ℹ️ See my write-plan and implement-plan skills.
Update August 23, 2026: I’ve updated the skills. The updates are about the relationship between the plan file and a project’s standing documents (like CLAUDE.md). Details are in this comment on the write-plan gist and this one for implement-plan.
I spent the first 10 years or so of my career (going back to the 90s here, folks) in the Waterfall/BDUF era: long meetings discussing endless hypothetical scenarios, big planning documents covering months of work, missed deadlines, and deliverables that typically ended up misaligned with actual needs. The reasons for this frequent misalignment are now obvious, since our industry has matured since then (at least in some ways):
This is what spawned the Agile movement, which started to gain traction in the early 2000s, and at the time it felt revolutionary. It turned Waterfall on its head, with short development and deliverable cycles and frequent feedback (Agile has unfortunately accreted its own layers of bureaucracy since then, but that’s another story).
In our new era of AI-assisted coding, BDUF is back: we can now generate planning documents and code faster and cheaper, so why not? You can develop your plan, walk away while AI works on it for a few hours, and then deliver. If what you delivered ends up needing changes, repeat the process. This is how the popular Superpowers skill for executing plans works (and most other AI planning skills I’ve seen): “Load plan, review critically, execute all tasks, report when complete.”
ℹ️ See my ASD-STE100 (Simplified Technical English) output style for Claude Code
Update August 23, 2026: I made an addition to the ASD-STE100 output style:
Main clause first: State the subject and the main verb before any qualifier. Move a relative clause to after the main verb where you can.
Example:
- Before: “The behavior I deleted the comment about still holds, and the spec keeps it honest.”
- After: “The behavior still holds, and the spec keeps it honest. I only deleted the comment.”
This post was originally going to be about AI-assisted planning, but if you’re a Claude Code user, you may be experiencing the same frustration I have recently with Opus 5: it’s often incomprensible. Others have been frustrated also. Matt Pocock posted the other day: “Christ, Opus, talk like a normal person. I built this app and I have no idea what it’s saying.”
Sometimes it veers from extremely dense technical language to just bizarre. Opus served up this gem while I was doing a PR review the other day (the code under review provides alternative text suggestions):
…Then a permissions misconfiguration degrades to “you don’t get the 👀 and the summary” instead of “you don’t get the review.” The suggestions are the product; the acknowledgment is garnish, and garnish shouldn’t be able to take the meal down.
So the suggestions are the product, which I think Opus is saying is also the meal, which apparently can be ruined by a permissions misconfiguration. Oh wait, does it mean it’s actually the acknowledgements (the garnish) that are the problem? And what is the 👀 emoji referring to?… What are we talking about again? 😵💫
ℹ️ Update August 23, 2026: I wrote this post a month ago, which is a long time in the AI coding world, and I have an updated recommendation: always use the grilling (or grill-with-docs) skill instead of brainstorm. Matt Pocock has recently updated grilling. I compared it head-to-head with the Superpowers brainstorm using a few different kinds of initial prompts, and consistently got a more thorough interview from grilling.
Typically the first step in my Claude Code assisted workflow is getting a rough idea ready for planning. Not the plan itself, but brainstorming any aspects I haven’t thought through yet, or identifying possible gaps. Popular skills for this are grilling and grill-with-docs from Matt Pocock’s “AI Hero” skills and brainstorming from the Superpowers skills. I’ve worked with both and they each are suited to different needs: