Command Claude Code
Parse a visual brief into the Image Node Factory intake JSON.
Identity-first cognitive agent OS with memory, multi-channel ingress, Operating Room orchestration, and desktop surfaces.
This repository also configures its own agents. See what taskchad-os tells them →
Command Claude Code
Parse a visual brief into the Image Node Factory intake JSON.
Command Claude Code
Build the dual-variant prompt pack, imagegen packet, and initial manifest using the selected library template.
Command Claude Code
Validate the Image Node Factory prompt-pack and render artifacts.
Command Claude Code
Render the selected variant with Codex built-in image generation or block cleanly.
Command Claude Code
Produce the final local report for the Image Node Factory run.
Command Claude Code
Dynamically select the strongest style-library template and nearest example cases using the gpt-image-2-style-library skill.
Command Claude Code
Author a full HyperFrames composition from the approved vision - agent-crafted choreography, registry blocks, voiceover-driven timing, and the pre-hide pass.
Command Claude Code
Apply exactly one numbered fix round from the QA issues - change only what was flagged, then re-verify.
Command Claude Code
Normalize a raw video request into the canonical intake JSON for the video-production workflow.
Command Claude Code
Fresh-context QA on the per-scene first-frame stills - returns a structured pass/issues verdict.
Command Claude Code
Final production report - MP4 path, ffprobe verification, scorecard, and the artifacts index.
Command Claude Code
Build the research dossier (facts, derived design, reference images) for a URL or theme via the framework research module.
Command Claude Code
Draft the operator-facing VISION (angle, beat outline, imagery treatment) with pipeline parity, ready for the approval gate.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: