nearfi.
Field notes from a little way ahead Week 45 · 2 Nov 2026 · Still early
Agent Index › Coding › Claude Code
Coding · vertical · Standalone · live

Claude Code

A coding agent that reads your codebase, edits files and runs commands from the terminal or editor.

By Anthropic · launched 2025-02-24 · last checked 2026-11-01

At a glance
Autonomy
4/5
Multi-step on its own

Why 4: it reads a codebase, edits files, runs tests and can commit and push without step-by-step prompting, but you check the result of long tasks, and it does not run unprompted.

The findings

What it does. Claude Code searches and reads a codebase, edits files, writes and runs tests, uses command-line tools and can commit and push to GitHub. It began as a limited research preview in February 2025 and became generally available that May. Anthropic's newest model, Claude Opus 5.5 (22 September 2026), comes with a classifier that Anthropic says screens every action before it runs.

Where it falls short. It acts with whatever permissions it is given, so a mistaken command can be destructive, and its own safety claims come from Anthropic's tests rather than independent ones. Long tasks still need a person to check the result.

Our score
7.2/10
Read the review →

What it can do

codefilesmulti-agent

Price: Included with Claude Pro ($20 a month, or $17 billed annually), Max ($100), Ultra ($200), and Team and Enterprise seats; or pay-as-you-go through the API. · Where: unknown · Surfaces: CLI, IDE, app, web

Incidents

  • 2025-11-13 Anthropic reported that a group it assessed with high confidence to be Chinese state-sponsored had used Claude Code to do 80–90% of the work in an espionage campaign against about 30 targets, succeeding in a small number of cases; Anthropic banned the accounts as it identified them. Source

Closest fiction

Moon — Each copy wakes, does the job and reports back.

Related coding agents

History

  • 2026-11-01 Added to the index.

Sources

  1. Claude 3.7 Sonnet and Claude Code Anthropic, 2025-02-24
  2. Introducing Claude 4 Anthropic, 2025-05-22
  3. Introducing Claude Opus 5.5 Anthropic, 2026-09-22
  4. Disrupting the first reported AI-orchestrated cyber espionage campaign Anthropic, 2025-11-13
  5. Plans & Pricing Anthropic

← All agents in the index · Autonomy is rated on what the product does today, on a 1–5 scale. Every fact links to a source.