Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
dsh-vision-router is a plugin that lets text-based DeepSeek Harness agents inspect images through a built-in vision service and image-analysis tools. Agents use it for tasks such as answering questions about images, locating elements, reading text, comparing pixels, and tracing or extracting visual content. The catalogue entries support using the plugin within DeepSeek Harness workflows.
Latest release v2.1.6 · 11 Sept 2026
4 files for GitHub Copilot, Claude Code and Codex: dsh-vision-router copilot-instructions.md, dsh-vision-router actions-security.instructions.md, dsh-vision-router runtime-security.instructions.md, code-review — 675 tokens loaded in every session.
.github/copilot-instructions.md A 304 tok .github/instructions/actions-security.instructions.md A 187 tok .github/instructions/runtime-security.instructions.md A 184 tok .github/skills/code-review/SKILL.md A 31 tok These files are ysr666/dsh-vision-router's own configuration — they tell GitHub Copilot, Claude Code and Codex how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.