Claude Local

The claude_local adapter runs Anthropic's Claude Code CLI locally. It supports session persistence, skills injection, and structured output parsing.

Prerequisites

• Claude Code CLI installed (claude command available)
• ANTHROPIC_API_KEY set in the environment or agent config

Configuration Fields

Field	Type	Required	Description
cwd	string	Yes	Working directory for the agent process (absolute path; created automatically if missing when permissions allow)
model	string	No	Claude model to use (e.g. claude-opus-4-6)
instructionsFilePath	string	No	Absolute path to the bundle entry file Baton points Claude at
promptTemplate	string	No	Prompt used for all runs
env	object	No	Environment variables (supports secret refs)
timeoutSec	number	No	Process timeout (0 = no timeout)
graceSec	number	No	Grace period before force-kill
maxTurnsPerRun	number	No	Max agentic turns per heartbeat
dangerouslySkipPermissions	boolean	No	Skip permission prompts (dev only)

Prompt Templates

Templates support {{variable}} substitution:

Variable	Value
{{agentId}}	Agent's ID
{{companyId}}	Company ID
{{runId}}	Current run ID
{{agent.name}}	Agent's name
{{company.name}}	Company name

Session Persistence

The adapter persists Claude Code session IDs between heartbeats. On the next wake, it resumes the existing conversation so the agent retains full context.

Session resume is cwd-aware: if the agent's working directory changed since the last run, a fresh session starts instead.

If resume fails with an unknown session error, the adapter automatically retries with a fresh session.

Instructions And Project Context

Claude local supports two prompt layers from Baton:

• the agent's instructions bundle entry file via instructionsFilePath
• composed project instructions generated from project conventions and governance reminders

This lets you keep role-specific instructions in the bundle while injecting project context separately.

Skills Injection

The adapter creates a temporary directory with symlinks to Baton skills and passes it via --add-dir. This makes skills discoverable without polluting the agent's working directory.

Environment Test

Use the "Test Environment" button in the UI to validate the adapter config. It checks:

• Claude CLI is installed and accessible
• Working directory is absolute and available (auto-created if missing and permitted)
• API key/auth mode hints (ANTHROPIC_API_KEY vs subscription login)
• A live hello probe (claude --print - --output-format stream-json --verbose with prompt Respond with hello.) to verify CLI readiness