Agent Decision Receipts

Overview

A log says an action happened. A receipt is tamper-evident: it records who, what, and under which policy, and it is signed, so any later edit breaks the signature. This skill mints one for a consequential agent action and verifies it later from the certificate alone: no database, no network, no trusting the issuer.

The crypto is not in this skill. It is the open-source OpenAgentOntology receipt primitive (Apache-2.0), which signs every receipt with Ed25519 and the post-quantum legs ML-DSA-65 (FIPS 204) + SLH-DSA (FIPS 205) when the post-quantum backend is installed. This skill is the decision layer: when to mint, what to put in, how to verify. One install, no per-skill crypto.

Three decisions, nothing else:

1. Does this action need a receipt? — side-effecting + consequential + later-provable = yes.
2. Mint the receipt — build the action manifest, sign it with the OAO primitive.
3. Verify it — recompute the hash, check each signature leg, from the cert alone.

This skill is NOT log analysis. Logs describe what happened and can be silently edited. A receipt is minted before/at execution and breaks if edited. Use logs for debugging; use receipts for evidence.

This skill is NOT a hosted notary. It mints a LOCAL, self-signed receipt anyone can verify offline. Cross-organization verification (one org proving to another) is a separate hosted service, out of scope here.

This skill is NOT a legal opinion. It produces evidence shaped to support FRE 902(13)/(14)-style certification and EU AI Act Article 12 record-keeping. Whether a given receipt is admitted is a question for counsel.