1## PART I - IF A LINEAR TICKET IS MENTIONED
 2
 30c. use `linear` cli to fetch the selected item into thoughts with the ticket number - ./thoughts/shared/tickets/ENG-xxxx.md
 40d. read the ticket and all comments to understand what research is needed and any previous attempts
 5
 6## PART I - IF NO TICKET IS MENTIONED
 7
 80.  read .claude/commands/linear.md
 90a. fetch the top 10 priority items from linear in status "research needed" using the MCP tools, noting all items in the `links` section
100b. select the highest priority SMALL or XS issue from the list (if no SMALL or XS issues exist, EXIT IMMEDIATELY and inform the user)
110c. use `linear` cli to fetch the selected item into thoughts with the ticket number - ./thoughts/shared/tickets/ENG-xxxx.md
120d. read the ticket and all comments to understand what research is needed and any previous attempts
13
14## PART II - NEXT STEPS
15
16think deeply
17
181. move the item to "research in progress" using the MCP tools
191a. read any linked documents in the `links` section to understand context
201b. if insufficient information to conduct research, add a comment asking for clarification and move back to "research needed"
21
22think deeply about the research needs
23
242. conduct the research:
252a. read .claude/commands/research_codebase.md for guidance on effective codebase research
262b. if the linear comments suggest web research is needed, use WebSearch to research external solutions, APIs, or best practices
272c. search the codebase for relevant implementations and patterns
282d. examine existing similar features or related code
292e. identify technical constraints and opportunities
302f. Be unbiased - don't think too much about an ideal implementation plan, just document all related files and how the systems work today
312g. document findings in a new thoughts document: `thoughts/shared/research/ENG-XXXX_research.md`
32
33think deeply about the findings
34
353. synthesize research into actionable insights:
363a. summarize key findings and technical decisions
373b. identify potential implementation approaches
383c. note any risks or concerns discovered
393d. run `humanlayer thoughts sync` to save the research
40
414. update the ticket:
424a. attach the research document to the ticket using the MCP tools with proper link formatting
434b. add a comment summarizing the research outcomes
444c. move the item to "research in review" using the MCP tools
45
46think deeply, use TodoWrite to track your tasks. When fetching from linear, get the top 10 items by priority but only work on ONE item - specifically the highest priority issue.