Claude Code

Claude Code is Anthropic's agentic coding tool that runs in your terminal. It connects to AgentXchain via the local_cli adapter, running claude as a subprocess for each governed turn.

Which adapter?

local_cli — AgentXchain spawns claude as a subprocess, pipes the governed prompt via stdin, and reads the turn result from the staged output.

Prerequisites

• Claude Code installed and available on your PATH (claude --version)
• agentxchain CLI installed (npm install -g agentxchain)
• An ANTHROPIC_API_KEY set in your environment (Claude Code uses this for model access)

Configuration

Add a runtime to your agentxchain.json:

{
  "runtimes": {
    "claude-dev": {
      "type": "local_cli",
      "command": ["claude", "--print", "--dangerously-skip-permissions"],
      "cwd": ".",
      "prompt_transport": "stdin"
    }
  },
  "roles": {
    "dev": {
      "runtime": "claude-dev",
      "mandate": "Implement features and fix bugs",
      "authority": "proposed"
    }
  }
}

Key fields

Field	Value	Why
command	["claude", "--print", "--dangerously-skip-permissions"]	--print outputs to stdout (non-interactive). --dangerously-skip-permissions lets Claude write files without confirmation prompts.
prompt_transport	"stdin"	The governed prompt is piped to Claude Code's stdin.
cwd	"."	Run in the project root so Claude Code sees your repo.

Verify the connection

agentxchain connector check

This probes that the claude binary exists on your PATH. If it fails, check your Claude Code installation.

Minimal working example

mkdir my-project && cd my-project
agentxchain init --governed --template cli-tool --goal "Build a markdown linter" -y
git init && git add -A && git commit -m "initial scaffold"
agentxchain run

The governed run will dispatch turns to Claude Code via subprocess. Each turn receives the full dispatch bundle (prompt, context, assignment) via stdin.

Gotchas

• --dangerously-skip-permissions is required for non-interactive governed runs. Without it, Claude Code will prompt for file-write confirmation and the subprocess will hang.
• --print is required to get stdout output instead of the interactive TUI.
• Token budgets: Claude Code manages its own context window internally. AgentXchain's budget.max_tokens_per_turn controls the prompt size sent to Claude Code, not Claude Code's internal context management.
• Long-running turns: Claude Code may take several minutes for complex tasks. Set timeouts.turn_timeout_ms appropriately (default is 300000ms / 5 minutes).