feat(ui): add Generate Init Command section to Agents tab#25
Merged
Conversation
Adds a section in the terminal editor's Agents tab that helps users
generate init command templates for different LLM CLI tools:
- Claude Code: claude "{{LLM_PROMPT}} {{LLM_NEXT_ACTION}}"
- Aider: aider --message "{{LLM_NEXT_ACTION}}"
- GitHub Copilot: gh copilot suggest "{{LLM_NEXT_ACTION}}"
- Custom: raw tokens for user's own tool
Features:
- Dropdown to select LLM tool
- Preview of the command template
- Note when tool only supports {{LLM_NEXT_ACTION}}
- "Apply to Init Command" button that sets the template and
switches to the Terminal tab
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Cursor CLI option: cursor agent -p "{{LLM_PROMPT}} {{LLM_NEXT_ACTION}}"
- Clarify note about templates not including persistent context
- Update docs with Cursor example and tip about using the generator
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Interactive Mode toggle for Claude Code and Cursor - When off, adds -p flag for non-interactive/headless execution - Useful for automated tasks, CI/CD, or long-running jobs - Update docs with interactive vs non-interactive examples Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The context documentation incorrectly stated that the MCP server is read-only and that write tools return CLI commands. This caused Claude to refuse to use write tools directly. Updated documentation to correctly describe: - Query tools for reading data - Write tools that modify the board directly - Added termq_get to the tool list Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix Cursor CLI command: use 'agent' not 'cursor agent' - Remove outdated "Read-Safe" security note from mcp-server docs - Update termq_create and termq_set descriptions (no longer CLI-only) - Sync Resources/Help files with Docs/Help Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a section in the terminal editor's Agents tab that helps users generate init command templates for different LLM CLI tools.
Supported Tools
claude "{{LLM_PROMPT}} {{LLM_NEXT_ACTION}}"aider --message "{{LLM_NEXT_ACTION}}"gh copilot suggest "{{LLM_NEXT_ACTION}}"{{LLM_PROMPT}} {{LLM_NEXT_ACTION}}Features
{{LLM_NEXT_ACTION}}Test plan
🤖 Generated with Claude Code