CW101reads asClaude Work 101The Independent Claude Ecosystem Reference

Everything in the Claude ecosystem, mapped and explained.

Models, products, Claude Code, Cowork, MCP, Skills, APIs, plans, courses and community tools — one sourced, versioned reference instead of twenty scattered entry points.

Entries: 84
Cited sources: 204
Sections: 8
Affiliation: Independent

Explain

What each thing is, what it is not, who can use it, and on which surface.

Connect

How products, models, protocols and features actually relate to one another.

Compare

Straight answers to the "which one of these do I want" questions.

Track

Release, rename, beta-to-GA, deprecation and retirement, with dates.

The map

The Claude ecosystem, as a stack

Anthropic ships these as separate products with separate docs. They are easier to hold in your head as layers — the surfaces you open, the things you configure, what you build on, the models underneath, what it costs, and the policy around all of it.

Open the full map →

Where you use Claude

What you configure

What you build on

What runs underneath

What it costs

What governs it

Change tracking

What changed recently

Renames, availability shifts and deprecations, recorded against the page they affect.

Full change log →

Decisions

The questions people actually ask

Claude vs Claude Code vs Cowork

Claude is for thinking with; Claude Code is for changing a codebase; Cowork is for producing a deliverable from your files and connected apps. If the output is a conversation, use Claude. If it is a commit, use Claude Code. If it is a document, deck or spreadsheet, use Cowork.

Agent Skills vs MCP

A Skill is knowledge — instructions and scripts Claude loads when the task calls for them. An MCP server is a connection — access to a tool or data source. If your problem is "Claude does not know our process", write a Skill. If it is "Claude cannot reach our system", stand up an MCP server.

Fable vs Opus vs Sonnet vs Haiku

Start with Opus 5. Move down to Sonnet 5 if it holds up on your evaluation — it is 60% cheaper and usually does. Use Haiku 4.5 for high-volume, latency-sensitive work that does not need a 1M-token window. Reach for Fable 5 only when a long-running agent is failing on capability, not on prompting.

Pro vs Max

Max unlocks nothing that Pro does not already have. You are buying 5x or 20x the usage, higher output limits, early feature access and priority traffic. If you are not hitting Pro's limits mid-task, you do not need Max yet.

All comparisons →

Routes through the reference

Start where you actually are

New to Claude

Understand what Claude actually is before choosing a plan or a surface.

Claude Code developer

Go from installing the CLI to running hooks, subagents and CI automation.

AI agent builder

The composable pieces of the agent stack and how they fit together.

Enterprise administrator

Rollout, controls, data handling and the policies you will be asked about.

API & platform engineer

Ship on the Developer Platform without re-reading the docs every week.

Educator

The AI Fluency framework and the Academy material built around it.

Why trust this

Every page states what it was checked against, and when

Every page records when it was last verified and what it was verified against. Community reports are labelled and never presented as settled fact.

Sources are graded in four tiers, from official Anthropic documentation down to community reports. Anything in the bottom tier is labelled as reported rather than confirmed — this reference would rather say “not documented” than guess.

Editorial policy How we source

CWork101 Weekly

Everything that changed in the Claude ecosystem this week — new models, renamed features, availability shifts and deprecation notices.

Not open yet. Follow the RSS feed or thechange log in the meantime.

Most-read entries

Model deprecations and retirements

Ongoing

Anthropic's model lifecycle — the four states a model moves through, the notice period, and the full record of what has been retired and what replaced it.

Models

Anthropic Academy

Anthropic's official learning site at academy.claude.com — courses, tutorials and product learning paths, free to take.

Academy

Claude

Anthropic's assistant, available as a web app, desktop app and mobile app, and the surface most people mean when they say "Claude".

Products

Claude Fable 5

Anthropic's most capable widely released model, aimed at long-running agents, with always-on adaptive thinking and the highest price of any generally available Claude model.

Models

CLAUDE.md

A markdown file in your project that Claude Code reads at the start of every session — the place for coding standards, architecture decisions and review checklists.

Claude Code

Messages API

The core Claude API endpoint — you send a list of messages and a model ID, you get a response, and every other platform feature is a parameter on top of it.

Platform