fix: harden generated agent platform access

agent_builder/skills/agent-quality-review/SKILL.md

@@ -30,8 +30,13 @@ Check these items:
   arguments.
 - The public schema is small and stable. No unbounded command strings, hidden
   prompt fragments, or provider credentials as public inputs.
-- The implementation reads `ctx.llm` when `llm_provisioning` is
-  `CALLER_PROVIDED`.
+- The implementation reads `ctx.llm` for both `CALLER_PROVIDED` and
+  `PLATFORM` LLM provisioning.
+- Generated/user agents should default to
+  `llm_provisioning = LLMProvisioning.CALLER_PROVIDED` and
+  `Pricing(..., caller_pays_llm=True, ...)`. If the user explicitly wants
+  platform-paid LLM usage, `LLMProvisioning.PLATFORM` is acceptable only if
+  the code still uses `ctx.llm` and never reads LiteLLM/provider keys directly.
 - Any use of DeepAgents file tools passes `backend=ctx.workspace_backend()`.
 - Any project skills are seeded into the backend and passed with
   `skills=skill_sources or None`.
@@ -81,8 +86,8 @@ frontend:
 For React/Vite frontends, expect `frontend/package.json`,
 `frontend/vite.config.js`, `frontend/src/App.jsx`, and `frontend/src/a2a.js`.
 For static frontends, expect `frontend/dist/index.html`. The browser code must
-not contain platform secrets, provider keys, hard-coded deployment URLs, or
-private stack details. It should load `/app/config.json`, use
+not contain platform secrets, provider keys, LiteLLM keys, hard-coded deployment
+URLs, or private stack details. It should load `/app/config.json`, use
 `/app/a2a-client.js` or generated config endpoints, and call only the public
 `@skill` schemas.