Key Takeaways
- Install Florian's Claude Code Kit and run
/grill-mebefore non-trivial tasks. - This guardrail interviews you one question at a time, forcing alignment before any code is written — catching misread requirements at their cheapest point.
What Changed — A Guardrail for the Most Expensive Mistake
Agentic coding has one failure mode that costs more than all the others combined: the agent confidently builds the wrong thing. Not buggy code — wrong code. It misread what you wanted, picked a default you'd never have chosen, made an architectural call you didn't notice, and by the time you catch it the thing is three files deep.
Developer Florian hit this repeatedly. His fix wasn't a better model or a longer prompt. It was a guardrail: don't let the work start until we actually agree on what it is.
So he built /grill-me — a slash command for Claude Code that's now part of an open-source kit you can install today.
What It Means For You — Catch Misalignment Before It Costs You
When you run /grill-me, instead of diving into implementation, Claude interviews you one question at a time:
- Each question comes with Claude's recommended answer and the trade-off behind it, so you're reacting to a concrete proposal, not staring at a blank prompt.
- One question per turn. No wall of ten questions you'll half-answer.
- No plan gets written until you say "alignment complete."
That last rule is the whole point. The command is structurally forbidden from producing an implementation plan until you explicitly release it. It can't sprint ahead. It has to surface the decisions — the ambiguous requirement, the unspoken default, the fork in the architecture — and get a real answer out of you first.
The effect: all the expensive disagreements happen in cheap turns of conversation, before a single line of code exists. The drift, the rework, the "wait, that's not what I meant" — caught at the point where catching them costs a sentence instead of a rebuild.
Why one question at a time, each with a recommendation? A batch of questions gets shallow answers; a single sharp question with a proposed default gets a real decision. And the recommendation does double duty — it forces Claude to commit to a position, which drags its assumptions into the open where you can veto them, instead of burying them inside a plan.
Try It Now — Install and Run /grill-me
The kit is Florian's Claude Code Kit — pure Node, zero dependencies, on macOS, Linux, and Windows. The installer merges into your ~/.claude without clobbering anything you already have:
git clone https://github.com/FlorinI/Florians-Claude-Code-Kit.git
cd Florians-Claude-Code-Kit
node install.mjs # --dry-run to preview, uninstall to remove exactly what it added
Then run /grill-me before your next non-trivial task and let it interview you.
The Other Guardrails in the Kit
/grill-me lives in a small kit of these things, all the same philosophy — catch a specific failure at its cheapest point:
/handoverguards continuity. A session piles up context the next one can't see;/handoverdumps that state to a file the next session picks up automatically. You stop losing the thread between sessions.- The status line guards cost and context — it forecasts what your next turn will cost and warns you before an auto-compaction quietly drops half your context.
- The
rcaskill guards debugging: a falsifiable hypothesis and a disconfirming check before any fix, so you don't confidently repair the wrong cause. It right-sizes itself — a quick inline diagnosis for a cheap, reversible bug; a full documented root-cause analysis when the fix gates something expensive or irreversible.
None of these is a complete answer to anything. Together they're a few guardrails for the failures you hit most.
Why This Matters for Your Claude Code Workflow
The pattern worth stealing even if you never touch this command: make alignment a gate, not a vibe.
When you're running Claude Code in auto mode — which excels at whole-task autonomy — the risk of building the wrong thing increases because you're not watching every decision. A guardrail like /grill-me gives you confidence to use auto mode more aggressively, knowing the expensive misalignments are caught before they become expensive rewrites.
It's MIT, maintained best-effort in spare time. If a guardrail you wish existed is missing — and many are — the repo's open.
Source: news.google.com
