agent-native-experiencelisted

# Agent Native Experience Turn one product/docs prompt into an honest local assessment and, only with explicit approval, an Apostl execution proof. ## Contract Require: - target docs or product URL; - selected quickstart or journey; - observable activation event promised by that journey. Accept optionally: product API/OpenAPI, repository path, `llms.txt` sources, human observations, business metrics/owners, corpus exclusions, and a desired local/sample/full mode. Return one report using [report-contract.md](references/report-contract.md). Always distinguish static evidence, agent runtime evidence, human evidence, and unknown/not-run work. Never turn a fetch, signup, HTTP 200, workaround, or high score into activation proof. ## Run the workflow 1. State the journey, target agent/user, activation event, environment, mode, and plausible business consequence. Label unmeasured impact as a hypothesis with the metric and owner needed to validate it. 2. Read [rubric.v1.json](references/rubric.v1.json) and [sources.v1.json](references/sources.v1.json). Refresh drift-prone sources before calling guidance current; record URL, retrieval time, and version or commit. 3. Inventory `llms.txt`, `llms-full.txt`, sitemaps, navigation, API specs, and supplied sources. Canonicalize URLs, record redirects/auth/exclusions and content hashes, then freeze the corpus before full execution. 4. Run local non-mutating checks. Use AFDocs directly when available and retain i