docs(tac): add agent multiplexer guidance

Fold cmux and herdr agent-multiplexer patterns into TAC loop-engineering guidance. Treat the primary agent as orchestrator over panes/tabs via CLI + socket (no MCP required), pane as isolation boundary, and multiplexer state (working/idle/blocked) as the feedback signal. Keep TAC invariants: deploy stays signed-action-only via git-proxy:8099/deploy, peer agents remain insider-threat candidates with least privilege and receipts, multiplexer driving shells does not grant a raw-command deploy path.

pipeline/test_loop_engineering_meta_prompt.py

@@ -48,6 +48,13 @@ def test_loop_engineering_meta_prompt_locks_safety_fields():
         "human approval before any action with business",
         "attestation that a human reviewed output",
         "YouTube `yvJYw2gR0cU`",
+        "Agent multiplexer note",
+        "Primary agent = orchestrator",
+        "Pane = isolation boundary",
+        "CLI + socket, not MCP",
+        "git-proxy:8099/deploy",
+        "WAFUMBLOjHo",
+        "herdr.dev",
         "External research anchors",
         "NVIDIA Secure Agent Workspace",
         "Infisical Agent Vault",

plans/meta-prompts/loop_engineering.md

@@ -169,3 +169,23 @@ Use this when it fits:
 - `40-ship/` — signed deploy request, outcome, rollback notes.
 
 Reference: arXiv 2603.16021, "Interpretable Context Methodology: Folder Structure as Agentic Architecture".
+
+## Agent multiplexer note
+
+Terminal multiplexers built for AI coding agents (cmux, herdr) prove a thesis TAC should learn from: one primary agent can stand up, drive, and tear down a fleet of peer agents and terminals entirely through CLI + socket, with no MCP server required. The agent treats panes/tabs as the unit of parallelism and multiplexer state (working/idle/blocked) as the feedback signal.
+
+Use this pattern when it fits:
+
+- **Primary agent = orchestrator** — it opens workspaces, sends prompts to peers, observes output, and tears down. Peers are real terminals, not framework objects.
+- **Pane = isolation boundary** — each peer runs in its own real terminal on its own cwd/branch; the multiplexer keeps sessions alive over SSH and across laptop sleep.
+- **State awareness** — working/idle/blocked lets the orchestrator gate handoffs on real progress, not on timeouts.
+- **CLI + socket, not MCP** — orchestration is driven by shell commands and a Unix socket; this keeps the surface small and scriptable.
+
+TAC invariants still hold when a multiplexer is the substrate:
+
+- panes that touch deploy still route through `git-proxy:8099/deploy` signed actions — the multiplexer is not a deploy bypass;
+- peer agents are insider-threat candidates (see Insider-threat model note): least privilege, no raw secrets, sandboxed execution, human approval for business-impacting actions;
+- every peer spawn/teardown and tool call stays receipted;
+- the primary agent must not gain a raw-command deploy path just because it can drive shells.
+
+References: cmux fleet-driving prompts (`github.com/disler/learning-cmux-with-agents`), herdr agent multiplexer (`herdr.dev`), cmux + Claude Code + Pi demo (YouTube `WAFUMBLOjHo`).