Skip to content

Conversation

@hashimwarren
Copy link

Added 'agent/runSubagent' tool to Context7-Expert for improved workflow execution.

Pull Request Checklist

  • I have read and followed the CONTRIBUTING.md guidelines.
  • [ x] My contribution adds a new instruction, prompt, or chat mode file in the correct directory.
  • [ x] The file follows the required naming convention.
  • [ x] The content is clearly structured and follows the example format.
  • [ x] I have tested my instructions, prompt, or chat mode with GitHub Copilot.
  • [x ] I have run npm start and verified that README.md is up to date.

Description

I ran the original context 7 agent and it performed multiple searches to retrieve the right documentation. Reportedly Context7 often uses a lot of the provided context window of the models.

I cleared the chat and ran an updated agent with "runSubagent" added as an instruction. The model followed the directions and I saw that most searched were performed by a subagent, noted with an indentation in the chat.

This should allow for better management of the provided context window, and better advice from the agent.


Type of Contribution

  • New instruction file.
  • New prompt file.
  • New chat mode file.
  • New collection file.
  • [ x] Update to existing instruction, prompt, chat mode, or collection.
  • Other (please specify):

Additional Notes


By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

Added 'agent/runSubagent' tool to Context7-Expert for improved workflow execution.
Copilot AI review requested due to automatic review settings December 5, 2025 00:03
Copilot finished reviewing on behalf of hashimwarren December 5, 2025 00:05
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR enhances the Context7-Expert agent by adding the agent/runSubagent tool to improve context window management during workflow execution. According to the PR description, the original agent performed multiple searches consuming significant context window space. With this enhancement, searches can be delegated to subagents (shown as indented in chat), allowing for better context management and more effective advice delivery.

Key Changes

  • Added agent/runSubagent to the tools array for delegating workflow tasks to subagents
  • Added instruction at the workflow section to use the runSubagent tool for efficient execution

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant