---
title: "Claude Code"
description: "Run Anthropic's Claude Code agent CLI in isolated Cloudflare Sandboxes with human approval gates."
---

> Documentation Index
> Fetch the complete documentation index at: https://tryshiba.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Code

Shiba supports [Claude Code](https://docs.anthropic.com/en/docs/claude-code) as a first-class coding agent harness. When selected, the orchestrator delegates the approved task to a Cloudflare Sandbox container running Anthropic's official `claude` CLI.

Claude Code is the default agent for tasks originated from Slack mentions and Telegram chats, providing high reasoning capability and fluid multi-turn code refactoring.

## Agent Overview

| Attribute | Specification |
| --- | --- |
| **Harness ID** | `claude-code` |
| **CLI Binary** | `claude` |
| **Pinned Version** | `2.1.277` (in Dockerfile) |
| **Default Model** | `anthropic/claude-sonnet-4-6` |
| **Supported Models** | `anthropic/claude-sonnet-4-6`, `anthropic/claude-3-7-sonnet-20250219`, `anthropic/claude-3-5-haiku-20241022` |
| **Credential Model** | AI Gateway BYOK (dummy key inside sandbox; real key injected at egress) |
| **Invocation** | `claude -p "<task>" --print --output-format stream-json --dangerously-skip-permissions` |

## How It Works

```
Developer Request
  └── CodingOrchestrator generates delegate_coding_task({ harness: "claude-code" })
      └── Human signs off on exact prompt & repository
          └── Ephemeral Cloudflare Sandbox boots
              ├── Clones repository via scoped git token
              ├── Executes: claude -p "<task>" --output-format stream-json
              ├── Streams newline-delimited JSON events back to Dashboard/Slack
              └── Produces unified diff & optional pull request
```

> **No Subscription Credentials**
>
> Anthropic terms forbid third-party platforms from proxying consumer Free/Pro/Max subscription tokens. Shiba strictly requires API key authentication configured in your account's Cloudflare AI Gateway.

## Configuration & Deployment

You can configure Claude Code globally across your deployment or select it on a per-task basis.

### 1. Configure the Provider Key in AI Gateway
Store your Anthropic API key in your Cloudflare AI Gateway under the provider ID `anthropic`. The Sandbox runtime provides a dummy key to the container environment, while Worker egress replaces it with the authentic key on calls to `api.anthropic.com`.

### 2. Deployment Defaults
Set your preferred harness and model defaults in `apps/backend/wrangler.jsonc` or via environment variables:

```bash
# Use Claude Code as the deployment-wide default harness
pnpm wrangler secret put AGENT_HARNESS --config apps/backend/wrangler.jsonc # enter "claude-code"

# Set the default Anthropic model
pnpm wrangler secret put CLAUDE_CODE_MODEL --config apps/backend/wrangler.jsonc # enter "anthropic/claude-sonnet-4-6"
```

### 3. Channel-Specific Overrides
Slack and Telegram can independently pin their agent harness:
- `SLACK_AGENT_HARNESS=claude-code`
- `TELEGRAM_AGENT_HARNESS=claude-code`

## Selecting Claude Code in a Task

When delegating from the API, dashboard, or chat triggers, specify `harness: "claude-code"`:

```json
{
  "repoUrl": "https://github.com/acme/backend",
  "task": "Migrate database connection pool to PgBouncer syntax",
  "baseBranch": "main",
  "harness": "claude-code",
  "codingModel": "anthropic/claude-sonnet-4-6"
}
```

## Event Streaming & Progress

Claude Code emits newline-delimited JSON envelopes via `--output-format stream-json`. The Shiba runtime parses each event in real time:
- Tool invocations (file reads, bash commands, edits) are extracted and displayed in the run transcript.
- Any envelope carrying `is_error: true` is treated as an immediate failure and surfaced honestly with the provider's exact error message.
- Clean completion triggers git status collection, index-to-add staging, and diff computation.

## Related Documentation

- [Coding Harnesses Overview](/docs/claude-code/)
- [Approval Gates](/docs/approval-gates/)
- [Security & Credential Boundaries](/docs/security/)

Source: https://tryshiba.dev/docs/agents/claude-code/index.mdx