Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.joggr.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

/gg-research explores your codebase to gather the technical context Workflows needs to create an accurate implementation plan. It identifies relevant architecture patterns, dependencies, existing code conventions, and potential risks.

​
Invocation

/gg-research [phase-number]
  • No argument — runs at the project level, gathering context for the entire project.
  • With a phase number — focuses research on a specific phase’s scope.

​
What It Produces

Populates research.md in your project directory with structured findings:
  • Architecture — relevant files, patterns, module boundaries, and data flow
  • Dependencies — existing libraries and services the work depends on
  • Existing patterns — code conventions and patterns Workflows should follow
  • External docs — links to relevant documentation
  • Risks — potential issues, conflicts, or complexity to watch for

​
Behavior

Workflows reads your codebase docs, project input, and discussion notes to determine what to investigate. It then scans the repository for relevant files, patterns, and dependencies.
/gg-research requires codebase docs to be present. If you haven’t run /gg-codebase yet, Workflows will ask you to run it first.
  • Path validation — Workflows validates that all file paths in the research output are absolute paths. If relative paths are detected, Workflows offers to retry or continue with a warning.
  • Checkpoint — after research completes, Workflows offers to commit research.md. You can skip this and commit manually later.
Research quality improves when you run /gg-discuss first. The more context Workflows has about your goals and constraints, the more targeted and useful the research findings will be.