Watch the video on LinkedIn here!
The most downloaded and widely used methodology in the Claude Code ecosystem is Superpowers, with over 208k stars⭐️ and 18.5k forks🍴 on GitHub (and counting!)
Going from raw Claude Code to using Superpowers is as revolutionary as going from a manual transmission to an automatic. Here's why this analogy holds:
Planning Mode vs. Coding Mode
When we build with Claude (or Codex, or Gemini...), we're usually in one of two states:
- planning mode
- coding mode
Like shifting gears in a car🚘, moving between these modes effectively is what makes it all work. Skip the shift, and you're just revving your engine (aka burning context and going nowhere.)
Superpowers lets Claude automatically detect and shift between these modes. It picks up on ambiguity in your prompt and ensures it fully understands the task before entering coding mode. No manual shifting required!
Slower, but for Good Reason
Superpowers can feel slower and less satisfying than raw Claude Code, like how driving an automatic can feel less engaging than a manual. But both serve the same critical purpose: they stop you from blowing up your engine!
That said, there's still a time and place for raw Claude. Sometimes you want direct, fast, unmediated output. But that minor gain in speed often isn't worth the added complexity, the ambiguity risk, and the tradeoffs that come with it.
The Layer Underneath
Entire is building the foundation beneath all of this — capturing every session and decision, and linking it to the commit it produced. It's the full record of how the code was written, not just the code itself.
So the question is this: how will you put your agent in drive🚘?
Top comments (2)
The automatic-transmission analogy is great because it captures the real lesson: the gains aren't a smarter engine, they're better drivetrain. Superpowers winning the Claude Code ecosystem is the strongest evidence going that the leverage is in the harness, not the raw model. Same underlying Claude, but structure around it (skills, workflows, the methodology that decides what to do when) is what turns capable-but-flaily into reliably-useful. That's the manual-to-automatic jump you're describing: you stop hand-managing every gear (context, tool order, when to verify) and the structure handles it so you can actually drive. The part I find most underrated is that this structure is also where you put the brakes, not just the acceleration, bounding loops, gating the irreversible step, knowing when to stop and ask. An automatic that only accelerates is a liability; the methodology is what makes speed safe. The harness is the product, the model is the engine is basically my whole thesis, it's how I think about Moonshift, agents that build and ship under structure rather than just a clever model left to wander. Out of the Superpowers workflow, which skill gave you the biggest jump from raw Claude Code?
I think the Planning/clarification mode. I make demos, and Claude Code has really changed my job because now it can effectively do my job! It can make demos very quickly! Planning and clarifications slows me (us?) down and think more about build decisions.