feat(opencode): complete MMA setup with conductor workflow

- Add product.md and product-guidelines.md to instructions for full context
- Configure MCP server exposing 27 tools (file ops, Python AST, git, web, shell)
- Add steps limits: tier1-orchestrator (50), tier2-tech-lead (100)
- Update Tier 2 delegation templates for OpenCode Task tool syntax

.opencode/agents/tier1-orchestrator.md

@@ -3,6 +3,7 @@ description: Tier 1 Orchestrator for product alignment, high-level planning, and
 mode: primary
 model: zai/glm-5
 temperature: 0.1
+steps: 50
 tools:
   write: false
   edit: false

.opencode/agents/tier2-tech-lead.md

@@ -3,6 +3,7 @@ description: Tier 2 Tech Lead for architectural design and track execution with
 mode: primary
 model: zai/glm-5
 temperature: 0.2
+steps: 100
 permission:
   edit: ask
   bash: ask
@@ -62,31 +63,59 @@ After completing each task:
 5. Update plan.md: Mark task `[x]` with commit SHA
 6. Commit plan update
 
-## Delegation Templates
+## Delegation via Task Tool
+
+OpenCode uses the Task tool for subagent delegation. Always provide surgical prompts with WHERE/WHAT/HOW/SAFETY structure.
 
 ### Tier 3 Worker (Implementation)
+Invoke via Task tool:
+- `subagent_type`: "tier3-worker"
+- `description`: Brief task name
+- `prompt`: Surgical prompt with WHERE/WHAT/HOW/SAFETY structure
+
+Example Task tool invocation for test creation:
+```
+description: "Write tests for cost estimation"
+prompt: |
+  Write tests for: cost_tracker.estimate_cost()
+  
+  WHERE: tests/test_cost_tracker.py (new file)
+  WHAT: Test all model patterns in MODEL_PRICING dict, assert unknown model returns 0
+  HOW: Use pytest, create fixtures for sample token counts
+  SAFETY: No threading concerns
+  
+  Use 1-space indentation for Python code.
 ```
-@tier3-worker
 
-Task: [Specific task description]
+Example Task tool invocation for implementation:
-
+```
-WHERE: file.py:line-range
+description: "Implement cost column in dashboard"
-WHAT: [Specific change description]
+prompt: |
-HOW: [API calls, patterns, data structures to use]
+  Implement: Add cost estimation column to token usage table
-SAFETY: [Thread-safety constraints if applicable]
+  
-
+  WHERE: gui_2.py:2685-2699 (_render_mma_dashboard)
-Use 1-space indentation for Python code.
+  WHAT: Extend table from 3 to 5 columns, add 'Model' and 'Est. Cost'
+  HOW: Use imgui.table_setup_column(), call cost_tracker.estimate_cost(model, input_tokens, output_tokens)
+  SAFETY: Read-only access to cost_tracker, no thread safety concerns
+  
+  Use 1-space indentation for Python code.
 ```
 
 ### Tier 4 QA (Error Analysis)
+Invoke via Task tool:
+- `subagent_type`: "tier4-qa"
+- `description`: "Analyze test failure"
+- `prompt`: Error output + explicit instruction "DO NOT fix - provide root cause analysis only"
+
+Example:
 ```
-@tier4-qa
+description: "Analyze cost estimation test failure"
-
+prompt: |
-Analyze this test failure and provide root cause analysis:
+  Analyze this test failure and provide root cause analysis:
-
+  
-[Test output or error log]
+  [paste test output here]
-
+  
-DO NOT fix - provide analysis only.
+  DO NOT fix - provide analysis only. Identify the specific line/condition causing failure.
 ```
 
 ## Phase Completion Protocol

opencode.json

@@ -11,10 +11,24 @@
   },
   "instructions": [
     "CLAUDE.md",
+    "conductor/product.md",
+    "conductor/product-guidelines.md",
     "conductor/workflow.md",
     "conductor/tech-stack.md"
   ],
   "default_agent": "tier2-tech-lead",
+  "mcp": {
+    "manual-slop": {
+      "type": "local",
+      "command": [
+        "C:\\Users\\Ed\\scoop\\apps\\uv\\current\\uv.exe",
+        "run",
+        "python",
+        "C:\\projects\\manual_slop\\scripts\\mcp_server.py"
+      ],
+      "enabled": true
+    }
+  },
   "agent": {
     "build": {
       "model": "zai/glm-5",