Claude Code Can't Draw — This Plugin Borrows Your Codex CLI Login

A new open-source plugin called codex-bridge lets Claude Code users route image generation and GPT-5 subagent tasks through their existing Codex CLI login, billing against a ChatGPT plan instead of a separate API key. The plugin, which has not been tested by the reviewer, uses bash wrappers to shell out to Codex CLI's non-interactive mode, keeping intermediate output out of Claude's context to save tokens. It includes a delegation rubric for deciding which tasks to offload, but requires that prompts be sent to OpenAI's servers, which may be a blocker for some teams.

TL;DR: "Claude can't draw" is a budget problem, not a capability problem. codex-bridge MIT is a Claude Code plugin that routes image generation gpt-image-2 and five GPT-5 subagents through the Codex CLI login you already have — billing against your ChatGPT plan instead of a second API key. I have not tested or run it; this is a source-reading review. How it works. Two bash wrappers shell out to codex exec , Codex CLI's non-interactive mode, with your existing codex login both scripts check codex login status first . Text tasks use a read-only sandbox and capture only the final answer via -o <tmpfile bin/codex-run:92-96 . Image tasks use a workspace-write sandbox scoped to the output directory bin/codex-imagegen:110 , then verify the file landed. Exit codes: 0 ok, 1 precondition, 2 failure, 124 timeout. Why the split matters. Codex runs as a separate process, so its intermediate output never enters your Claude context — you pay Claude tokens only for the brief and the review. The trade-off: Codex is blind to your conversation history, so every brief must stand alone, which is why every subagent is instructed to verify before reporting. The delegation rubric skills/codex-delegate/SKILL.md is the most reusable part: delegate high-volume, low-judgment work mechanical multi-file edits, bulk scaffolding, exhaustive sweeps, all image work, long self-contained subtasks ; keep low-volume, high-judgment work architecture calls, ambiguous requirements, anything needing conversation history, edits under ~3 files . Round-tripping a two-line fix costs more, not less. Trust boundary. No API key: credentials live in ~/.codex from codex login , and every call forwards your task text to OpenAI's servers. If your team's data policy cannot accept a second vendor seeing prompts, that is a blocker, not a footnote. Caveats from README and source. 1–4 minutes per image; image turns burn ChatGPT quota ~3–5× faster than text; the default path cannot emit native alpha chroma-key strip, or CLI fallback plus API key ; macOS and Linux only; custom sizes must satisfy longest edge ≤3840px, both edges multiples of 16, ratio ≤3:1, and 655,360–8,294,400 total pixels. Who should try it. You already pay for a ChatGPT plan, run Claude Code daily, and regularly produce images or mechanical bulk edits. Skip it if you rarely need images, your work is small and interactive, or your data rules forbid OpenAI seeing prompts. Project: https://github.com/Sateezg/codex-bridge https://github.com/Sateezg/codex-bridge · README: https://github.com/Sateezg/codex-bridge/blob/main/README.md https://github.com/Sateezg/codex-bridge/blob/main/README.md · codex-run: https://github.com/Sateezg/codex-bridge/blob/main/bin/codex-run https://github.com/Sateezg/codex-bridge/blob/main/bin/codex-run · codex-imagegen: https://github.com/Sateezg/codex-bridge/blob/main/bin/codex-imagegen https://github.com/Sateezg/codex-bridge/blob/main/bin/codex-imagegen · delegate rubric: https://github.com/Sateezg/codex-bridge/blob/main/skills/codex-delegate/SKILL.md https://github.com/Sateezg/codex-bridge/blob/main/skills/codex-delegate/SKILL.md