SecretRefs into an in-memory runtime snapshot — far safer than plaintext credentials in config or prompts. Secret hygiene must precede any API-heavy skill.exec, browser, web_fetch, and web_search as high-risk. Restrict these explicitly to trusted agents or allowlists before they're ever invoked.memory_search and memory_get. Highly auditable, useful, and significantly less dangerous than any action skill.rg.write/edit/apply_patch in what gets containerized.env and apiKey declarations before install — these map directly to secrets injected into your host process.rg for grep workflows.SecretRef resolution into in-memory snapshots and explains how skills.entries.*.env and apiKey surface in the host process per agent turn.skills.entries.*.env and apiKey values end up in the host process for that agent turn. Secret hygiene is architectural, not operational.