Open-source qiaomu-codex-imagegen lets any agent call Codex's built-in image generation via MCP or skill
vista8 · x · 2026-10-04
qiaomu-codex-imagegen is open source: it exposes OpenAI Codex's built-in image generation through an MCP server, a CLI, and an Agent Skill sharing one core, so Claude Code, Cursor, or any command-capable agent can generate images. Instead of drawing directly, suggestdirections first offers at least four mechanically distinct style directions (text-led, flat layout, photographic, product close-up, material/space, plus a Mondo artist option); you pick one, composeprompt expands it into a full prompt, then the image is generated and checked. Ships with 24 scenario templates (48 presets), 20 Mondo poster artist styles, and rules against fabricating facts or garbled text. Install: npx skills add joeseesun/qiaomu-codex-imagegen.
Related event: Open-Source Tool Exposes Codex Image Generation to Any Agent(2 posts)→
More from coding & agent
- Engineer uses Claude Opus 5.5 to run river hydraulics calc with 3D viz, in-browser — anselm · 2026-10-04
- Google's VeriHarness shows agent agreement hides shared errors, gains 6+ points with agentic verifier — omarsar0 · 2026-10-04
- NVIDIA paper: verify-then-execute lifts TerminalBench Pass@1 from 50.0% to 68.0% — dair_ai · 2026-10-04
- Dev builds fully code-generated drivable Mars demo with Claude Opus 5.5: 23.7 hours, ~$259 in API costs — bennash · 2026-10-04
- Dev shows off mostly-autonomous agent cluster: one Orchestrator running Claude Code fleets — aksh_stocks · 2026-10-04
- Codex usage resets expire in under 13 hours if unused — just ask Codex for the exact time — JeremyNguyenPhD · 2026-10-04