Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
Clean up git branches marked as [gone] (deleted on remote but still exist locally). Use when you want to prune stale local branches, remove worktrees for deleted branches, or clean up after PR merges.
Complete workflow to commit changes, push to remote, and create a pull request. Use when you want to ship changes end-to-end in one operation, from local changes to an open PR.
Commit changes and push to the current branch remote. Use when you want to commit local changes and push them upstream in one workflow, with branch protection against main/master.
Commit local changes on the current branch following conventional commit message format. Use when you need to create a git commit without pushing, or when you want to stage and commit changes with a properly formatted message.
Multi-agent exploration and task delegation for complex areas of interest. Use when you need to deeply explore a codebase area, gather information from multiple perspectives, or delegate parallel research tasks for comprehensive analysis.
Create a new command file following repo conventions. Use when you need to add a new slash command, create automation workflows, or extend the command library with new functionality.
Remove AI-generated code slop and improve code quality. Use when you need to clean up AI-written code, remove unnecessary defensive patterns, eliminate inconsistent comments, or align code style with the rest of the codebase.
Read-only file search and codebase exploration specialist. Use when you need to find files by pattern, search code with regex, navigate unfamiliar codebases, or understand code architecture without making changes.
Read all suggested PR changes and apply them directly to the codebase. Use when you have PR review comments to address, suggested changes to implement, or feedback to incorporate into your code.
Initialize AGENTS.md documentation for a codebase. Use when setting up a new repository for AI coding assistants, creating project documentation for Claude Code or Cursor, or improving existing AGENTS.md files.
Iterate on tasks using debug instrumentation and browser tools. Use when you need to debug web applications, verify frontend behavior, or fix issues without asking the user to manually test.
Comprehensive onboarding process for new developers. Use when helping someone get set up with a codebase, configuring development environments, or creating onboarding documentation.
Rebase the current branch with flexible target options. Use when you need to rebase on main, a specific branch, or a remote branch, with intelligent conflict handling.
Refactor code to improve quality while maintaining functionality. Use when you need to improve code structure, eliminate duplication, optimize performance, or enhance maintainability without changing behavior.
Streamline code by removing redundancy and aligning with repo style. Use when you need to consolidate logic, reduce indirection, clean up repeated patterns, or make code more concise.
Deep reasoning mode for complex problems requiring maximum cognitive depth. Use when facing difficult architectural decisions, complex debugging, multi-step problem solving, or situations requiring careful analysis before implementation.
Generate Mermaid diagrams from code, architecture, or concepts. Use when you need to visualize code flow, system architecture, data relationships, state machines, sequences, class structures, or any other diagrammable concept.
Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agents, terminals, or…
Use only when the user explicitly types /orchestrate goal to decompose a large task, spawn a tree of parallel cloud-agent workers/subplanners/verifiers via the Cursor SDK, and collect structured handoffs; do not invoke autonomously.
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
3 2mo agoA54 tokens
copy · 92%MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: