Recipes, ready to hand over.
Each is a real build, distilled: principles, contracts and scars an AI agent germinates back into the capability — on its own stack, in a repository that has never seen yours. New to the idea? What a recipe is →
Every recipe here is sealed — its bytes hash (sha256) to a value committed in the public registry — and gate-passed, re-checked on every push. Verified in CI ↗
Trust you can recompute — and honesty about the rest.
Two claims on every recipe are mechanical and public. A third that isn't real yet gets no badge — a decorative trust mark is worse than none.
Each recipe's exact bytes hash (SHA-256) to a fingerprint committed in the public registry. Open any recipe and click the seal — your browser refetches the source and the registry from GitHub and recomputes the hash. Nothing to trust from this site.
sporo lint checks every recipe against the genre — the eleven sections in order, neutrality (no leaked paths or product names), and earned scars — on every push. The green run ↗ is the proof.
No "scanned for prompt injection" or "verified publisher" mark — those need a real scan and cryptographic attestation we haven't built. When they exist they'll be earned, not decorative. A recipe is still text an agent reads: audit the prose before you run it.