How can skills that include scripts work in an agent plugin?

[ScottChapman]

Select Topic Area

Bug

Copilot Feature Area

Copilot Agent Mode

Body

I am writing some agent plugins that include skills that have a scripts folder (with some scripts the agent skill can run).
The skill folder ends up in an agent skill path (along with the scripts), but what happens is that the agent tries to run the script using the relative path that the skill mentions. Since the script is NOT in the workspace root it cannot be run directly from the terminal by the agent.

Maybe I just don't understand how this is supposed to work, but it seems to me that scripts should be relative to the skill that owns them.

[github-actions[bot]]

💬 Your Product Feedback Has Been Submitted 🎉

Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users.

Here's what you can expect moving forward ⏩

• Your input will be carefully reviewed and cataloged by members of our product teams. 
  • Due to the high volume of submissions, we may not always be able to provide individual responses.
  • Rest assured, your feedback will help chart our course for product improvements.
• Other users may engage with your post, sharing their own perspectives or experiences. 
• GitHub staff may reach out for further clarification or insight. 
  • We may 'Answer' your discussion if there is a current solution, workaround, or roadmap/changelog post related to the feedback.

Where to look to see what's shipping 👀

• Read the Changelog for real-time updates on the latest GitHub features, enhancements, and calls for feedback.
• Explore our Product Roadmap, which details upcoming major releases and initiatives.

What you can do in the meantime 💻

• Upvote and comment on other user feedback Discussions that resonate with you.
• Add more information at any point! Useful details include: use cases, relevant labels, desired outcomes, and any accompanying screenshots.

As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities.

Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐

[jannoguer]

This is a classic execution context headache with Copilot Extensions. You’re right that the agent defaults to the workspace root for any terminal command it tries to run, which completely breaks local scripts tucked away in a plugin folder.

The best way to handle this isn't to rely on the agent to "figure out" the path, but to resolve the absolute path within your plugin logic before the command ever hits the agent.

If you’re building the plugin in Node, you should use path.resolve or __dirname to point to your scripts folder specifically. When your skill tells the agent, "Run this script," it should be passing the full, absolute path (e.g., /Users/name/.vscode/extensions/your-plugin/scripts/script.sh) rather than the relative one. That way, it doesn't matter that the agent's terminal is sitting in the workspace root—it has the direct map to the file it needs.

Basically, think of the agent as a user who is always cd'd into the project root. If you want them to run something "internal" to your extension, you have to give them the full GPS coordinates to it.

Hope that helps! If it solves the problem, feel free to mark this as the answer. It helps other people with the same issue find the fix faster.

jannoguer

[ScottChapman]

Yea, I tried a bunch of approaches most of them failed. The one that I landed on was basically telling the skill to construct an absolute path to the script based on the location of the skill file (which apparently it does know). That approach seems to work but feels janky...