| name | feasibility-analysis |
| description | Start here to scout an unfamiliar problem space — research existing solutions, patterns, anti-patterns, constraints, and technical feasibility before committing to an approach. |
| context | fork |
| agent | researcher |
Scout the problem space and map the landscape. Find what already exists, how others solve this, and what could make it hard or impossible. Explore wide before going deep — survey many options, don't tunnel on the first.
Use the codebase, Context7, and web search together. Every claim you make must trace to a source.
What to investigate
- Existing solutions — libraries, tools, and prior art in this codebase and the wider ecosystem.
- Patterns and anti-patterns — how this problem is solved well, and the ways it's solved badly.
- Constraints — technical limits, performance bounds, compatibility, security, licensing.
- Trade-offs — for each viable option, what you gain and what you give up.
Depth
Default to WIDE reconnaissance — breadth over depth. Go DEEP on a specific option only when asked. If you've spent more time than the question warrants, stop and report what you have.
What to produce
A scout report: the landscape, viable options with their trade-offs, the key constraints, open questions, and red flags. Mark your confidence and cite the source for every finding. Say what you couldn't determine rather than guessing.
