1. Create shared journal file:
   thoughts/shared/journal/YYYY-MM-DD-<topic>-council.md

2. Define section ownership per agent

3. Spawn agents IN PARALLEL with:
   - Assigned research documents
   - MCPs to query (deepwiki, exa)
   - Section template
   - Journal location

Research → Journal → Spec → ADR → WBS

# <Topic> Architecture Council — Shared Journal

**Session**: YYYY-MM-DD
**Purpose**: <Goal of the council>
**Input**: <Research documents count>
**Output**: <Target spec location>

---

## Council Members

| Name | Domain | Research Docs | Section Ownership |
|------|--------|---------------|-------------------|
| Schema-Sage | Types | doc1.md, doc2.md | Section 3 |
| ... | ... | ... | ... |

---

## Protocol

1. Each agent reads their assigned research documents
2. Extract patterns relevant to their section
3. Write findings to their thread below (append only)
4. When ready, write "READY FOR SYNTHESIS"
5. Architect-Prime synthesizes all threads into final spec

---

## Thread: Schema-Sage

### Executive Summary
[Summary of findings]

### 1. Pattern Category
[Detailed findings with code examples]

### Recommendations for v3
[Actionable recommendations]

---

**READY FOR SYNTHESIS**

---

## Thread: Repo-Maven
[...]

## Thread: Event-Oracle
[...]

## Synthesis: Architect-Prime
[Final integration]

You are Schema-Sage, the council's type system and validation specialist.

**Your Domain**: Schema patterns, branded types, validation, TaggedClass, transforms

**Research Documents**:
- <list of assigned docs>

**MCPs to Query**:
- deepwiki: Effect-TS/effect (Schema module)

**Output Location**: <journal-path>#Thread: Schema-Sage

**Protocol**:
1. Read your assigned research documents
2. Query deepwiki to verify any uncertain patterns
3. Extract patterns with code examples
4. Write to your journal thread
5. Signal "READY FOR SYNTHESIS" when complete

mcp__deepwiki__ask_question
  repoName: "Effect-TS/effect"
  question: "Is my understanding of [PATTERN] correct? I believe..."

mcp__exa__search
  query: "ISA-95 manufacturing operations management event sourcing"

mcp__playwright__navigate
  url: "https://www.isa.org/standards-and-publications/..."

I'll convene the Architecture Council to analyze this decision.

**Creating shared journal**: thoughts/shared/journal/2026-01-25-v3-iiot-council.md

**Spawning council members in parallel**:

1. Schema-Sage → IIoT schema patterns
2. Repo-Maven → Repository patterns analysis  
3. Event-Oracle → Event sourcing fit assessment
4. Entity-Weaver → Entity/aggregate patterns
5. Infra-Smith → Database and infrastructure

[Agents run in parallel, writing to journal]

**Synthesis phase**: Architect-Prime integrating findings...

**Deliverables**:
- Journal: thoughts/shared/journal/2026-01-25-v3-iiot-council.md
- Spec: thoughts/shared/specs/2026-01-25-v3-service-architecture.md
- ADR: assets/documents/iiot/ADR-0012-event-sourcing-boundaries.md

// Phase 1: Research (parallel)
const schemaSage = Task.create({ name: "schema-sage-research", ... })
const repoMaven = Task.create({ name: "repo-maven-research", ... })
const eventOracle = Task.create({ name: "event-oracle-research", ... })

// Phase 2: Synthesis (depends on all Phase 1)
const synthesis = Task.create({
  name: "architect-prime-synthesis",
  blockedBy: [schemaSage.id, repoMaven.id, eventOracle.id],
  ...
})

// Phase 3: ADR (depends on synthesis)
const adr = Task.create({
  name: "write-adr",
  blockedBy: [synthesis.id],
  ...
})

❌ Agents write directly to spec
✅ Agents write to journal, Prime synthesizes to spec

❌ Run Schema-Sage, wait, run Repo-Maven, wait...
✅ Spawn all agents in parallel

❌ "I believe this is the pattern..."
✅ "[VERIFIED via deepwiki] The current pattern is..."

❌ "Event sourcing seems right for IIoT"
✅ "[VERIFIED via ISA-95] Event sourcing aligns with activity model..."