Agent-safe workflows

Keep plaintext out of prompts, diffs, and terminal output agents can observe.

Avoid plaintext get/read in agent context Files agents can read API_KEY=authsia://… safe to inspect Approved exec JIT or automation secret in child only

Without JIT

Unlock as a human or supply a scoped automation credential. Agents must stop when access is missing — not fall back to plaintext commands.

With JIT

Confirmed agent context uses scoped folder grants for exec and list. Deny or expiry ends the path.

Need the commands?

Agent launch, access create/revoke, and guarded shell live in the CLI guides.

Open agent JIT