design, validate, launch, and monitor castform post-training runs from codex.
Install
- 1Add it in ChatGPT
Open Plugins in the ChatGPT sidebar (web or desktop), search for “castform” and select +. You'll be asked to sign in to any connected service on first use. Then type @ in a chat to call it.
Skills 7
- design-environment
Design a benchmax environment, its ordered dataset, tools, and explicit reward shape for a Castform project.
- generate-data
Prepare, clean, generate, or reference the data used by a Castform environment from project-owned Python scripts.
- launch-run
Review, bundle, upload, and explicitly launch a Castform GPU training run from the project script.
- setup
One-time bootstrap for a new Castform project — install the Castform CLI and scaffold the Codex guide, skills, and starter environment. Run this before any other Castform skill.
- train-sft
Build a validated benchmax-sft-v1 dataset from existing labeled conversations, upload it, and explicitly launch a supervised finetuning run — no environment, rewards, or rollouts.
- verify-environment
Run and inspect the script-owned local two-sibling validation before spending GPU credits.
- view-progress
Monitor a Castform run with status, scalar, rollout, and log commands, then diagnose failures or reward drift.
Things to ask
- “Set up this project for Castform.”
- “Help me design a Castform environment.”
- “Validate and launch my Castform run.”
Related
SuperpowersPlan, develop, and debug codeplugin · by Jesse Vincent · 294k stars
ShopifyBuild and manage your storeplugin · by Shopify · 7.2k stars