I can't afford the $200+ per month subs needed to support full use of GSD so I'm investigating using it between Antigravity (with it's free timed windows for Gemini & Opus tokens) & Opencode using free or cheap AI models - being able to switch between these seamlessly as a project progresses. So when my free tokens are expired in Antigravity, switching over to Opencode & progressing the project until the 3-5H or 5D window refreshes the free tokens in Antigravity. AFAIK, this requires installing GSD in both Opencode & Antigravity but linking the together the different folders GSD uses as the working folder in each - .gsd in Antigravity & .planning in the Opencode GSD installation. I don't know why the Opencode installation from here https://github.com/rokicool/gsd-opencode/tree/main/gsd-opencode uses .planning instead of .gsd? Just setting this up, atm, to check it out

Quick question for the experienced folks here. I'm brand new to claude code and GSD, used cursor and n8n a bunch 12 months ago, built a little business and then shut it down. I'm using GSD workflow and built a post-planning hook that verifies implementation patterns in my plans against Context7 documentation before execution. What it does: After /gsd:plan-phase completes, it extracts patterns from the PLAN.md files (install commands, config setups, import statements, API usage) and checks each one against current Context7 docs. Example check: - Plan says: ConvexProvider wraps BrowserRouter - Context7 query: "Is this still the correct provider hierarchy?" - Result: ✅ Current or ⚠️ Pattern changed Why I built it: I'm new to this and paranoid about executing plans with outdated patterns. The planner agent might be using stale knowledge, and I'd rather catch API changes before running code. My concern: Am I creating unnecessary overhead? Is this actually useful, or am I solving a problem that doesn't exist? More experienced users - do you verify plans before execution, or do you just trust the planner and fix issues as they come up?

So I'm a semi-retired artist/designer/music producer and curious about AI. I found TÂCHES in the Meta Mind Music community on Skool and discovered his new GSD/Claude Code project and I'm into it. While I make good use of AI chat bots, I haven't delved into vibe coding yet. I'm one of those people that gets scared off by terminal and the technical hurdles. Not to mention the price tag ($200/mo, yikes). In my experience, gen-AI has been a waste of time and money. Hitting my limits and putting more money in the slot machine to try and get it to do what I want. There's so much hype and marketing BS and I just want to find out what's honest and what works for me.

Go on then... What are you using GSD for right? Share in the comments 👇

Hi, I'm a retired university lecturer & old codger programmer many years ago but I still have a personality (apologies to all the software engineers out there). Having time on my hands I started to get interested in AI in 2025 & late last year hit on an idea for a music-related app which started me down the rabbit hole of vibe coding. Too old & not interested in learning modern language coding so at the mercy of runaway, fickle AI model for coding. When the app was about 80% finished I started to find the AI slop in it when I went to make changes & realised that Ai coding were mostly fur coat & no drawers - looks good on the outside but don't delve too deep. So I started to try to put some manners on the AI models & like it says in GSD intro - most coding frameworks are for teams, corporate enterprise approaches which, as a solo enterprise, is just more work & complexity than necessary so I started to try to put some AI guardrails of my own. And then I came across GSD a while ago but as I'm a cheapskate & not a Claude user, I ignored it. But recently saw that a version for Opencode & AntiGravity were knocking around so here I am. I'm going to start a thread for cheapskate coders using GSD as that's the road I'm pursuing