opensesh/canvas-to-code

opensesh/canvas-to-code

Agent

Read-only codebase audit for the target surface declared in Gate 0. Returns route status, components/hooks/lib used, sub-routes, and behaviors to port.

opensesh/canvas-to-code

Agent

Classifies each visual unit's data source. Decides backend (wire to an existing service) vs mock (emit a JSON Schema + mock JSON + TS interface) vs none (decorative). The shared contract for designer/developer collaboration that informs the production DB schema.

opensesh/canvas-to-code

Agent

Decodes any design-source HTML (Claude Design bundle, Figma Export-to-Code, V0, Lovable, Webflow, generic HTML) into a flat JSX/HTML reference, OR short-circuits when the source is a v2 iter folder (pre-extracted JSX). Deterministic.

opensesh/canvas-to-code

Agent

The keystone agent. Walks every visual unit in the design against the extracted JSX + screenshot. Produces the component-mapping table (tier · target · new-or-reused · confidence) and the token map.

opensesh/canvas-to-code

Agent

Stitches extractor + auditor + mapper output into the plan-doc template. Writes the canonical spike doc. Iterates conversationally with the engineer.

opensesh/canvas-to-code

Agent

Conversational PM orchestrator for Canvas-to-Code. Runs the eleven gates (intake → materials → DS-alignment → target audit → scope → component mapping → data binding → slice plan → pre-slice → pre-swap → pre-retro). Never writes feature code.

opensesh/canvas-to-code

Agent

Validates a single slice PR diff against the plan's slice spec. Returns PASS/REVISE with citations. Read-only — never pushes fixes.