claude

A configuration guide for using Claude Code, Anthropic’s command-line AI coding assistant, with Operator. It covers installation, authentication, settings, and optional communication between multiple agents.

In plain words
What is it for?
Use it when installing Claude Code, enabling it in Operator, signing in, or connecting it to Operator’s relay system for multi-agent work.
Why use it?
It explains how to make Claude Code available to Operator and how to pass the settings needed for agent coordination. This avoids guessing at installation and configuration steps.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/untra/operator/claude
Clone the repo
git clone --depth 1 https://github.com/untra/operator
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00009 $0.00399
Opus 5 $0.00005 $0.00199
Sonnet 5 $0.00002 $0.00080
Haiku 4.5 $0.00001 $0.00040

Measured 2d ago against content hash 65359531ca80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/getting-started/agents/claude.md · 63 lines

What it actually says

Claude Code is Anthropic's AI coding assistant agent, available as Claude Code for command-line development workflows.

Installation

Install Claude Code via npm:

npm install -g @anthropic-ai/claude-code

Or download directly from Anthropic.

Plans and Pricing

View the Claude pricing page

Configuration

See the full Claude agent configuration reference.

Add Claude to your Operator configuration:

# ~/.config/operator/config.toml

[agents.claude]
enabled = true
path = "claude"  # or full path to binary

Authentication

Claude Code requires an API key or Claude Pro subscription. Set up authentication:

claude auth login

Multi-agent relay

Agents launched by Operator can participate in the relay hub when the hub is running. As long as the delegator (or global config) has enabled relay MCP injection.

When relay is enabled for a delegator, Operator:

  1. Injects RELAY_HUB_SOCKET and RELAY_AGENT_NAME (the ticket ID, e.g. FEAT-042) into the session environment.
  2. Writes a per-session relay-mcp.json config and passes --mcp-config <path> to Claude Code, so the relay MCP server starts alongside the agent.

To enable relay for a delegator, set operator_relay = true in its launch_config. The global default is false (opt-in), so single-agent workflows stay lean unless relay is explicitly requested.

See Relay for the full architecture.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 63 lines · 9 tokens per session scan A 65359531ca80

Subscribe to this mod's changes

claude is an agent published in the GitHub repository untra/operator (36 stars, last pushed 4d ago), licensed MIT. It adds 9 tokens to every session and 399 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.