One spec, 30 correct formats
The Universal Core is written once. Everything below is a deterministic render of it — no second model call, no chance for two files to contradict each other, and no generic “build kit” that fits nothing properly.
30
platforms
Every one gets the artifact it actually parses
1
with hard ceilings
Rendered under the limit and verified by a test, not by hope
2
obsolete formats avoided
Formats these tools stopped reading — we never emit them
Repo agents
These read files committed to your project. Get the layout wrong and the agent silently ignores everything you wrote.
CLAUDE.md + AGENTS.mdLives at the repo root, in version control. One long prompt rots the context instead.
.cursor/rules/*.mdcDirectory format. The single-file .cursorrules is obsolete and should not be generated.
.windsurf/rules/*.md.github/copilot-instructions.mdOne compact file. Rules scattered across several files never fire.
AGENTS.mdWhere the AGENTS.md standard originated.
GEMINI.md + AGENTS.md.kiro/specs/{slug}/requirements.md · design.md · tasks.mdSpec-first: it writes no code until you approve the plan. The ideal target for us — acceptance criteria in EARS format.
AGENTS.mdAGENTS.md.clinerules + AGENTS.mdAGENTS.md + knowledgeAGENTS.mdAGENTS.mdCONVENTIONS.mdPrompt-to-app builders
No repo — they take a founding prompt and iterate. Each one digests a different amount, and going over the ceiling gets you truncated without warning.
Knowledge Base + founding promptTheir own docs call the Knowledge Base the single most effective thing you can set up. A PRD buried in the prompt gets forgotten.
6-part founding promptPurpose · Features · User Flow · Data Model · UI Style · Extras. Go past 400 words and the model chokes.
Single full-stack promptAgent-segmented brief (UI / logic / DB / API / QA)A PM agent validates the requirements — the platform hungriest for structured input.
replit.md + numbered task listDo not ask for the whole app in one go; it stops halfway.
Per-screen component prompts + design tokensFounding prompt + iterationsFounding promptPrompt + Python backend briefFounding prompt (React)Founding promptFounding promptFounding promptMobile-first
These design screens first, then hand off to engineering. We ship the handoff bridge too, so the repo agent doesn't redo your design.
React Native + Expo prompt + screen flowScreen list + brand tokens + handoff bridgeWe also emit a handoff file so you can move to Cursor or Claude Code after export.
Visual + AI brief (Flutter)What we deliberately do not generate
Formats these tools have moved on from. Shipping them looks like more value and produces exactly nothing — the tool never reads the file.
- Cursor — no
.cursorrules, we emit.cursor/rules/*.mdcinstead - Windsurf — no
.windsurfrules, we emit.windsurf/rules/*.mdinstead
Why this is one price, not thirty
The expensive part is the core: the evidence, the counter-evidence, the scope boundary. Rendering that into a platform's file layout is template work, so it costs 5 credits and you are never charged twice for the same platform. Pick as many as you want to try.