gs-why
Why
Investigate the motivation and intent behind code. The companion gs-how skill answers what the code does and how it works. gs-why answers what forces led to its shape.
Run investigators and the synthesizer as subagents, using the harness's subagent tools. If the user names models, use those. Otherwise run investigators on a fast, capable model and the synthesizer on the strongest model the harness reaches. If the harness offers no model choice, use the session's model. If the harness has no subagent tools, run each investigation yourself, one source at a time, then synthesize, and say so.
Subagents need the session's MCP servers and connectors. The MCP-backed investigators search through them, and the synthesizer spot-checks citations through them. If the harness has a read-only subagent mode that removes that access, do not use it. Investigators still shouldn't write anything.
Operating Posture
Operate as a careful, cautious, and precise investigator. Be honest about what you know vs what you're inferring. Read references/epistemics.md for the full confidence framework and phrasing guide. The synthesizer must follow it.
Step 1. Understand the Target and the Question
The target is usually a chunk of code, a pattern, a feature, or a named design decision. The question is usually a design rationale, a tradeoff, a motivating edge case, an external constraint, dead code, or a broad history sweep.
If the target is vague ("why do we do it this way?" with no clear referent), make your best guess from conversation context (open files, recent edits, what was just discussed). State your interpretation briefly so the user can redirect if you're off, then proceed.