fix: generate agents with platform LLM grants

README.md

@@ -14,7 +14,7 @@ The single `build(name, prompt)` skill:
    - `a2apack-agent-authoring` — how to shape `agent.py`, public `@skill`
      schemas, runtime metadata, pricing, resources, and auth
    - `deepagents-implementation-patterns` — concrete `create_deep_agent`
-     wiring for caller LLMs, skills, tools, and subagents
+     wiring for `ctx.llm` credentials, skills, tools, and subagents
    - `workspace-artifact-safety` — workspace grants, artifacts, bounded
      subprocesses, and scope expansion
    - `agent-quality-review` — pre-sandbox and pre-deploy checks for generated
@@ -57,8 +57,9 @@ marketplace — the dashboard already surfaces these on the agent card.
 
 `$0.10 / call` during the current pricing model. The builder uses your
 selected LLM creds when present and falls back to a scoped platform grant.
-The deployed agent is yours forever; subsequent invocations of your agent run on
-their own pricing (whatever you set when generating it).
+The deployed agent is yours forever; subsequent invocations of a generated LLM
+agent default to scoped platform LLM grants unless you explicitly generate a
+BYOK/caller-paid agent.
 
 ## How to call it