Images: paste from the clipboard into the chat, thumbnails and a lightbox for
what is sent, image-only messages, attachments sent at 1568px with the
original kept for zoom_image.
Brief and finish: ask_user question cards (swatches, reference tiles, the
recommended answer), chat rules for a brief, design system first, density,
short reports and next steps.
Research: the composer's Web chip, fetch_reference_images (public addresses
only; icons, logos and backdrops dropped), a References gallery, and a Haiku
researcher sub-agent on Claude Code.
Image generation (opt-in): Codex, Google Flow (gf) or a custom command.
Plugins page: Avataaars, DiceBear, Iconify, Lorem Picsum, Flags and QR codes
through <x-plugin>; SVG import draws masked groups as images.
Tokens: lean Claude Code sessions, deferred tool schemas and context editing
on the API, a fresh session with a recap past 120k or on demand, per-turn and
chat totals, a 1M context meter, a turn budget, model and effort pickers.
Also: page switcher in Chat, no flicker while steps run, desktop target size
in lint, the installer keeps papercraft-mcp current.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Marcos Paulo
1b795fa971