Groundrules
Assemble the ground rules your AI coding agents follow
11 followers
Assemble the ground rules your AI coding agents follow
11 followers
Every AI coding agent reads an instruction file — AGENTS.md, CLAUDE.md, or a system prompt. Most are copy-pasted and half-stale. Groundrules is a visual builder for them: drag battle-tested blocks (conventions, workflows, hard rules with verification probes) onto a canvas, compile to any target your tools read, then Test Drive against 12+ live models (Claude, GPT, Gemini, Grok…) to see whether the agent actually obeys — before you commit the file. Core builder is free.
Free Options
Launch Team / Built With
honestly the test drive against 12+ models thing is genuinely clever, like actually seeing whether the agent obeys before you ship the file saves so much guesswork. solid execution.
@vedatmdxs Thanks Vedat! Test Drive came out of getting burned... I kept writing rules that felt airtight until a model cheerfully ignored them. Watching an agent break your rule in a sandbox costs 30 seconds; watching it break the rule in your repo costs an afternoon. Curious to know which model do you run day to day? That's the one worth test-driving against first.
The test-drive-against-live-models idea is genuinely clever, turning what used to be blind faith in a prompt file into something you can actually verify before shipping it.
@theshipper "Blind faith in a prompt file" is exactly the disease, well put. The uncomfortable discovery from building it: rules that survive one model sometimes die on another; same file, different obedience. That's why it's 12+ models and not a generic linter. If you take it for a spin, I'd love to know if any of your go-to rules fail somewhere surprising as those make the best catalog blocks.