refactor(team): add fast-advance notification and knowledge transfer protocol

- team-worker: add fast_advance message bus log after spawning successor,
  closing coordinator state blind spot during fast-advance
- team-worker: add Knowledge Transfer section with upstream loading,
  downstream publishing, and context_accumulator conventions
- role-spec-template: add Knowledge Transfer Protocol with Transfer
  Channels table and shared-memory.json namespaced write convention
- monitor.md (v2+v5): add fast-advance reconciliation step reading
  fast_advance messages, add State Sync section for coordinator wake
- lifecycle-v5 SKILL.md: update cadence diagram with fast_advance log

Author: catlog22

.claude/agents/team-worker.md

@@ -404,6 +404,48 @@ Write discoveries to corresponding wisdom files:
 
 ---
 
+## Knowledge Transfer
+
+### Upstream Context Loading (Phase 2)
+
+When executing Phase 2 of a role-spec, the worker MUST load available cross-role context:
+
+| Source | Path | Load Method |
+|--------|------|-------------|
+| Upstream artifacts | `<session>/artifacts/*.md` | Read files listed in task description or dependency chain |
+| Shared memory | `<session>/shared-memory.json` | Read and parse JSON |
+| Wisdom | `<session>/wisdom/*.md` | Read all wisdom files |
+| Exploration cache | `<session>/explorations/cache-index.json` | Check before new explorations |
+
+### Downstream Context Publishing (Phase 4)
+
+After Phase 4 verification, the worker MUST publish its contributions:
+
+1. **Artifact**: Write deliverable to `<session>/artifacts/<prefix>-<task-id>-<name>.md`
+2. **shared-memory.json**: Read-merge-write under role namespace
+   ```json
+   { "<role>": { "key_findings": [...], "decisions": [...], "files_modified": [...] } }
+   ```
+3. **Wisdom**: Append new patterns to `learnings.md`, decisions to `decisions.md`, issues to `issues.md`
+
+### Inner Loop Context Accumulator
+
+For `inner_loop: true` roles, `context_accumulator` is maintained in-memory:
+
+```
+context_accumulator.append({
+  task: "<task-id>",
+  artifact: "<output-path>",
+  key_decisions: [...],
+  summary: "<brief>",
+  files_modified: [...]
+})
+```
+
+Pass the full accumulator to each subsequent task's Phase 3 subagent as `## Prior Context`.
+
+---
+
 ## Message Bus Protocol
 
 Always use `mcp__ccw-tools__team_msg` for logging. Parameters:

.claude/skills/team-coordinate-v2/specs/role-spec-template.md

@@ -134,3 +134,46 @@ Coordinator MAY reference these patterns when composing Phase 2-4 content for a
 - Phase 2: Detect test framework + identify changed files from upstream
 - Phase 3: Run test-fix cycle — iteration count and strategy determined by task
 - Phase 4: Verify pass rate + coverage (Behavioral Traits) + update shared-memory
+
+---
+
+## Knowledge Transfer Protocol
+
+How context flows between roles. Coordinator MUST reference this when composing Phase 2 of any role-spec.
+
+### Transfer Channels
+
+| Channel | Scope | Mechanism | When to Use |
+|---------|-------|-----------|-------------|
+| **Artifacts** | Producer -> Consumer | Write to `<session>/artifacts/<name>.md`, consumer reads in Phase 2 | Structured deliverables (reports, plans, specs) |
+| **shared-memory.json** | Cross-role | Read-merge-write `<session>/shared-memory.json` | Key findings, decisions, metadata (small, structured data) |
+| **Wisdom** | Cross-task | Append to `<session>/wisdom/{learnings,decisions,conventions,issues}.md` | Patterns, conventions, risks discovered during execution |
+| **context_accumulator** | Intra-role (inner loop) | In-memory array, passed to each subsequent task in same-prefix loop | Prior task summaries within same role's inner loop |
+| **Exploration cache** | Cross-role | `<session>/explorations/cache-index.json` + per-angle JSON | Codebase discovery results, prevents duplicate exploration |
+
+### Phase 2 Context Loading (role-spec must specify)
+
+Every generated role-spec Phase 2 MUST declare which upstream sources to load:
+
+```
+1. Extract session path from task description
+2. Read upstream artifacts: <list which artifacts from which upstream role>
+3. Read shared-memory.json for cross-role decisions
+4. Load wisdom files for accumulated knowledge
+5. For inner_loop roles: load context_accumulator from prior tasks
+6. Check exploration cache before running new explorations
+```
+
+### shared-memory.json Usage Convention
+
+- **Read-merge-write**: Read current content -> merge new keys -> write back (NOT overwrite)
+- **Namespaced keys**: Each role writes under its own namespace: `{ "<role_name>": { ... } }`
+- **Small data only**: Key findings, decision summaries, metadata. NOT full documents
+- **Example**:
+  ```json
+  {
+    "researcher": { "key_findings": [...], "scope": "..." },
+    "writer": { "documents_created": [...], "style_decisions": [...] },
+    "developer": { "files_changed": [...], "patterns_used": [...] }
+  }
+  ```

.claude/skills/team-lifecycle-v5/SKILL.md

@@ -192,7 +192,9 @@ Beat Cycle (single beat)
   Fast-Advance (skips coordinator for simple linear successors)
 ======================================================================
   [Worker A] Phase 5 complete
-    +- 1 ready task? simple successor? --> spawn team-worker B directly
+    +- 1 ready task? simple successor?
+    |   --> spawn team-worker B directly
+    |   --> log fast_advance to message bus (coordinator syncs on next wake)
     +- complex case? --> SendMessage to coordinator
 ======================================================================
 ```

.claude/skills/team-lifecycle-v5/roles/coordinator/commands/monitor.md

@@ -59,7 +59,12 @@ Receive callback from [<role>]
       +- None completed -> STOP
 ```
 
-**Fast-advance awareness**: Check if next task is already `in_progress` (fast-advanced by worker). If yes -> skip spawning, update active_workers.
+**Fast-advance reconciliation**: When processing any callback or resume:
+1. Read recent `fast_advance` messages from team_msg (type="fast_advance")
+2. For each: add spawned successor to `active_workers` if not already present
+3. Check if expected next task is already `in_progress` (fast-advanced)
+4. If yes -> skip spawning (already running)
+5. If no -> normal handleSpawnNext
 
 ---
 
@@ -205,6 +210,13 @@ Detect orphaned in_progress task (no active_worker):
   +- Reset to pending -> handleSpawnNext
 ```
 
+### Fast-Advance State Sync
+
+On every coordinator wake (handleCallback, handleResume, handleCheck):
+1. Read team_msg entries with `type="fast_advance"` since last coordinator wake
+2. For each entry: sync `active_workers` with the spawned successor
+3. This ensures coordinator's state reflects fast-advance decisions even before the successor's callback arrives
+
 ### Consensus-Blocked Handling
 
 ```