agent-decision-receipts

原文涵盖的主题

• Agent Decision Receipts
• Overview
• Quick Start
• Core Workflow
• Decision 1: Does this action need a receipt?
• Decision 2: Mint the receipt
• Decision 3: Verify it
• Anti-Patterns

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

这里只展示节选，请以完整原文和当前要求为准。