research.
research is the protocol you reach for when you don’t yet know enough to write a task. It produces a knowledge artifact — findings plus a recommendation — rather than shippable code. There’s no commit/push/MR step and no git branch; the only writes are to the research task file.
Steps
- 01Scopingread-only
Formulate a specific, answerable research question. Classify the type (spike / architecture / evaluation / exploration), bound the scope, set a time box, compose the task file.
OpusAntigravityCodexyour call — answer to go on - 02Explorationdeep research
Deep, read-only investigation — gather evidence, analyze code, run read-only experiments. code-explorer agents and AI providers do the heavy lifting.
~100 agents fan out in parallel - 03Synthesissynthesize
Distill the evidence into findings and a recommendation in the task file.
- 04Conclusiondocs only
You review; the engine archives the task. No branch to merge, no dispatcher menu.
writes back to the shared LLM wiki
What makes it distinctive
Four research types
Scoping classifies the work as a spike (feasibility → PoC), architecture (design analysis → ADR), evaluation (tool comparison → weighted matrix), or exploration (codebase understanding → documented patterns). Each gets a tailored investigation strategy.
No branch by design
Research tasks declare branch: none. There’s no git_setup_branch in scoping and no completion dispatcher in conclusion — research output is knowledge, not a diff.
branch none — r-<name>, always branchless