code GitHub Actions: @claude Mentions and PR Review](https://claudekit.ai/guides/claude-code-github-actions/): Set up Claude Code GitHub Actions: /install-github-app, secrets, @claude mentions, automated PR review, scheduled jobs, claude_args and cloud providers. - [Claude Code Review: Official, /code-review, Action or Kit?](https://claudekit.ai/guides/claude-code-review/): Four ways to get Claude to review code: the managed Code Review app, /code-review in your terminal, the GitHub Action or a kit you own. Cost and setup compared. - [Claude Code Pricing (2026): Plans, API Costs and Limits](https://claudekit.ai/guides/claude-code-pricing/): Claude Code pricing explained: which Claude plans include it, Pro vs Max vs Team seats, API token rates, usage limits, and how to track spend with /usage. - [Claude Code Security Checklist for Teams](https://claudekit.ai/guides/claude-code-security-checklist/): A Claude Code security checklist for teams: permission modes, secret deny rules, the Bash sandbox, guard hooks, MCP and plugin review, CI and managed settings. - [Claude Code Token Usage: How to Check and Track It](https://claudekit.ai/guides/claude-code-token-usage/): Check Claude Code token usage with /usage, /context, the status line, claude -p JSON and OpenTelemetry, and learn which tokens count and why sessions grow. - [Claude Code Statusline: Show Your Rate Limit Usage](https://claudekit.ai/guides/claude-code-statusline-usage/): Show your Claude Code 5-hour and weekly limit usage in the status line: a tested bash script using the documented rate_limits fields, with setup and fixes. - [Claude Code Subagents: How to Create and Use Them](https://claudekit.ai/guides/claude-code-subagents-guide/): A practical guide to Claude Code subagents: built-in agents, .claude/agents files, frontmatter, tool limits, models, memory and patterns that save context. - [Claude Limits Changelog: Every Usage Limit Change, Dated](https://claudekit.ai/guides/claude-limits-changelog/): A dated log of changes to Claude and Claude Code usage limits since weekly limits arrived in 2025, each with an official or press source and a checked date. - [Claude Pricing (2026): Free, Pro, Max, Team and Enterprise](https://claudekit.ai/guides/claude-pricing/): Claude pricing in one place: what Free, Pro, Max, Team and Enterprise cost, what each plan includes, how usage limits work, and which plan fits how you work. - [Hire an AI Agent Developer: Freelancer, Agency or DIY?](https://claudekit.ai/guides/hire-ai-agent-developer/): How to hire an AI agent developer: when a freelancer, a fixed-price service, an agency or DIY fits, published prices, 10 questions to ask and the red flags. - [Claude Usage Limits Explained: 5-Hour and Weekly Limits](https://claudekit.ai/guides/claude-usage-limits/): Claude usage limits on Free, Pro, Max, Team and Enterprise: five-hour and weekly windows, Claude Code limits, how to check usage and what to do at the limit. - [Is Claude Code Safe? What It Can Touch, How to Lock It](https://claudekit.ai/guides/is-claude-code-safe/): Is Claude Code safe? What it can read, run and send, where your code goes, whether it is fine for work, and three settings that make it safer to run locally. - [How to Reduce Claude Token Usage (Claude Code, Chat and API)](https://claudekit.ai/guides/reduce-claude-token-usage/): Documented ways to cut Claude token usage: /clear and /compact, model and effort choice, a lean CLAUDE.md, subagents, MCP hygiene, and prompt caching on the API. - [Best MCP Servers for Claude Code (2026): 10 Picks](https://claudekit.ai/guides/best-mcp-servers/): The 10 best MCP servers for Claude Code in 2026: GitHub, Context7, Playwright, Sentry, Linear and more, with verified install commands and security notes. - [Best Claude Code Skills (2026): 12 Picks Worth Installing](https://claudekit.ai/guides/best-claude-code-skills/): The best Claude Code skills in 2026: official Anthropic skills, Superpowers, Matt Pocock's skills and frontend picks, with verified install commands. - [The Agent Skills Standard Explained (SKILL.md, 2026)](https://claudekit.ai/guides/agent-skills-standard/): What the Agent Skills open standard is, the SKILL.md fields the spec allows, how progressive disclosure works, and what Claude Code adds on top of the standard. - [Best Claude Chrome Extensions (2026): Official + 4 More](https://claudekit.ai/guides/best-claude-chrome-extensions/): The official Claude in Chrome extension plus verified third-party Claude extensions for exports, usage tracking and prompts, with a safety checklist. - [Build an MCP Server in TypeScript (SDK v2 Tutorial)](https://claudekit.ai/guides/build-mcp-server-typescript/): Build your first MCP server in TypeScript with the v2 SDK: setup, a tool, a resource and a prompt, testing in MCP Inspector, then connecting it to Claude Code. - [Anthropic API Key: Get, Store and Rotate It Safely](https://claudekit.ai/guides/claude-api-key/): How to get an Anthropic (Claude) API key in the Claude Console, store it in env vars, scope it to a workspace, rotate it and fix 401, 403 and 429 errors. - [Claude API Tutorial: First Request in curl, Python and TS](https://claudekit.ai/guides/claude-api-tutorial/): Claude API tutorial for 2026: make your first Anthropic API request in curl, Python and TypeScript, then add streaming, multi-turn chat and tool use. - [Claude API Pricing (2026): Per-Token Costs and Examples](https://claudekit.ai/guides/claude-api-pricing/): Claude API pricing for every current model: input, output and cache prices per million tokens, Batch API discounts, tool fees and four worked cost examples. - [Claude Artifacts: Create, Share and Publish (2026 Guide)](https://claudekit.ai/guides/claude-artifacts/): What Claude artifacts are, how to create, edit, share and publish them, AI-powered apps, templates, storage and connectors, and limits by plan (Oct 2026). - [Claude Code Best Practices: 20 Tips That Actually Work](https://claudekit.ai/guides/claude-code-best-practices/): Claude Code best practices and tips from the official guide and daily use: verification loops, plan mode, lean CLAUDE.md, context hygiene and parallel work. - [Claude Code Context Window: /context, /compact and /clear](https://claudekit.ai/guides/claude-code-context-management/): Manage the Claude Code context window: what loads at startup, when to use /context, /compact and /clear, how compaction works, and habits that keep it lean. - [Block Dangerous Commands in Claude Code with PreToolUse Hooks](https://claudekit.ai/guides/claude-code-block-dangerous-commands/): Stop rm -rf, curl | sh, force-pushes and DROP TABLE before they run: a tested PreToolUse hook for Claude Code, deny rules, onFailure and the limits to know. - [Claude Code FAQ: 15 Common Questions, Answered](https://claudekit.ai/guides/claude-code-faq/): Straight answers to 15 common Claude Code questions: cost, plans, Windows, models, privacy, undo, CLAUDE.md vs AGENTS.md, MCP, limits and resuming sessions. - [Claude Code --dangerously-skip-permissions: When It's Safe](https://claudekit.ai/guides/claude-code-dangerously-skip-permissions/): What --dangerously-skip-permissions does in Claude Code, what still stops it, and how to run it safely in a container as a non-root user. Checked October 2026. - [Getting Started with Claude Code: Install to First PR](https://claudekit.ai/guides/claude-code-getting-started/): Install Claude Code, sign in, run your first session, set up CLAUDE.md, learn the essential slash commands and adopt the habits that get reliably good results. - [Claude Code Hooks Guide: Automate and Guard Your Agent](https://claudekit.ai/guides/claude-code-hooks-guide/): How Claude Code hooks work: lifecycle events, matchers, exit codes and JSON output, plus ready-made hooks for formatting, alerts and blocking risky edits. - [Claude Code Headless Mode: claude -p for Scripts and CI](https://claudekit.ai/guides/claude-code-headless-mode/): Run Claude Code headless with claude -p: output formats, JSON schema, streaming, tool allowlists, bare mode, resuming sessions and copy-paste CI scripts. - [Claude Code Plugins Guide: Install, Build and Share](https://claudekit.ai/guides/claude-code-plugins-guide/): How Claude Code plugins work: installing from marketplaces, install scopes, the best official plugins, and building your own with skills, agents, hooks and MCP. - [Claude Code Plugin Marketplace: Build One for Your Team](https://claudekit.ai/guides/claude-code-plugin-marketplace/): Create a private Claude Code plugin marketplace: marketplace.json schema, plugin sources, validation, auto-install via settings.json, private repos and updates. - [Claude Code Permission Modes: Auto, Plan, Accept Edits & More](https://claudekit.ai/guides/claude-code-permission-modes/): Every Claude Code permission mode explained: Manual, acceptEdits, plan, auto, dontAsk and bypass, plus allow/ask/deny rules and safe defaults for local and CI. - [Claude Code Sandbox: Set Up /sandbox for Safer Bash Commands](https://claudekit.ai/guides/claude-code-sandboxing/): Turn on the Claude Code sandbox with /sandbox: what it blocks, auto-allow vs regular mode, allowWrite, allowedDomains, credentials and strict mode explained. - [Claude Code Skills Guide: How to Write a SKILL.md](https://claudekit.ai/guides/claude-code-skills-guide/): Learn what Claude Code skills are, where SKILL.md files live, the key frontmatter fields, and how to write, test and share skills, with copy-paste examples. - [Claude Code Slash Commands: A Practical Cheatsheet (2026)](https://claudekit.ai/guides/claude-code-slash-commands/): Claude Code slash commands cheatsheet: the built-in commands that matter, their aliases and arguments, plus how to add custom commands, plugin and MCP ones. - [Claude Code Tutorial: How to Use Claude Code on a Real Task](https://claudekit.ai/guides/claude-code-tutorial/): How to use Claude Code step by step: explore a codebase, plan a feature, implement it with tests, review the diff, commit, then save the workflow as a skill. - [Claude Code Worktrees: Run Parallel Sessions Safely](https://claudekit.ai/guides/claude-code-worktrees/): Run Claude Code sessions in parallel with git worktrees: the --worktree flag, .worktreeinclude, subagent isolation, /batch, cleanup rules and manual setup. - [Claude Code VS Code Extension and JetBrains Plugin Guide](https://claudekit.ai/guides/claude-code-vscode/): Install and use the Claude Code VS Code extension and JetBrains plugin: setup, shortcuts, @-mentions, diffs, checkpoints, settings and when to use the CLI. - [Claude Desktop MCP Setup: A No-Code Guide (2026)](https://claudekit.ai/guides/claude-desktop-mcp-setup/): Connect Claude Desktop to your files, apps and tools with MCP, no coding needed: connectors, one-click desktop extensions, the config file and quick fixes. - [Claude Desktop App: Download, Install and Features (2026)](https://claudekit.ai/guides/claude-desktop/): Get the Claude desktop app on Mac, Windows or Linux: system requirements, install steps, Chat, Cowork and Code tabs, MCP desktop extensions, and quick fixes. - [Claude Kit Pricing (2026): Paid Kits vs Free, Reviewed](https://claudekit.ai/guides/claude-kit-pricing-and-review/): Claude kit pricing compared: Agentkit.best (formerly Claudekit.cc), theclaudekit.com's ClaudeKit and free kits like Superpowers, with honest pros, cons and picks. - [Claude Models Explained: Fable, Opus, Sonnet and Haiku](https://claudekit.ai/guides/claude-models-explained/): Claude Sonnet, Opus, Haiku and Fable compared: current model IDs, context windows, max output, API prices and how to pick the right model, checked October 2026. - [CLAUDE.md Guide: Write Project Memory That Claude Follows](https://claudekit.ai/guides/claude-md-guide/): How CLAUDE.md works in Claude Code: file locations, load order, @imports, .claude/rules, AGENTS.md, what to include, plus copy-paste templates for 5 stacks. - [Claude Projects: How to Set Up and Use Them (2026)](https://claudekit.ai/guides/claude-projects/): Claude Projects explained: how to create one, add project knowledge and instructions, how RAG expands capacity, sharing on Team and Enterprise, and plan limits. - [Claude Prompting Best Practices: A Practical 2026 Guide](https://claudekit.ai/guides/claude-prompting-best-practices/): Claude prompting best practices from Anthropic's docs: clear instructions, context, examples, XML tags, long documents, output control and agentic prompts. - [How to Install Claude Code (Mac, Windows, Linux, WSL)](https://claudekit.ai/guides/how-to-install-claude-code/): Install Claude Code on macOS, Windows, WSL or Linux, then update, pin a version or uninstall it. Every command checked against the official docs, plus fixes. - [MCP Servers for Claude: Setup Guide for Code and Desktop](https://claudekit.ai/guides/mcp-servers-for-claude-guide/): What the Model Context Protocol is, how to add MCP servers for Claude in Claude Code and Claude Desktop, scopes, auth, and which server types to install first. - [Skills vs Subagents vs Hooks: When to Use Each in Claude Code](https://claudekit.ai/guides/skills-vs-subagents-vs-hooks/): Skills vs subagents vs hooks in Claude Code, answered: what each one does, context cost, when to pick which, how they combine, plus CLAUDE.md, MCP and plugins. - [What Is Claude Code? Anthropic's Coding Agent Explained](https://claudekit.ai/guides/what-is-claude-code/): What is Claude Code? A plain guide to Anthropic's agentic coding tool: what it does, where it runs, what it costs, and every guide you need to master it. - [What Is a Claude Kit? How to Build Your Own Claude Toolkit](https://claudekit.ai/guides/what-is-claude-kit/): A Claude kit is your bundle of skills, subagents, hooks, MCP servers and prompts. What goes in one, what happened to Claudekit.cc, and how to build your own. - [What Is Claude? Anthropic's AI Assistant Explained](https://claudekit.ai/guides/what-is-claude/): What is Anthropic Claude? A plain guide to the Claude apps, models, plans, API and Claude Code, plus Projects, Artifacts and connectors, checked October 2026. - [What Is MCP? Model Context Protocol Explained (2026)](https://claudekit.ai/guides/what-is-mcp/): What the Model Context Protocol is, how an MCP server works, hosts vs clients vs servers, tools, transports, the 2026-07-28 spec and security basics. ## Skills - [All skills](https://claudekit.ai/skills/): Browse Claude Code and Claude.ai Skills by category with install commands, source repos, licenses and GitHub stars. Find a skill and add it in minutes. - [claude-api Skill: Claude API and SDK Reference for Agents](https://claudekit.ai/skills/claude-api/): Anthropic's claude-api skill gives Claude current API and SDK reference: model IDs, tool use, caching, streaming and migrations. Install and usage tips. - [DOCX Skill for Claude: Create and Edit Word Documents](https://claudekit.ai/skills/docx/): Anthropic's docx skill lets Claude create, read and edit Word files: templates, tables of contents, tracked changes and comments. Install and example prompts. - [algorithmic-art Skill: Generative Art with p5.js](https://claudekit.ai/skills/algorithmic-art/): Anthropic's algorithmic-art skill has Claude create generative p5.js art with seeded randomness, flow fields and particles, plus an interactive viewer. Usage. - [canvas-design Skill: Posters and Visual Art with Claude](https://claudekit.ai/skills/canvas-design/): Anthropic's canvas-design skill has Claude write a design philosophy, then express it as an original poster or artwork in PNG or PDF. How it works and install. - [doc-coauthoring Skill: Write Specs and Docs with Claude](https://claudekit.ai/skills/doc-coauthoring/): Anthropic's doc-coauthoring skill guides you through context gathering, section-by-section drafting and fresh-reader testing for specs, PRDs and proposals. - [Cloudflare Skills: Workers, Agents SDK and More](https://claudekit.ai/skills/cloudflare-skills/): Cloudflare's official skills teach Claude Workers, Durable Objects, the Agents SDK, Wrangler, Sandbox and web performance, and bundle the Cloudflare MCP server. - [CCPM Skill: Spec-Driven Project Management for Claude](https://claudekit.ai/skills/ccpm/): CCPM is an agent skill that turns ideas into PRDs, epics and GitHub issues, then runs parallel agents in worktrees with a full audit trail. Install, workflow. - [Awesome Claude Skills by Composio: Curated Skill List](https://claudekit.ai/skills/awesome-claude-skills/): ComposioHQ's awesome-claude-skills curates 1,000+ Claude skills and plugins by category, plus a connect-apps plugin for 1,000+ app integrations. How to use it. - [Expo Skills: Official React Native Skills for Claude](https://claudekit.ai/skills/expo-skills/): Expo's official skills teach Claude to build, upgrade, deploy and debug Expo apps: Router, native UI, EAS Build, Update and Workflows. Install and usage tips. - [dev-browser Skill: Let Claude Drive Chrome with Scripts](https://claudekit.ai/skills/dev-browser/): dev-browser lets Claude control Chrome through short Puppeteer scripts with persistent tabs and compact accessibility snapshots. Install the CLI and its skill. - [frontend-design Skill: Distinctive UI from Claude](https://claudekit.ai/skills/frontend-design/): Anthropic's frontend-design skill steers Claude toward intentional, non-templated UI: aesthetic direction, typography and self-critique. Install and usage. - [Hugging Face Skills: ML Workflows for Claude Code](https://claudekit.ai/skills/hugging-face-skills/): Hugging Face's official skills teach Claude the hf CLI, datasets, model training, evaluation, Gradio and SageMaker deployment. Install steps, uses and caveats. - [internal-comms Skill: Status Reports and Updates](https://claudekit.ai/skills/internal-comms/): Anthropic's internal-comms skill gives Claude formats for 3P updates, newsletters, FAQs, status reports, leadership updates and incident reports. How to use. - [PPTX Skill for Claude: Create and Edit Slide Decks](https://claudekit.ai/skills/pptx/): Anthropic's pptx skill lets Claude build, read and edit PowerPoint decks and templates, with design guidance and a required QA pass. Install and prompts. - [PDF Skill for Claude: Read, Merge, Fill and Create PDFs](https://claudekit.ai/skills/pdf/): Anthropic's pdf skill lets Claude extract text and tables, merge, split, fill forms, watermark and create PDFs. What it does, install and example prompts. - [mcp-builder Skill: Build MCP Servers with Claude](https://claudekit.ai/skills/mcp-builder/): Anthropic's mcp-builder skill guides Claude through building quality MCP servers in Python (FastMCP) or TypeScript, from research to evals. Install and usage. - [react-best-practices Skill: Vercel's React Rules](https://claudekit.ai/skills/react-best-practices/): Vercel's react-best-practices skill gives Claude 40+ prioritized React and Next.js performance rules, from waterfalls to bundle size. Install, uses, limits. - [Remotion Skills: Make Videos in React with Claude](https://claudekit.ai/skills/remotion-skills/): Remotion's official agent skills teach Claude to create, preview and render React videos: compositions, captions, maps, Studio and upgrades. Install and usage. - [Scientific Agent Skills: 177 Research Skills for Claude](https://claudekit.ai/skills/scientific-agent-skills/): K-Dense's Scientific Agent Skills gives Claude 177 skills for bioinformatics, chemistry, clinical research, physics, ML and lab automation. Install and caveats. - [Sentry Skills: Engineering Workflows from Sentry](https://claudekit.ai/skills/sentry-skills/): getsentry/skills packages Sentry's internal agent skills: code review, find-bugs, security review, PR writing, commit rules and skill scanning. Install, tips. - [Supabase Agent Skills: Supabase and Postgres for Claude](https://claudekit.ai/skills/supabase-agent-skills/): Supabase's official agent skills cover every Supabase product plus Postgres performance best practices, so Claude writes correct auth, RLS and SQL. Install. - [skill-creator: Anthropic's Skill for Building Skills](https://claudekit.ai/skills/skill-creator/): skill-creator is Anthropic's official skill for writing, editing and testing Claude skills, with evals and description tuning. Install, usage and tips. - [SuperClaude Framework: 30 Commands for Claude Code](https://claudekit.ai/skills/superclaude-framework/): SuperClaude is a configuration framework that adds 30 /sc: slash commands for research, brainstorming, implementation, testing and PM to Claude Code. Install. - [Superpowers: Agentic Skills Framework for Claude Code](https://claudekit.ai/skills/superpowers/): Superpowers by obra is an open-source skills library that adds brainstorming, planning, TDD, systematic debugging and review workflows to Claude Code. - [Trail of Bits Skills: Security Auditing for Claude Code](https://claudekit.ai/skills/trail-of-bits-skills/): Trail of Bits' skills marketplace adds 46 security plugins to Claude Code: code auditing, static analysis, smart contracts, fuzzing and verification. Setup. - [theme-factory Skill: Consistent Themes for Claude Output](https://claudekit.ai/skills/theme-factory/): Anthropic's theme-factory skill applies one of 10 preset color and font themes, or a custom one, to slides, docs, reports and landing pages. How to use it. - [UI UX Pro Max Skill: Design Intelligence for Claude](https://claudekit.ai/skills/ui-ux-pro-max/): UI UX Pro Max gives Claude a searchable design database and generator: 192 product rules, 79 styles, 192 palettes and 74 font pairings. Install, usage, caveats. - [XLSX Skill for Claude: Build and Clean Spreadsheets](https://claudekit.ai/skills/xlsx/): Anthropic's xlsx skill lets Claude create, edit and clean spreadsheets with working formulas, formatting and charts. Install command, prompts and tips. - [webapp-testing Skill: Test Web Apps with Playwright](https://claudekit.ai/skills/webapp-testing/): Anthropic's webapp-testing skill lets Claude test local web apps with Playwright: verify UI, debug behavior, capture screenshots and read browser logs. - [web-artifacts-builder Skill: React Artifacts for Claude](https://claudekit.ai/skills/web-artifacts-builder/): Anthropic's web-artifacts-builder skill has Claude build multi-component React, Tailwind and shadcn/ui apps, then bundle them into one HTML artifact. Usage. ## Prompts - [All prompts](https://claudekit.ai/prompts/): Copy-ready Claude prompts organised by category and use case, tested across Claude models. Practical templates for coding, writing, research and agents. - [API Documentation Prompt for Claude: Docs From Code](https://claudekit.ai/prompts/api-docs-prompt/): A copy-paste API documentation prompt for Claude that turns route handlers or source code into accurate endpoint docs with params, errors and examples. - [Bug Triage Prompt: Classify, Prioritize and Find Root Cause](https://claudekit.ai/prompts/bug-triage-prompt/): A bug triage prompt for Claude that classifies a report, rates severity, ranks root-cause hypotheses with evidence and lists the next diagnostic steps to run. - [Log Analysis Prompt for Claude: Find the Root Cause](https://claudekit.ai/prompts/log-analysis-prompt/): A copy-paste log analysis prompt for Claude that turns production error logs into a timeline, ranked root-cause hypotheses and the next checks to confirm one. - [Commit Message Prompt for Claude: Conventional Commits](https://claudekit.ai/prompts/commit-message-prompt/): A copy-paste commit message prompt for Claude that turns a staged diff into a Conventional Commits message with type, scope, body and breaking-change footer. - [Code Review Prompt for Claude: Severity-Ranked Findings](https://claudekit.ai/prompts/code-review-prompt/): A copy-paste code review prompt for Claude that returns severity-ranked findings with evidence, fixes and open questions. For claude.ai, Claude Code or API. - [Refactor Plan Prompt: Safe, Step-by-Step Refactoring](https://claudekit.ai/prompts/refactor-plan-prompt/): A refactor plan prompt that makes Claude map current behavior, list risks and propose small, test-backed steps before touching code. Copy, fill in and run. - [PRD Writer Prompt: Turn Rough Notes into a Clear PRD](https://claudekit.ai/prompts/prd-writer-prompt/): A PRD writer prompt for Claude that turns rough notes into a product requirements doc with goals, non-goals, user stories and acceptance criteria. - [Blog Outline Prompt: Search-Ready Outlines with Claude](https://claudekit.ai/prompts/blog-outline-prompt/): A blog outline prompt for Claude that builds a search-ready article outline from your keyword, audience and sources, with H2/H3 structure, angle and FAQ ideas. - [Meeting Notes to Action Items Prompt for Claude](https://claudekit.ai/prompts/meeting-notes-to-action-items-prompt/): Turn messy meeting notes or transcripts into decisions, owners, deadlines and open questions with this Claude prompt. Nothing is invented; gaps are flagged. - [SQL Explainer Prompt: Understand Any Query Step by Step](https://claudekit.ai/prompts/sql-explainer-prompt/): An SQL explainer prompt that has Claude walk through a query clause by clause, describe the result set, flag correctness and performance risks, and fix them. - [Unit Test Generator Prompt: Meaningful Tests with Claude](https://claudekit.ai/prompts/unit-test-generator-prompt/): A unit test generator prompt that makes Claude plan cases first, cover edge cases and errors, follow your framework's style and test behavior, not internals. ## Tools - [All tools](https://claudekit.ai/tools/): Directory of tools built for Claude: MCP servers, CLIs, plugins, apps, extensions and starter kits, with pricing, repos and honest notes on each one. - [Agentkit.best (formerly Claudekit.cc): Claude Code Kit Review](https://claudekit.ai/tools/agentkit-best/): Claudekit.cc changed to Agentkit.best: a paid kit of skills, subagents and slash-command workflows for Claude Code and other agents. What it includes, pros and cons. - [Claude Code: Anthropic's Agentic Coding CLI](https://claudekit.ai/tools/claude-code/): Claude Code is Anthropic's agentic coding tool for the terminal, IDE, desktop and web. Install commands, use cases, pros and cons, and where to start. - [Apify MCP Server: Run Web Scrapers from Claude](https://claudekit.ai/tools/apify-mcp-server/): Apify's official MCP server lets Claude find and run Actors from Apify Store to scrape sites, maps and social media. Claude Code plugin, OAuth, caveats. - [Agent SDK Dev Plugin: Scaffold and Verify Claude SDK Apps](https://claudekit.ai/tools/agent-sdk-dev/): agent-sdk-dev is Anthropic's Claude Code plugin to scaffold Claude Agent SDK apps in Python or TypeScript with /new-sdk-app and check them with verifier agents. - [Atlassian MCP Server: Jira and Confluence in Claude](https://claudekit.ai/tools/atlassian-mcp-server/): Atlassian's official remote MCP server connects Claude to Jira, Confluence, JSM, Bitbucket, Compass and Loom. Claude Code setup, admin controls, alternatives. - [AWS MCP Servers: Official AWS Tools for Claude Code](https://claudekit.ai/tools/aws-mcp-servers/): awslabs/mcp is AWS's open-source suite of MCP servers for docs, APIs, IaC, pricing, databases and more. Claude Code commands, picks to start with, caveats. - [Azure DevOps MCP Server: Work Items, Repos and Pipelines](https://claudekit.ai/tools/azure-devops-mcp-server/): Microsoft's Azure DevOps MCP server lets Claude read work items, repos, builds, wikis and test plans. Claude Code command, remote vs local server, caveats. - [CC Safety Net: Block Destructive Commands in Claude Code](https://claudekit.ai/tools/cc-safety-net/): CC Safety Net is a Claude Code plugin hook that blocks destructive commands like git reset --hard and rm -rf, plus access to secrets, before a tool call runs. - [Azure MCP Server: Microsoft's MCP Server for Azure Services](https://claudekit.ai/tools/azure-mcp-server/): Microsoft's Azure MCP Server gives Claude tools for Storage, Cosmos DB, Key Vault, AKS, Monitor and more. Claude Code plugin, npx setup, permissions. - [Beads Plugin: A Dependency-Aware Issue Tracker for Claude](https://claudekit.ai/tools/beads/): Beads is a dependency-aware issue tracker for coding agents. Its Claude Code plugin adds /beads commands, a task agent and hooks to find and close ready work. - [Brave Search MCP Server: Web Search for Claude](https://claudekit.ai/tools/brave-search-mcp-server/): Brave's official MCP server adds web, news, image, video, local and LLM-context search to Claude via the Brave Search API. Setup, tools, pricing and caveats. - [ccstatusline: Custom Status Line for Claude Code](https://claudekit.ai/tools/ccstatusline/): ccstatusline is a TUI-configured status line for Claude Code showing model, git branch, context use, session and weekly usage and costs. Setup and caveats. - [ccusage: Track Claude Code Token Usage and Cost](https://claudekit.ai/tools/ccusage/): ccusage reads local logs to report Claude Code token usage and estimated cost by day, week, month or session. Commands, use cases, pros and cons. - [Chrome DevTools MCP: Debug Pages with Claude](https://claudekit.ai/tools/chrome-devtools-mcp/): Chrome DevTools MCP gives Claude a live Chrome with DevTools: performance traces, console and network inspection. Claude Code install, use cases, pros and cons. - [Claude Code Action: Claude in GitHub PRs and Issues](https://claudekit.ai/tools/claude-code-action/): Claude Code Action runs Claude Code in GitHub Actions to answer @claude mentions, review PRs and implement changes. Setup, workflow example, pros and cons. - [Claude Code Router: Route Agents to Any Model](https://claudekit.ai/tools/claude-code-router/): Claude Code Router (CCR) is a local gateway routing Claude Code and other agents to the providers you choose, with fallbacks and logs. Setup, uses, caveats. - [Claude Code Templates: Agents, Commands, Hooks, MCPs](https://claudekit.ai/tools/claude-code-templates/): Claude Code Templates (aitmpl.com) is an npx CLI and catalog to install agents, commands, hooks, settings, MCPs and skills, plus analytics. Uses, caveats. - [Claude Code Usage Monitor: Live Limits in Terminal](https://claudekit.ai/tools/claude-code-usage-monitor/): Claude Code Usage Monitor (claude-monitor) shows live token use, burn rate, reset timers and limit forecasts for your plan in a terminal UI. Install, tips. - [Claude HUD: Live Context and Usage Status Line Plugin](https://claudekit.ai/tools/claude-hud/): Claude HUD is a Claude Code plugin that adds a live status line with context usage, rate limits, git branch, active tools, running subagents and todo progress. - [Claude Code Setup Plugin: Get Automation Recommendations](https://claudekit.ai/tools/claude-code-setup/): claude-code-setup is Anthropic's read-only plugin that scans your codebase and recommends hooks, skills, MCP servers, subagents and slash commands to set up. - [CLAUDE.md Management Plugin: Audit and Update Project Memory](https://claudekit.ai/tools/claude-md-management/): claude-md-management is Anthropic's plugin to audit CLAUDE.md files against your codebase and save session learnings with /revise-claude-md. Install and usage. - [Claude-Mem: Persistent Memory Plugin for Claude Code](https://claudekit.ai/tools/claude-mem/): Claude-Mem captures what Claude does in each session, compresses it into searchable observations and injects relevant context into later sessions. - [Claude Plugins Official: Anthropic's Plugin Directory](https://claudekit.ai/tools/claude-plugins-official/): claude-plugins-official is Anthropic's curated Claude Code marketplace: 300+ internal and partner plugins for MCP, skills, LSPs and workflows. How to install. - [Claude Squad: Run Many Claude Code Agents in tmux](https://claudekit.ai/tools/claude-squad/): Claude Squad is a terminal app managing multiple Claude Code, Codex or Gemini sessions, each in its own git worktree via tmux. Install, workflow and caveats. - [Code Review Plugin: Multi-Agent PR Review for Claude Code](https://claudekit.ai/tools/code-review/): Anthropic's code-review plugin runs parallel review agents on a pull request, scores each issue for confidence and posts only findings scoring 80 or higher. - [Commit Commands Plugin: /commit and /commit-push-pr](https://claudekit.ai/tools/commit-commands/): commit-commands is Anthropic's Claude Code plugin with /commit, /commit-push-pr and /clean_gone for git commits, pull requests and stale branch cleanup. - [Compound Engineering: Every's Plan-Build-Review Plugin](https://claudekit.ai/tools/compound-engineering/): Compound Engineering from Every is a 36-skill Claude Code plugin that runs a brainstorm, plan, build, review loop and saves learnings for the next change. - [Cloudflare MCP Servers: Docs, Browser, Containers](https://claudekit.ai/tools/cloudflare-mcp-server/): Cloudflare's remote MCP servers give Claude access to Cloudflare docs, Browser Run, sandbox containers and the full API. Which to pick, setup and caveats. - [container-use: Sandboxed Containers for Claude Code](https://claudekit.ai/tools/container-use/): Dagger's container-use gives each coding agent its own container and git branch via an MCP server, so parallel agents run safely. Install, workflow, cons. - [Context Mode: Keep Tool Output Out of Claude's Context](https://claudekit.ai/tools/context-mode/): Context Mode is a Claude Code plugin that runs tool output through sandboxed tools and a local search index so raw data stays out of your context window. - [DBHub MCP Server: Connect Claude to Your Database](https://claudekit.ai/tools/dbhub/): DBHub by Bytebase is an MCP server that connects Claude to Postgres, MySQL, SQL Server, Oracle, MariaDB or SQLite. Setup, safe use, pros and cons. - [Docker MCP Gateway: Run MCP Servers in Containers for Claude](https://claudekit.ai/tools/docker-mcp-gateway/): Docker's MCP Gateway runs MCP servers from the Docker MCP Catalog in isolated containers behind one endpoint. Profiles, secrets and Claude Code connect. - [Context7: Up-to-Date Library Docs for Claude](https://claudekit.ai/tools/context7/): Context7 by Upstash feeds Claude current, version-specific library documentation via MCP or a CLI skill. Setup for Claude Code, use cases, pros and cons. - [Exa MCP Server: AI-Native Web Search for Claude](https://claudekit.ai/tools/exa-mcp-server/): Exa's MCP server gives Claude web search, clean page fetching and multi-step research agents through a hosted endpoint or Claude plugin. Setup, tools, caveats. - [ECC (Everything Claude Code): Agents, Skills and Hooks Plugin](https://claudekit.ai/tools/ecc/): ECC, formerly everything-claude-code, is an MIT plugin with 71 agents, 311 skills, hooks, rules and AgentShield scanning for Claude Code. Install and caveats. - [Explanatory Output Style Plugin: Learn While Claude Codes](https://claudekit.ai/tools/explanatory-output-style/): Anthropic's explanatory-output-style plugin restores the old Explanatory style via a SessionStart hook, so Claude adds short Insight notes as it codes. - [Feature Dev Plugin: A 7-Phase Feature Workflow for Claude](https://claudekit.ai/tools/feature-dev/): feature-dev is Anthropic's Claude Code plugin for a guided 7-phase feature workflow with explorer, architect and reviewer agents. Install, phases, pros, cons. - [Figma MCP Server: Official Design-to-Code for Claude](https://claudekit.ai/tools/figma-mcp-server/): Figma's official remote MCP server gives Claude design context, variables and Code Connect data, plus canvas writes. Claude Code setup, use cases and limits. - [Filesystem MCP Server: Give Claude Desktop File Access](https://claudekit.ai/tools/filesystem-mcp-server/): The Filesystem MCP server lets Claude read, write and search files in folders you allow. Setup for Claude Desktop and Claude Code, use cases, pros and cons. - [Firecrawl MCP Server: Scrape and Crawl with Claude](https://claudekit.ai/tools/firecrawl-mcp-server/): Firecrawl's MCP server lets Claude search, scrape, crawl, map and interact with websites, returning clean Markdown or JSON. Hosted and npx setup, pros, cons. - [GitLab MCP Server: Issues, MRs and CI in Claude Code](https://claudekit.ai/tools/gitlab-mcp-server/): GitLab's built-in MCP server lets Claude read projects, issues, merge requests and CI pipelines on GitLab.com or self-managed. Claude Code setup, toolsets. - [Framelink MCP for Figma: Community Figma Server](https://claudekit.ai/tools/framelink-figma-mcp/): Framelink (figma-developer-mcp) feeds simplified Figma layout and styling data to Claude so it can one-shot designs. Setup with a token, use cases, pros, cons. - [GitHub MCP Server: Connect Claude to GitHub](https://claudekit.ai/tools/github-mcp-server/): GitHub's official MCP server lets Claude read repos, review pull requests and manage issues. Remote and Docker setup for Claude Code, use cases, pros and cons. - [Happy: Mobile and Desktop Client for Claude Code](https://claudekit.ai/tools/happy/): Happy is an open-source app and CLI that wraps Claude Code and Codex so you can continue sessions from your phone with end-to-end encryption. Install, uses. - [Grafana MCP Server: Dashboards, Metrics and Logs in Claude](https://claudekit.ai/tools/grafana-mcp-server/): Grafana's official MCP server lets Claude search dashboards, run PromQL and LogQL, and read alerts and incidents. Setup with uvx or Docker, read-only mode. - [Hookify: Create Claude Code Hooks from Plain Markdown Rules](https://claudekit.ai/tools/hookify/): Hookify is Anthropic's Claude Code plugin that turns plain-language requests into regex-based hook rules stored as Markdown files that warn on or block actions. - [Linear MCP: Manage Linear Issues from Claude Code](https://claudekit.ai/tools/linear-mcp/): Linear's official remote MCP server lets Claude find, create and update issues, projects and comments over OAuth. Claude Code setup, read-only mode, use cases. - [MCP Inspector: Test and Debug MCP Servers](https://claudekit.ai/tools/mcp-inspector/): MCP Inspector is the official tool for testing MCP servers, with web UI, CLI and terminal UI modes. How to run it, when to use it, and its pros and cons. - [Hugging Face MCP Server: Search the Hub from Claude](https://claudekit.ai/tools/hugging-face-mcp-server/): The official Hugging Face MCP server lets Claude search models, datasets, Spaces and papers, and call Gradio apps as tools. Claude Code setup and use cases. - [MCP Reference Servers: The Official modelcontextprotocol Repo](https://claudekit.ai/tools/mcp-reference-servers/): The official MCP reference servers repo: Everything, Fetch, Filesystem, Git, Memory, Sequential Thinking and Time, plus where archived servers moved. - [MongoDB MCP Server: Query MongoDB and Atlas with Claude](https://claudekit.ai/tools/mongodb-mcp-server/): MongoDB's official MCP server lets Claude query collections, inspect schemas and indexes, and manage Atlas clusters. Setup, read-only mode, use cases, caveats. - [Neon MCP Server: Manage Neon Postgres from Claude](https://claudekit.ai/tools/neon-mcp-server/): Neon's official MCP server lets Claude create projects and branches, run SQL and plan migrations on Neon Postgres. OAuth setup, read-only mode, pros and cons. - [Notion MCP: Connect Claude to Your Notion Workspace](https://claudekit.ai/tools/notion-mcp/): Notion's hosted MCP server lets Claude search, read and edit pages in Markdown over OAuth. Claude Code setup command, use cases, plan limits and caveats. - [Plannotator: Review and Annotate Claude Code Plans in a Browser](https://claudekit.ai/tools/plannotator/): Plannotator opens Claude Code plans, docs and diffs in a local browser UI so you can annotate them and send feedback straight back to the agent. Install, pros. - [Perplexity MCP Server: Web Search and Research for Claude](https://claudekit.ai/tools/perplexity-mcp-server/): Perplexity's official MCP server gives Claude web search, quick answers, deep research and reasoning via its API. Claude Code commands, costs and limits. - [Playwright MCP: Browser Automation for Claude](https://claudekit.ai/tools/playwright-mcp/): Microsoft's Playwright MCP server lets Claude drive a real browser through accessibility snapshots. Install for Claude Code, use cases, pros and cons. - [Plugin Dev: Anthropic's Toolkit for Building Claude Plugins](https://claudekit.ai/tools/plugin-dev/): plugin-dev is Anthropic's toolkit for building Claude Code plugins: seven skills on hooks, MCP, commands and agents, plus a guided create-plugin workflow. - [Postman MCP Server: Collections and API Specs in Claude](https://claudekit.ai/tools/postman-mcp-server/): Postman's official MCP server connects Claude to workspaces, collections, specs and environments. Minimal, Code and Full modes, Claude Code commands. - [PR Review Toolkit: Six Review Subagents for Claude Code](https://claudekit.ai/tools/pr-review-toolkit/): pr-review-toolkit adds six Anthropic review subagents to Claude Code for comments, tests, silent failures, type design, code quality and simplification. - [Ralph Loop Plugin: Run Claude Code in a Self-Repeating Loop](https://claudekit.ai/tools/ralph-loop/): ralph-loop is Anthropic's plugin for the Ralph Wiggum technique: a Stop hook re-feeds one prompt so Claude keeps iterating until a completion promise appears. - [Security Guidance Plugin: Security Review for Claude Code](https://claudekit.ai/tools/security-guidance/): security-guidance reviews Claude-generated code in three layers: pattern warnings on edits, an LLM diff review on Stop and an agentic review on git commit. - [Serena: Semantic Code Tools MCP for Claude Code](https://claudekit.ai/tools/serena/): Serena gives Claude IDE-grade, symbol-level code retrieval, editing and refactoring tools over MCP using language servers or JetBrains. Install, uses, caveats. - [Slack MCP Server and Plugin for Claude Code](https://claudekit.ai/tools/slack-mcp-server/): Slack's official plugin connects Claude Code to Slack's hosted MCP server plus nine skills and five commands. Install, use cases, admin limits and alternatives. - [Sentry MCP: Debug Production Errors with Claude](https://claudekit.ai/tools/sentry-mcp/): Sentry's MCP server lets Claude read issues, stack traces, traces and logs from Sentry. Remote and stdio setup, Claude Code plugin, use cases, pros and cons. - [Stripe MCP and Plugin: Build Payments with Claude](https://claudekit.ai/tools/stripe-mcp/): Stripe hosts a remote MCP server and an official Claude Code plugin with agent skills for current Stripe best practices. Install, use cases, pros and caveats. - [Supabase MCP Server: Manage Supabase from Claude](https://claudekit.ai/tools/supabase-mcp/): Supabase's official MCP server lets Claude manage tables, run SQL, fetch config and read docs for your projects. Hosted setup, read-only mode, risks, use cases. - [Terraform MCP Server: Terraform Registry Docs for Claude](https://claudekit.ai/tools/terraform-mcp-server/): HashiCorp's Terraform MCP server gives Claude live Terraform Registry docs and HCP Terraform workspace tools. Docker setup, Claude Code command, pros and cons. - [Tavily MCP: Web Search, Extract and Crawl for Claude](https://claudekit.ai/tools/tavily-mcp/): Tavily's official MCP server gives Claude real-time web search, page extraction, site mapping and crawling. Claude Code commands, OAuth or API key, caveats. - [TypeScript LSP Plugin: Code Intelligence in Claude Code](https://claudekit.ai/tools/typescript-lsp/): typescript-lsp is Anthropic's plugin that connects Claude Code to typescript-language-server for definitions, references and error checking in TS and JS files. - [Vercel MCP: Manage Vercel Projects and Deployments from Claude](https://claudekit.ai/tools/vercel-mcp/): Vercel MCP is Vercel's hosted OAuth server that lets Claude search docs, manage projects, read deployment logs and query Web Analytics. Claude Code setup. - [Zapier MCP: Connect Claude to 9,000+ Apps](https://claudekit.ai/tools/zapier-mcp/): Zapier MCP is a hosted server that lets Claude take actions in 9,000+ apps like Gmail, Slack and Sheets. Claude Code command, task billing, use cases, caveats. - [wshobson/agents: 94 Claude Code Plugins and Agents](https://claudekit.ai/tools/wshobson-agents/): wshobson/agents is a plugin marketplace with 94 plugins, 200+ subagents, 185 skills and 105 commands for Claude Code and other tools. Install and caveats. - [Awesome Claude Code Subagents by VoltAgent](https://claudekit.ai/tools/voltagent-subagents/): VoltAgent's awesome-claude-code-subagents collects 160+ Claude Code subagents in 10 categories, installable as plugins or as files. Setup, picks, caveats. ## News - [All news](https://claudekit.ai/news/): The latest Claude news: model releases, Claude Code updates, API changes, MCP ecosystem launches and community highlights, summarised with sources. - [Claudekit.cc Is Now Agentkit.best: What Changed and Where to Go](https://claudekit.ai/news/claudekit-cc-is-now-agentkit-best/): The Claude Code starter kit Claudekit.cc changed its name to Agentkit.best and moved from claudekit.cc to agentkit.best. What that means for existing users. - [Claude Code v2.1.309: Sandbox and Permission Fixes](https://claudekit.ai/news/claude-code-v2-1-309/): Claude Code v2.1.309 tightens sandbox and Bash permission checks, protects MCP config files, and changes how sed -i and claude ultrareview behave. - [Claude Models on Google Cloud (Anthropic Managed) Launches](https://claudekit.ai/news/claude-platform-release-notes-october-22-2026/): Anthropic launched Claude Models on Google Cloud, the Claude API run by Anthropic via your Google Cloud project, with IAM access and Marketplace billing. - [Claude API Version 2026-10-21: New SDKs and Apache 2.0](https://claudekit.ai/news/claude-platform-release-notes-october-21-2026/): Anthropic released API version 2026-10-21 with new default SDK and ant CLI versions, Apache 2.0 licensing, and enforcement status fields for user profiles. ## Compare - [All compare](https://claudekit.ai/compare/): Side-by-side comparisons of Claude models, kits, MCP servers and AI coding tools, so you can pick the right option for your workflow with confidence. - [Claude Pro vs Max (2026): Which Plan Is Worth It?](https://claudekit.ai/compare/claude-pro-vs-max/): Claude Pro vs Max compared: prices, usage multipliers, Claude Code limits, included API credits and a simple test to decide if Pro is worth it or Max pays off. - [Agentkit.best (formerly Claudekit.cc) vs DIY and Free Kits](https://claudekit.ai/compare/agentkit-vs-diy-claude-kit/): Agentkit.best vs a DIY Claude kit, Superpowers, carlrannaberg's claudekit and official plugins: what each includes, what it costs you, and which one fits your team. - [Claude Code vs Codex: Which Coding Agent Fits You?](https://claudekit.ai/compare/claude-code-vs-codex/): Claude Code vs OpenAI Codex compared fairly: CLI, IDE and cloud surfaces, safety controls, AGENTS.md vs CLAUDE.md, extensibility, CI, and when to pick each one. - [Claude Code vs Cursor: Which AI Coding Tool Fits You?](https://claudekit.ai/compare/claude-code-vs-cursor/): Claude Code vs Cursor compared fairly: workflow, models, extensibility, automation and team setup, with clear advice on when to pick each and how to use both. - [Claude Code vs Gemini CLI (2026): Features and Limits](https://claudekit.ai/compare/claude-code-vs-gemini-cli/): Gemini CLI vs Claude Code compared: pricing and free quotas, install, context files, extensibility, safety and automation, with advice on which to use when. - [Claude Code vs Windsurf (Now Devin Desktop) in 2026](https://claudekit.ai/compare/claude-code-vs-windsurf/): Claude Code vs Windsurf, now Devin Desktop: what changed in 2026, how the agents, models, rules, MCP, hooks and CLI compare, and which one fits how you work. - [Claude Code vs GitHub Copilot: Which to Use in 2026?](https://claudekit.ai/compare/claude-code-vs-github-copilot/): Claude Code vs GitHub Copilot compared fairly: CLI and cloud agents, IDE support, models, instructions, skills, MCP, hooks, CI and when to pick each one. - [Claude vs ChatGPT for Coding: A Fair 2026 Comparison](https://claudekit.ai/compare/claude-vs-chatgpt-for-coding/): Claude vs ChatGPT for coding: chat apps, coding agents (Claude Code vs Codex), extensibility and workflow fit, plus a checklist to test both on your own repo. - [Claude vs ChatGPT (2026): Which AI Assistant Fits You?](https://claudekit.ai/compare/claude-vs-chatgpt/): Claude vs ChatGPT for everyday use: writing, research, files, memory, privacy and plan prices compared side by side, checked against official pages in 2026. - [Claude vs ChatGPT vs Gemini (2026): Which AI to Pick?](https://claudekit.ai/compare/claude-vs-chatgpt-vs-gemini/): Claude vs ChatGPT vs Gemini side by side: plan prices, free tiers, coding agents, ecosystem fit and who each assistant suits best, with prices checked in 2026. - [Claude vs Gemini (2026): Plans, Models and Coding](https://claudekit.ai/compare/claude-vs-gemini/): Claude vs Gemini compared fairly: plans and prices, models, API costs, coding agents, ecosystem fit and privacy, plus clear advice on which one suits whom. ## Recipes - [All recipes](https://claudekit.ai/recipes/): Claude Code kits we actually ran: what each one gets you, how long setup takes, the test level it reached, the Claude Code version and the date we tested it. - [Safe Mode: Block Destructive Commands in Claude Code](https://claudekit.ai/recipes/safe-mode/): A free Claude Code hook kit that denies rm -rf on broad paths and curl | sh, and asks before force-pushes, hard resets and DROP TABLE. It fails closed. - [Token Diet: Audit What Claude Code Loads Every Session](https://claudekit.ai/recipes/token-diet/): A free Claude Code kit that lists every CLAUDE.md, import, always-on rule and MCP server loaded at startup, flags files over 200 lines and suggests trims. - [PR Review: Review Your Branch Diff with Claude Code](https://claudekit.ai/recipes/pr-review/): A free Claude Code kit that reviews your branch against its base with an eight-point checklist and writes REVIEW.md with path:line findings. Works offline. - [Usage Meter: See Your Claude Code Limits in the Status Line](https://claudekit.ai/recipes/usage-meter/): A free Claude Code kit that puts the model, context use and your 5-hour and weekly plan usage in the status line. One setup command, no tokens used. - [Release Notes: Draft a Changelog from Git with Claude Code](https://claudekit.ai/recipes/release-notes/): A free Claude Code kit that turns git log between two refs into release notes grouped by Conventional Commit type, breaking changes first. Nothing is published. ## Free generators - [All generators](https://claudekit.ai/generators/): Free, private tools for Claude: build a CLAUDE.md, a valid SKILL.md and MCP configs, or estimate API costs in your browser. Nothing you type leaves your device. - [CLAUDE.md Generator](https://claudekit.ai/generators/claude-md/): Free CLAUDE.md generator: fill in your stack, commands, code style and rules, preview the file live, then copy or download it. Runs in your browser. - [SKILL.md Generator](https://claudekit.ai/generators/skill-md/): Build a valid SKILL.md for Claude Code or Agent Skills: name checked against the spec, description, when-to-use, instructions and allowed-tools. Free. - [MCP Config Generator](https://claudekit.ai/generators/mcp-config/): Pick MCP servers and get claude mcp add commands, a .mcp.json project file or claude_desktop_config.json, with env placeholders instead of secrets. - [Claude API Cost Calculator](https://claudekit.ai/generators/api-cost/): Estimate Claude API costs per request, day and month with caching and batch, or compare your Claude Code usage with Pro, Max and Team plan prices. ## Kits - [All kits](https://claudekit.ai/kits/): focused Claude Code plugins from the Claudekit workshop - [Kiln Guard](https://claudekit.ai/kits/kiln-guard/) ## JSON API - [API index](https://claudekit.ai/api/index.json): read-only JSON exports of the directory, rebuilt on every deploy - [tools.json](https://claudekit.ai/api/tools.json): Every tool in the Claudekit directory: MCP servers, CLIs, plugins, apps, extensions and kits. - [skills.json](https://claudekit.ai/api/skills.json): Claude Code and Claude.ai Skills listed on Claudekit, with category and tags. - [guides.json](https://claudekit.ai/api/guides.json): Claudekit guides and tutorials for Claude Code, the Claude API, MCP and agents. - [mcp.json](https://claudekit.ai/api/mcp.json): MCP servers from the Claudekit tools directory, grouped by area. - [recipes.json](https://claudekit.ai/api/recipes.json): Tested Claude Code kits with the outcome, the test level reached, the Claude Code version, the test date and the zip download. ## Optional - [RSS feed](https://claudekit.ai/rss.xml) - [Sitemap](https://claudekit.ai/sitemap-index.xml)