[DOCS] Branding guidelines should address third-party projects that wrap Claude Code CLI

Documentation Type

Missing documentation (feature not documented)

Documentation Location

https://platform.claude.com/docs/en/agent-sdk/overview (bottom of page, "Branding guidelines" section)

Section/Topic

Agent SDK overview > Branding guidelines

Current Documentation

Allowed: - "Claude Agent" (preferred for dropdown menus) - "Claude" (when within a menu already labeled "Agents") - "{YourAgentName} Powered by Claude" (if you have an existing agent name) Not permitted: - "Claude Code" or "Claude Code Agent" - Claude Code-branded ASCII art or visual elements that mimic Claude Code Your product should maintain its own branding and not appear to be Claude Code or any Anthropic product.

What's Wrong or Missing?

The current guidelines address naming and visual branding for Agent SDK-based products, but don't address a common scenario: third-party projects that wrap the Claude Code CLI binary itself (not the Agent SDK).

Projects exist (e.g., The Vibe Companion) that spawn the claude CLI binary as a subprocess, replicate its permission approval flow, display its tool calls, and present a web UI that functions as an alternative Claude Code frontend. These projects:

1. Don't use the Agent SDK -- they control the CLI binary directly
2. Don't call themselves "Claude Code" -- but functionally replicate the Claude Code experience
3. May use the user's Claude Code subscription authentication rather than an API key

The current guidelines don't clarify:

• Whether wrapping the CLI binary (as opposed to using the Agent SDK) is a supported use case
• Whether using the user's Claude Code subscription authentication (vs an API key) is permitted for third-party products
• Whether replicating the Claude Code tool-approval UX pattern (even with different branding) is acceptable

Suggested Improvement

Expand the branding guidelines to address these scenarios. Possible additions:

1. CLI wrapping: Clarify whether third-party products should use the Agent SDK (Python/TypeScript) rather than spawning the claude CLI binary. If CLI wrapping is not supported, state that explicitly.
2. Authentication: The Agent SDK overview already states "Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products." Reiterate this in the branding section or link to it, since projects wrapping the CLI may use the subscription auth by default.
3. UX patterns: Clarify whether replicating Claude Code's interactive UX (tool approval prompts, permission modes, slash commands) under different branding is acceptable.

Impact

Medium - Makes feature difficult to understand

Additional Context

The note about authentication is already present elsewhere on the same page:

Unless previously approved, Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products, including agents built on the Claude Agent SDK. Please use the API key authentication methods described in this document instead.

This is important context that developers wrapping the CLI might miss since it's in the "Set your API key" step, not in the branding section.