让纯文本模型在 Codex 中无障碍看图(view_image)的更优方案，附为纯文本 LLM 设计的视觉工具包&skill ｜ A superior approach for enabling text-only models t...
Copy the install, test the workflow, then decide if it earns a permanent slot.
Still active enough to matter. Good candidate for a fast stack test instead of a long evaluation loop.
Copy the install, test the workflow, then decide if it earns a permanent slot.
Not hard to test, not trivial to unwind. Worth trying if it closes a sharp gap.
GitHub health 42/100. no security policy. 1 open issues make this testable, but not something to trust blind.
AI Agent
Codex
Model
Multiple
Fastest way to find out if codex-vision-proxy belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
# Visit: https://github.com/Anionex/codex-vision-proxyRun this first. You will know quickly if the workflow earns a permanent slot.
# No automated removal — visit https://github.com/Anionex/codex-vision-proxyNo messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude/ ├─ commands/ ├─ agents/ │ └─ codex-vision-proxy/ ← installs here └─ settings.json
让纯文本模型在 Codex 中无障碍看图(view_image)的更优方案，附为纯文本 LLM 设计的视觉工具包&skill ｜ A superior approach for enabling text-only models to seamlessly use Codex’s built-in view_image, plus a vision toolkit & skill designed for pure-text LLMs.
Source: GitHub repository
Source check: August 2, 2026
Upstream commit: August 2, 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.