What a cookbook holds, and what a recipe is.
A cookbook is the shelf every recipe in a project sits on. A recipe is the individual item on that shelf: a saved, repeatable procedure built once from Kitchen nodes, then run again on demand without being rebuilt from scratch. A cookbook holds recipes; a recipe holds nodes.
Building a recipe once and reusing it is the point of the split. Reasoning that would otherwise get redone by hand every session gets wired once on the Kitchen canvas — prompts, gates, asks, or the newer node kinds — and saved as a callable procedure. What ships to the catalog is exactly what a recipe run pulls back out, node for node.
The older three primitives, and the newer fifteen.
Every recipe is built from Kitchen nodes, and today those nodes come from two generations. The older vocabulary is three primitives — prompt, ask, gate — enough to chain a question, wait on an answer, and branch on a condition. It’s what most of the catalog is actually built from. The newer vocabulary is fifteen distinct v2 node kinds, built to cover more of what a recipe can do than prompt, ask, and gate ever tried to.
A recipe doesn’t have to touch the newer vocabulary to work. The three-primitive set closes plenty of loops on its own — a prompt that asks a question, a gate that waits for a yes — and nothing about the newer kinds retires it.
Three recipes, two built the older way.
Three recipes live in the catalog right now, confirmed by calling the running endpoint that serves them, not by counting a spec — this page makes that call on every render. Two of them are built entirely from the older three-primitive vocabulary: prompt, ask, gate covers the whole recipe, start to finish.
That leaves a real gap between what the catalog could look like and what it holds today. One recipe uses the newer vocabulary. The other two do the same job the older vocabulary has always done, and they do it fine. The newer node kinds are proven on one recipe, not standard across the catalog yet.
An earlier read of the catalog counted higher: eight additional “primitive” recipes, plus a recipe that wrote other recipes, a self-styled Chef’s Table. Neither was ever seeded into production. The correction landed as #12503, and the count it settled on was fourteen — true when it was written, and the reason this page no longer hard-codes a number. The catalog has been culled since. Whatever is above came off the endpoint just now.
scout-and-brief: fifteen nodes, every v2 kind, not yet run end to end.
One recipe in the catalog, scout-and-brief, is built differently from the other two. It runs fifteen nodes, and those fifteen nodes span all fifteen distinct v2 node kinds: not a sample of the newer vocabulary, the entire set, in one graph.
It’s dispatchable, and that’s confirmed by static analysis of its live graph: a check of the graph’s shape, not a completed run. Nobody has taken scout-and-brief start to finish in production yet. What’s verified is that it’s built correctly enough to; what’s not yet verified is what happens when it does.
What's actually in the catalog, read straight off the endpoint.
The count above didn’t come from a spec or a slide. It came from calling GET /api/cookbook/recipes on the running server and counting what came back: three recipes, two on the older vocabulary, scout-and-brief spanning the newer one. The catalog once carried a bigger number: eight extra “primitive” recipes and a recipe-writing “Chef’s Table” recipe, both confirmed never seeded (#12503). The corrected count is the one still standing.
| What was measured | The number |
|---|---|
| recipes in the live catalog | 3 |
| built from prompt, ask, gate only | 2 of 3 |
| recipes spanning all 15 v2 node kinds | 1 (scout-and-brief, 15 nodes) |
| scout-and-brief's dispatchability | confirmed by static analysis of the live graph, not yet run end to end |
| recipes an earlier count wrongly included | 8 “primitive” recipes + a recipe-writing “Chef’s Table” recipe, never seeded, per #12503 |
| source | GET /api/cookbook/recipes, called when this page rendered, plus #12503 for the earlier correction |
Common questions.
How many of the three recipes actually run today?
All three. The count isn’t a roadmap figure. It’s what GET /api/cookbook/recipes returns from the running server right now — this page calls that endpoint and prints what comes back. What varies between them is which vocabulary each one is built from: two close their loops with prompt, ask, gate, and one, scout-and-brief, runs all fifteen of the newer node kinds. scout-and-brief is dispatchable by static analysis, though nobody has taken it start to finish in production yet.
What makes a recipe different from a saved prompt?
A saved prompt is a block of text pasted back in each time. A recipe is a graph of Kitchen nodes — prompts, asks, gates, or the newer kinds — wired once, so asking, waiting, and branching are separate nodes doing their own job instead of one paragraph trying to do all three at once.
Is the older three-node vocabulary going away?
No sign of it. Two of the three recipes in the catalog run on prompt, ask, gate today, and nothing about the newer v2 node kinds retires that vocabulary. It’s simpler, not deprecated.