Research Codebase

You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning parallel subagents and synthesizing their findings.

Initial Setup:

When this command is invoked, respond with:

I'm ready to research the codebase. Please provide your research question or area of interest, and I'll analyze it thoroughly by exploring relevant components and connections.

Then wait for the user's research query.

Steps to follow after receiving the research query:

1. Read any directly mentioned files first:

   • If the user mentions specific files (tickets, docs, JSON), read them FULLY first
   • IMPORTANT: Use the Read tool WITHOUT limit/offset parameters to read entire files
   • CRITICAL: Read these files yourself in the main context before spawning any subagent tasks
   • This ensures you have full context before decomposing the research

2. Analyze and decompose the research question:

   • Break down the user's query into composable research areas
   • Take time to ultrathink about the underlying patterns, connections, and architectural implications the user might be seeking
   • Identify specific components, patterns, or concepts to investigate
   • Create a research plan using TodoWrite to track all subtasks
   • Consider which directories, files, or architectural patterns are relevant

3. Spawn parallel subagent tasks for comprehensive research:

   • Create multiple subagent tasks to research different aspects concurrently
   • We now have specialized agents that know how to do specific research tasks:

   For codebase research:

   • Use the mem8:codebase-locator agent to find WHERE files and components live
   • Use the mem8:codebase-analyzer agent to understand HOW specific code works
   • Use the mem8:codebase-pattern-finder agent if you need examples of similar implementations

   For memory directory:

   • Use the mem8:memory-locator agent to discover what documents exist about the topic
   • Use the mem8:memory-analyzer agent to extract key insights from specific documents (only the most relevant ones)

   For web research (only if user explicitly asks):

   • Use the mem8:web-search-researcher agent for external documentation and resources
   • IF you use web-research agents, instruct them to return LINKS with their findings, and please INCLUDE those links in your final report

   For GitHub issues (if relevant):

   • Use gh issue view {number} to get full details of a specific issue
   • Use gh issue list --search "query" to find related issues or historical context

   The key is to use these agents intelligently:

   • Start with locator agents to find what exists
   • Then use analyzer agents on the most promising findings
   • Run multiple agents in parallel when they're searching for different things
   • Each agent knows its job - just tell it what you're looking for
   • Don't write detailed prompts about HOW to search - the agents already know

4. Wait for all subagents to complete and synthesize findings:

   • IMPORTANT: Wait for ALL subagent tasks to complete before proceeding
   • Compile all subagent results (both codebase and memory findings)
   • Prioritize live codebase findings as primary source of truth
   • Use memory/ findings as supplementary historical context
   • Connect findings across different components
   • Include specific file paths and line numbers for reference
   • Verify all memory/ paths are correct using flat structure (memory/plans/, memory/research/, etc.)
   • Highlight patterns, connections, and architectural decisions
   • Answer the user's specific questions with concrete evidence

5. Gather metadata for the research document:

   • IMPORTANT: Use the mem8 CLI to generate proper metadata. DO NOT manually gather git information.
   • Run the command with the user's actual research question/topic:

     mem8 metadata research "the user's actual question here" --format json
     

   • Example: If user asks "How does auth work?", run: mem8 metadata research "How does auth work?" --format json
   • This will output JSON with all required fields including a slug field for the filename
   • Parse the JSON to extract the slug field for use in the filename
   • Note: The topic argument is optional and defaults to "research" if omitted, but it's better to use the actual user question
   • Store this output to use in the next step
   • Filename format: memory/research/YYYY-MM-DD_HH-MM-SS_{slug}.md
     • Extract timestamp from the date field: parse ISO format and convert to YYYY-MM-DD_HH-MM-SS
     • Use the slug field directly from the metadata JSON
     • Example: 2025-10-15_12-15-24_memory-directory-documentation.md

6. Generate research document:

   • CRITICAL: Use the metadata from step 5 to generate both frontmatter and filename
   • Get frontmatter by running: mem8 metadata research "topic" --format frontmatter
   • DO NOT manually run git commands or gather metadata yourself
   • Structure the document with the YAML frontmatter, followed by content:

     ---
     date: [Current date and time with timezone in ISO format]
     researcher: [Researcher name from memory status]
     git_commit: [Current commit hash]
     branch: [Current branch name]
     repository: [Repository name]
     topic: "[User's Question/Topic]"
     slug: [URL-safe slug from metadata]
     tags: [research, codebase, relevant-component-names]
     status: complete
     last_updated: [Current date in YYYY-MM-DD format]
     last_updated_by: [Researcher name]
     ---
     
     # Research: [User's Question/Topic]
     
     **Date**: [Current date and time with timezone from step 4]
     **Researcher**: [Researcher name from memory status]
     **Git Commit**: [Current commit hash from step 4]
     **Branch**: [Current branch name from step 4]
     **Repository**: [Repository name]
     
     ## Research Question
     [Original user query]
     
     ## Summary
     [Hi#level findings answering the user's question]
     
     ## Detailed Findings
     
     ### [Component/Area 1]
     - Finding with reference ([file.ext:line](link))
     - Connection to other components
     - Implementation details
     
     ### [Component/Area 2]
     ...
     
     ## Code References
     - `path/to/file.py:123` - Description of what's there
     - `another/file.ts:45-67` - Description of the code block
     
     ## Architecture Insights
     [Patterns, conventions, and design decisions discovered]
     
     ## Historical Context (from memory/)
     [Relevant insights from memory/ directory with references]
     - `memory/decisions/something.md` - Historical decision about X
     - `memory/docs/notes.md` - Past exploration of Y
     Note: Paths exclude "searchable/" even if found there
     
     ## Related Research
     [Links to other research documents in memory/research/]
     
     ## Open Questions
     [Any areas that need further investigation]
     

7. Add GitHub permalinks (if applicable):

   • Check if on main branch or if commit is pushed: git branch --show-current and git status
   • If on main/master or pushed, generate GitHub permalinks:
     • Get repo info: gh repo view --json owner,name
     • Create permalinks: https://github.com/{owner}/{repo}/blob/{commit}/{file}#L{line}
   • Replace local file references with permalinks in the document

8. Sync and present findings:

   • Run mem8 sync to sync the memory directory (if configured with git sync)
   • Present a concise summary of findings to the user
   • Include key file references for easy navigation
   • Ask if they have follow-up questions or need clarification

9. Handle follow-up questions:

   • If the user has follow-up questions, append to the same research document
   • Update the frontmatter fields last_updated and last_updated_by to reflect the update
   • Add last_updated_note: "Added follow-up research for [brief description]" to frontmatter
   • Add a new section: ## Follow-up Research [timestamp]
   • Spawn new subagents as needed for additional investigation
   • Continue updating the document and syncing

Important notes:

• ALWAYS use mem8 metadata research command - NEVER manually gather git metadata
• Use the slug from metadata JSON - NEVER make up your own filename slug
• Filename format: YYYY-MM-DD_HH-MM-SS_{slug}.md where slug comes from mem8 metadata research --format json
• Sorting: Files use ISO date format (YYYY-MM-DD) which sorts chronologically
  • Ascending sort (A-Z, default): Oldest files first
  • Descending sort (Z-A): Newest files first ← Recommended
  • In VS Code: Click the column header to toggle sort order
  • Or sort by "Modified" date descending for most recent work
• Always use parallel subagent tasks to maximize efficiency and minimize context usage
• Always run fresh codebase research - never rely solely on existing research documents
• The memory/ directory provides historical context to supplement live findings
• Focus on finding concrete file paths and line numbers for developer reference
• Research documents should be self-contained with all necessary context
• Each subagent prompt should be specific and focused on read-only operations
• Consider cross-component connections and architectural patterns
• Include temporal context (when the research was conducted)
• Link to GitHub when possible for permanent references
• Keep the main agent focused on synthesis, not deep file reading
• Encourage subagents to find examples and usage patterns, not just definitions
• Explore all of memory/ directory, not just research subdirectory
• File reading: Always read mentioned files FULLY (no limit/offset) before spawning subagent tasks
• Critical ordering: Follow the numbered steps exactly
  • ALWAYS read mentioned files first before spawning subagent tasks (step 1)
  • ALWAYS wait for all subagents to complete before synthesizing (step 4)
  • ALWAYS gather metadata before writing the document (step 5 before step 6)
  • NEVER write the research document with placeholder values
• Path handling: The memory/searchable/ directory contains hard links for searching
  • Always document paths by removing ONLY "searchable/" - preserve all other subdirectories
  • Examples of correct transformations:
    • memory/searchable/docs/notes.md → memory/docs/notes.md
    • memory/searchable/prs/123.md → memory/prs/123.md
    • memory/searchable/research/auth.md → memory/research/auth.md
  • NEVER modify the subdirectory structure - preserve the exact paths found
  • This ensures paths are correct for editing and navigation
• Frontmatter consistency:
  • Always include frontmatter at the beginning of research documents
  • Keep frontmatter fields consistent across all research documents
  • Update frontmatter when adding follow-up research
  • Use snake_case for multi-word field names (e.g., last_updated, git_commit)
  • Tags should be relevant to the research topic and components studied