docs(tac): add activity-mode role guidance

Capture the AI-era role archetype discourse as delivery activity modes rather than permanent job titles. Add Prototyper, Grower, Sweeper, Reviewer/Taster, Architect/Primitive keeper, and Operator/SRE invariants while preserving the guardrail that role collapse does not make expertise obsolete.

pipeline/test_loop_engineering_meta_prompt.py

@@ -30,6 +30,12 @@ def test_loop_engineering_meta_prompt_locks_safety_fields():
         "model-timing assumptions",
         "deletion/simplification",
         "YouTube `P3KDebPTUrw`",
+        "Activity modes",
+        "Prototyper",
+        "Grower",
+        "Sweeper",
+        "Architect/Primitive keeper",
+        "role collapse means expertise is obsolete",
         "External research anchors",
         "NVIDIA Secure Agent Workspace",
         "Infisical Agent Vault",

plans/meta-prompts/loop_engineering.md

@@ -101,6 +101,19 @@ When implementation gets cheap, do not delete product discipline. Plans should u
 
 Reference: Lenny's Podcast, "OpenAI Codex lead on the new shape of product work" with Andrew Ambrosino (YouTube `P3KDebPTUrw`).
 
+## Activity modes note
+
+Treat AI-era role archetypes as activity modes in the delivery loop, not permanent job titles. A person or agent can move across modes, but each mode needs its own invariant:
+
+- **Prototyper** — creates options and working artifacts; invariant: stage is marked and prototype output cannot skip PRD/spec or receipts.
+- **Grower** — compounds a rough artifact into a durable product; invariant: every iteration preserves traceability, tests, and user/problem fit.
+- **Sweeper** — deletes, simplifies, migrates, and pays down prototype debt; invariant: complexity budget and deletion/simplification review are explicit.
+- **Reviewer/Taster** — applies human taste, systems thinking, security, and product judgment; invariant: production readiness requires review evidence, not vibes.
+- **Architect/Primitive keeper** — maintains shared primitives, interfaces, and harness boundaries; invariant: tools, credentials, deploy actions, and context sources stay governed.
+- **Operator/SRE** — keeps the loop running in production; invariant: observability, rollback, incident ownership, and revocation paths are named.
+
+Do not claim role collapse means expertise is obsolete. The safer claim is that boundaries flex while specialties, ownership, and best practices remain necessary.
+
 ## External research anchors
 
 Ground agent plans against external production guidance, not just video notes: