为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
Last commit October 13, 2026, 35 days ago.
1,229 GitHub stars and 0 Honeystax upvotes. Copy the install, test the workflow, then decide if it earns a permanent slot.
You can test this quickly and remove it cleanly if it misses.
Starts at 6. Added: last commit 35 days ago +7, GitHub health 42/100 +14, no security policy +8, no contributing guide +4, no code of conduct +3.
AI Agent
Multiple
Model
Multiple
Fastest way to find out if agent-vision-toolkit belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
git clone https://github.com/Anionex/agent-vision-toolkit ~/.claude/skills/agent-vision-toolkitRun this first. You will know quickly if the workflow earns a permanent slot.
rm -rf ~/.claude/skills/agent-vision-toolkitNo messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude/ ├─ commands/ ├─ skills/ │ └─ agent-vision-toolkit/ ← installs here ├─ agents/ └─ settings.json
agent-vision-toolkit is listed on Honeystax as a Skill for Multiple, since August 5, 2026. Its code is at github.com/Anionex/agent-vision-toolkit, with 1,229 GitHub stars and 1 open issues. Last commit October 13, 2026, 35 days ago. GitHub's community health check gives it 42 out of 100.
Source: GitHub repository
Source check: October 13, 2026
Upstream commit: October 13, 2026
Repository state: Not marked archived
Honeystax upvotes are community interest signals, not star ratings. GitHub stars and repository health are source measurements; editorial risk and trial-cost notes are Honeystax analysis.