linear-read

Explain completed or proposed software work so a human can understand its intent, consequential changes, design choices, and supporting evidence.

Restack downstream stacked PRs and apply the current PR's reviewer feedback in their code.

Watch a Loom video — pull its transcript and screen frames so the agent can understand what was said and shown.

Drive a multi-phase plan to completion autonomously by delegating each phase to a fresh-context subagent that lands the work as a stacked PR.

Investigate feature implementations and generate comprehensive top-down Markdown documentation with Mermaid diagrams.

Produce a compact, syntax-highlighted pseudo-code gist that explains how a specific code path, class, module, feature, or subsystem works.

Interview the user one question at a time, drilling down into the technical details needed to implement a chunk of work.

Drive a multi-phase plan to completion autonomously by spawning fresh-context subagents — one per phase — that land each phase as a stacked PR.

Drive a single stage from a stages document all the way to a stack of reviewed PRs, autonomously.

Senior-engineer code review focused on architecture — loose coupling, cohesion, separation of concerns, abstraction, and reuse.

Break down implementation plans into detailed, self-contained phased plans where each phase is a single focused commit.

Propagate review findings from a reviewed PR forward to downstream PRs in the same stack as inline GitHub comments.