Remove experimental designation from Claude/Codex engines

[Copilot]

Claude and Codex engines labeled "experimental" despite production evidence (29 Claude workflows, 9 Codex workflows in active use). Label created unnecessary perception of instability and discouraged adoption.

Changes

• Banner replacement (lines 10-12): Removed "Experimental Engines" warning; replaced with neutral multi-engine support note stating all engines support same tools/triggers/safe-outputs
• Claude section (line 61): Removed "experimental" designation from description

Before/After

Before:

> [!NOTE]
> Experimental Engines
> Claude and Codex engines are available but marked as experimental...

After:

> [!NOTE]
> Multiple AI Engines Supported
> GitHub Agentic Workflows supports multiple AI engines: GitHub Copilot CLI (default), 
> Anthropic Claude, and OpenAI Codex. All engines support the same tools, triggers, 
> and safe outputs. Choose the engine that best fits your needs and API access.

Documentation-only change. No functional impact.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>[plan] Remove 'experimental' label from Claude/Codex engines documentation</issue_title>
<issue_description>## Context

As identified in discussion #12027 (Claude Code User Documentation Review), the "experimental" label on Claude and Codex engines creates unnecessary perception of instability, despite evidence of production viability (29 Claude workflows and 9 Codex workflows exist in the repository).

Current State

In docs/src/content/docs/reference/engines.md:12, there is a banner stating:

"Claude and Codex engines are available but marked as experimental. They are not documented here but can still be used by setting engine: claude or engine: codex in your workflow frontmatter. For production workflows, we recommend using the GitHub Copilot CLI engine."

Problem

• Creates perception that Claude/Codex are unstable or risky
• Discourages production use despite evidence of stability
• States "not documented here" which is confusing (they ARE documented in the same file)
• Contradicts repository evidence (29 Claude workflows in active use)

Objective

Replace the "experimental" warning with a neutral, welcoming note about multi-engine support.

Proposed Solution

Replace the current experimental banner with:

> [!NOTE]
> Multiple AI Engines Supported
> GitHub Agentic Workflows supports multiple AI engines: GitHub Copilot CLI (default), Anthropic Claude, and OpenAI Codex. All engines support the same tools, triggers, and safe outputs. Choose the engine that best fits your needs and API access.

Files to Modify

• docs/src/content/docs/reference/engines.md (line 12 area)

Acceptance Criteria

• Remove "experimental" language from engines.md
• Replace with neutral multi-engine note
• Verify documentation renders correctly
• No changes to actual engine functionality (docs-only change)

References

• Discussion 🔍 Claude Code User Documentation Review - January 27, 2026 #12027 - Priority 1 recommendation
• Evidence: 29 Claude workflows, 9 Codex workflows in repository

AI generated by Plan Command for discussion #12027

Comments on the Issue (you are @copilot in this section)

• Fixes [plan] Remove 'experimental' label from Claude/Codex engines documentation #12031

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.