State of Claude Code 2026: What 2,500 Public Repos Reveal | Build This Now

Build This Now

Search⌘K<br>svg]:size-12"><br>Real Builds<br>Concrete builds shipped with Claude Code, real products, real code

Real BuildsState of Claude Code 2026: What 2,500 Public Repos RevealBuilding Isn't the Bottleneck AnymoreDistribution Is the New MoatWhy QA Is the Real Bottleneck in AI DevelopmentFirst Principles in the Age of 24-Hour MVPsThe Autonomy Curve: How Much Freedom Can You Give an AI Agent?Idea to SaaSGAN LoopSelf-Evolving HooksTrace to SkillDistribution AgentsAI Security AgentsAutonomous AI SwarmAI Email SequencesAI Cleans ItselfAgent Swarm OrchestrationBuild a Full App with Claude Code: Real ExamplesClaude Code for Non-Developers: Real ExamplesClaude Code for Freelancers: Ship 3x FasterA Security Update from Build This NowOwn Your Vercel Analytics: I Built a Drain-to-Postgres Pipeline

Get Build This Now

Copy for AIShare

State of Claude Code 2026: What 2,500 Public Repos Reveal<br>We analyzed 2,500 public repositories that use Claude Code. 85% ship a CLAUDE.md, but only 25% define a custom subagent. Here is how developers actually configure Claude Code in 2026: agents, skills, hooks, MCP, and how big CLAUDE.md files have grown.<br>Stop configuring. Start building.<br>SaaS builder templates with AI orchestration.

Get Build This Now

Published Jun 19, 202611 min readReal Builds hub<br>We analyzed 2,500 public repositories that use Claude Code. 85% ship a CLAUDE.md file, but only 25% define a single custom subagent. Most developers use Claude Code as a smarter assistant that follows written instructions. Far fewer have crossed into the agent system it was built for: subagents, skills, hooks, and MCP. That gap is the most interesting thing in the data.

Here is what 2,500 real .claude/ setups look like in 2026, and what the numbers say about how people actually work with Claude Code.

The headline: a CLAUDE.md, and usually nothing more

Of the public repositories we sampled, 84.9% had a CLAUDE.md file and 62.1% had a .claude/ directory of some kind. But the deeper features drop off fast. Only 24.6% defined a custom subagent, and just 13.3% used hooks.

A CLAUDE.md is a plain-text instruction file. It tells Claude Code your conventions, your stack, and your house rules. It is the easy first step, and almost everyone takes it. The agent system is the harder, more powerful step, and most people have not taken it yet.

That is the core finding: the Claude Code ecosystem in 2026 is wide and shallow. Lots of people have it installed and pointed at their repo. A minority have built a system on top of it.

The adoption ladder

Feature adoption falls off in a clear order. Here is the share of all 2,500 sampled repositories using each capability.

FeatureWhat it doesAdoptionCLAUDE.mdPlain-English project instructions84.9%.claude/ directoryAny structured config62.1%Any power featureAgents, skills, commands, hooks, or MCP53.9%.claude/settings.jsonPermissions and config41.0%SkillsReusable SKILL.md capabilities28.1%Custom slash commandsSaved prompts as /commands25.6%Custom subagentsSpecialized agents in .claude/agents24.6%Project .mcp.jsonModel Context Protocol servers17.0%HooksScripts that fire on tool events13.3%

The drop from "has a CLAUDE.md" (85%) to "uses any agent feature" (54%) to "defines a subagent" (25%) is the shape of the whole ecosystem. Each rung up the ladder loses roughly a third of the field.

If you only look at the repos that bothered to create a .claude/ directory, the picture is more committed: 45% use skills, 41% use slash commands, 40% define subagents, and 21% use hooks. The people who set up structured config are far more likely to go all the way. The split is between developers who treat Claude Code as autocomplete and developers who treat it as a platform.

CLAUDE.md files are getting big

A CLAUDE.md is not a one-liner anymore. The median file in our sample was 6.2 KB, which is roughly 100 to 150 lines of instructions. A third of them (33.8%) were over 10 KB.

The long tail is striking. The top 10% of CLAUDE.md files exceeded 24 KB, the top 1% passed 62 KB, and the single largest we found was 341 KB. That is one instruction file the length of a short book, which says something about how much context a serious Claude Code user ends up encoding.

This is the quiet trend underneath the headline. People who stick with Claude Code keep feeding the CLAUDE.md until it becomes the institutional memory of the project. For more on doing that well, see CLAUDE.md mastery and what Claude Skills are.

The power users go deep

Among the 614 repositories that defined at least one subagent, the median was 6 agents. The top 10% ran 25 or more. These are not toy setups. They are teams of specialized agents, each scoped to a job.

Skills go even further. Among repositories using skills, the median was 8 and the long tail ran into the hundreds. A small group of builders is clearly treating Claude Code as the runtime for an entire...