koco-co

koco-co/deepseek-vision-bridge

Plugin Claude Code

A vision bridge that lets text-only models interpret images through Claude Code and Codex plugins.

koco-co/deepseek-vision-bridge

Plugin Claude Code

An image-to-text bridge that lets the text-only DeepSeek model work with pictures. It uses codex exec to send images to gpt-5.4-mini, which returns structured descriptions in Chinese for the conversation.

koco-co/deepseek-vision-bridge

Hook

Runs when you submit a prompt, before the agent sees it, executing user-prompt-submit.mjs via node. From koco-co/deepseek-vision-bridge.

koco-co/deepseek-vision-bridge

Hook

Runs before the agent uses a tool for ^(Read and view_image)$ tool calls, executing pre-tool-use.mjs via node. From koco-co/deepseek-vision-bridge.

koco-co/deepseek-vision-bridge

Hook

Runs after a tool call finishes, executing post-tool-use.mjs via node. From koco-co/deepseek-vision-bridge.

koco-co/deepseek-vision-bridge

Skill Claude CodeCodex

A skill that turns images available to a text-only agent into structured descriptions in Chinese.