Remove experimental label from Claude/Codex engines

[Copilot]

Documentation incorrectly labels Claude and Codex as "experimental" despite 31 production Claude workflows in this repository demonstrating stability.

Changes

• Banner replacement: Changed "Experimental Engines" warning to neutral "Multiple AI Engines Supported" note emphasizing feature parity (tools, triggers, safe outputs)
• Claude section: Removed "experimental" qualifier from engine description

Before

> [!NOTE]
> Experimental Engines
> 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.

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.

All engines now presented without hierarchy or stability implications.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• telemetry.astro.build
  • Triggering command: /opt/hostedtoolcache/node/24.13.0/x64/bin/node node /home/REDACTED/work/gh-aw/gh-aw/docs/node_modules/.bin/astro build (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>[Code Quality] Remove "experimental" label from Claude/Codex engines in documentation</issue_title>
<issue_description>## Description

The documentation labels Claude and Codex engines as "experimental" which creates an unnecessary perception of instability, despite evidence that Claude is production-ready (29 Claude workflows exist in this repository).

Affected File

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

Current State

The documentation currently states:

"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."

Problems

1. Misleading: 29 production Claude workflows in this repo demonstrate stability
2. Inconsistent: Says "not documented here" but documentation exists below in same file
3. Discouraging: Creates hesitation for Claude users without evidence of instability

Suggested Change

Replace the "experimental" banner with a neutral note:

> [!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.

Impact

Severity: High (perception issue) - Affects adoption confidence
Audience: Claude Code users, non-Copilot developers
Benefit: Improves Claude adoption by removing false "experimental" stigma

Success Criteria

• "Experimental" banner removed from engines.md
• Neutral "Multiple AI Engines Supported" note added
• No language suggesting Copilot is only production-ready engine
• Documentation builds successfully

Source

Extracted from Claude Code User Documentation Review discussion githubnext/gh-aw#12027

Finding: Obstacle 1 - "Experimental" Label Creates Perception Claude is Unstable
Assessment Score: 8.5/10 (points deducted for this issue)

Context

This is part of a broader effort to improve multi-engine documentation parity. Claude users currently feel like second-class citizens despite having full feature parity (except Copilot-specific bot features).

AI generated by Discussion Task Miner - Code Quality Improvement Agent

• expires on Feb 10, 2026, 9:06 PM UTC

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

• Fixes [Code Quality] Remove "experimental" label from Claude/Codex engines in documentation #12110

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.