Claude Code

Claude Code — Anthropic's terminal-first agent, with IDE, web and GitHub Action surfaces. Claude Code started as a terminal harness and grew IDE extensions, a hosted web surface and a GitHub Action around the same agent loop. It is deliberately Anthropic-only: no model picker beyond Claude, which lets the loop be tuned tightly against one family's behaviour. The extensibility story — subagents, hooks, skills and MCP — is the most complete of the vendor-coupled harnesses. It is bundled with Pro and Max subscriptions, or metered against an API key including Bedrock and Vertex. Built by Anthropic. Founded 2025. Licensed Proprietary.

We track it in 1 comparison — Coding agents — so every claim below is a cell in a table you can open and check rather than an impression. Across those rosters it sits against 16 other tools, and what follows is where it visibly separates from them.

Where it wins.

• Opens PRs — Yes, which only 6 of 16 tools here manage.
• Subagents — Yes, which only 5 of 14 tools here manage.
• Background agents — Yes, which only 5 of 16 tools here manage.
• Hooks — Yes, which only 3 of 10 tools here manage.

Each of those is ranked against the whole roster on its category page, not against a hand-picked subset, so a first place here means first of everything we list.

Where it gives ground.

• Local models — No. Codex CLI records Yes.
• Licence — proprietary, 10th of 15. Codex CLI records Apache-2.0.

None of these disqualify it on their own. They are the fields to check against your own requirements before you commit, because they are the ones where a competitor genuinely does better.

Provenance. 23 of 26 tracked fields carry a value for Claude Code, and 13 of those cite a document you can open. Last verified 2026-01-15. Every figure keeps its own provenance — measured by us, claimed by the vendor, inferred, or community-reported — and we would rather print a dash than a guess.

Its nearest neighbour in our data is Aider. Claude Code is ahead on Opens PRs (Yes against No) and MCP (Yes against No). Aider takes Licence (Apache-2.0 against proprietary) and Local models (Yes against No). That pattern repeats across the rest of the roster — see Claude Code alternatives for the other rivals, each compared the same way.

Company

Anthropic

Founded

2025

Licence

Proprietary

Fields we track

23 of 26

Last verified

2026-01-15

The most complete extensibility surface of any harness here — subagents, hooks, skills and MCP all first-class — at the cost of being locked to one model vendor. If Anthropic's pricing or availability is a business risk for you, that lock is the whole argument against it.

Opens PRs

●Yes1st of 16

Vendor-claimedsource

Subagents

●Yes1st of 14

Vendor-claimedverified 2026-01-15source

Background agents

●Yes1st of 16

Vendor-claimedsource

Local models

○No11th of 16

Community-reported

Hooks

●Yes1st of 10

Vendor-claimedverified 2026-01-15source

Entry price

$20 /seat/mo13th of 16

Vendor-claimedverified 2026-01-15source

Permissions

allowlist + OS sandbox1st of 16

Vendor-claimedverified 2026-01-15source

BYOK

●Yes1st of 16

Inferred

Claude Code is the right call in these situations, each one drawn from a field we actually record:

• Terminal-native teams who want subagents and hooks without building them.
• Repos where an OS sandbox is a hard requirement for unattended runs.
• Anyone already paying for Max who wants the subscription to cover agent use.
• Opens PRs is your binding constraint. Claude Code records Yes, which only 6 of the 16 tools in the Coding agents roster do. We define that field as a first-class path to a pull request: a built-in command, a vendor-published GitHub App with its own identity, or a hosted runner.
• Subagents is your binding constraint. Claude Code records Yes, which only 5 of the 14 tools in the Coding agents roster do. We define that field as can the agent spawn child agents with their own context window and toolset, and collect their results? The main lever for keeping long tasks inside a context budget.
• Background agents is your binding constraint. Claude Code records Yes, which only 5 of the 16 tools in the Coding agents roster do.
• Hooks is your binding constraint. Claude Code records Yes, which only 3 of the 10 tools in the Coding agents roster do.

Reach for something else when any of the following is a requirement rather than a nice-to-have:

• Local models. Claude Code records No on the Coding agents table. Codex CLI records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Licence. Claude Code records proprietary, 10th of 15 in the Coding agents roster. Codex CLI records Apache-2.0 on the same field. If that is a hard requirement rather than a preference, start elsewhere.

We publish this block because a comparison that only lists what a tool is good at is marketing. Every figure above sits on the same page as its source, and the field definitions are on the category tables if you want to check how we measured them.

What we don't know. 3 of the 26 fields we track for Claude Code are still blank: GitHub stars, Terminal-Bench and Bench model. Those render as dashes rather than as zeroes or assumptions, because an empty cell and a bad cell are not the same thing and only one of them is honest. If you know any of these figures and can point at a document, tell us.