why
Why
Investigate the motivation and constraints behind code. Use how for runtime mechanics; use this skill for rationale, tradeoffs, regressions, defensive checks, thresholds, and historical intent.
This is a read-only investigation. Agents may inspect repository state, version-control history, local documentation, and user-authorized observability or analytics sources. They must never create or edit an issue, change a pull request, reply to a review, send a message, post a comment, or mutate an external system. Keep findings and drafts local to the task.
When subagents are available, assign one evidence lane to each investigator. Subagents may communicate with each other, but no agent may communicate with a person. Repeat that sentence verbatim in every child prompt. If delegation is unavailable, run the same lanes sequentially and identify any lane the host could not inspect.
Model and reasoning preferences are optional. Read repository-documented model configuration or .agents/agent-models.md when present. Use bulk source reading for investigators and synthesis for a delegated synthesizer.
Read its optional reasoning profile line and validate each explicit model/profile pair against the current host. For a missing role or an auto or inherit-parent model entry, omit both overrides. For a missing, auto, or inherit-parent profile, omit the reasoning override. Never require the file, construct model identifiers from effort labels, or use unconfirmed choices. If a configured choice is unavailable or the host rejects a model/profile pair, report the fallback and retry that seat once with both overrides omitted. If the retry fails, record the gap or use the local fallback below. When engineering-mode is installed, match each subagent's reasoning profile to the job by its Delegation rule; otherwise use the configured profile.