oh-my-customcode 0.35.1 → 0.35.3

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-customcode",
-  "version": "0.35.1",
+  "version": "0.35.3",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/rules/MUST-agent-design.md

@@ -165,10 +165,10 @@ Use `context: fork` for skills that orchestrate multi-agent workflows. Cap at **
 | Multi-agent coordination patterns | Single-agent reference skills |
 | Task decomposition/planning | External tool integrations |
 
-Current skills with `context: fork` (9/10 cap):
+Current skills with `context: fork` (8/10 cap):
 - secretary-routing, dev-lead-routing, de-lead-routing, qa-lead-routing
 - dag-orchestration, task-decomposition, worker-reviewer-pipeline
-- pipeline-guards, deep-plan
+- pipeline-guards
 
 ## Naming
 

package/templates/.claude/rules/MUST-orchestrator-coordination.md

@@ -6,6 +6,8 @@
 
 The main conversation is the **sole orchestrator**. It uses routing skills to delegate tasks to subagents via the Agent tool (formerly Task tool). Subagents CANNOT spawn other subagents.
 
+**Agent Teams Exception**: Agent Teams members are peers, not hierarchical subagents. Teams members CAN spawn sub-agents via the Agent tool to execute complex workflows (e.g., research teams, verification teams). This enables Teams-compatible skills like `/research` and `/deep-plan` to run inside Team members. The Teams member acts as a local orchestrator for its own sub-tasks.
+
 **The orchestrator MUST NEVER directly write, edit, or create files. ALL file modifications MUST be delegated to appropriate subagents.**
 
 ## Self-Check (Before File Modification)

package/templates/.claude/rules/SHOULD-memory-integration.md

@@ -157,7 +157,7 @@ User signals session end
        3. Return formatted summary to orchestrator
   → Orchestrator performs MCP saves directly:
        1. claude-mem save (if available via ToolSearch)
-       2. episodic-memory verification (if available via ToolSearch)
+       (episodic-memory auto-indexes after session — no action needed)
   → Orchestrator confirms to user
 ```
 
@@ -170,7 +170,7 @@ MCP tools (claude-mem, episodic-memory) are **orchestrator-scoped** and not inhe
 | Session summary collection | sys-memory-keeper | Domain expertise in memory formatting |
 | Native auto-memory (MEMORY.md) | sys-memory-keeper | Has Write access to memory directory |
 | claude-mem MCP save | Orchestrator | MCP tools only available at orchestrator level |
-| episodic-memory MCP verification | Orchestrator | MCP tools only available at orchestrator level |
+| episodic-memory | Automatic | Conversations are auto-indexed after session ends — no manual action needed |
 
 ### Dual-System Save
 
@@ -178,7 +178,7 @@ MCP tools (claude-mem, episodic-memory) are **orchestrator-scoped** and not inhe
 |--------|-------|------|--------|----------|
 | Native auto-memory | sys-memory-keeper | Write | Update MEMORY.md with session learnings | Yes |
 | claude-mem | Orchestrator | `mcp__plugin_claude-mem_mcp-search__save_memory` | Save session summary with project, tasks, decisions | No (best-effort) |
-| episodic-memory | Orchestrator | `mcp__plugin_episodic-memory_episodic-memory__search` | Verify session is indexed for future retrieval | No (best-effort) |
+| episodic-memory | Automatic | (auto-indexed) | No action needed — conversations are indexed automatically after session ends | N/A |
 
 ### Session-End Self-Check (MANDATORY)
 
@@ -194,12 +194,10 @@ MCP tools (claude-mem, episodic-memory) are **orchestrator-scoped** and not inhe
 ║     YES → Continue (even if it failed)                           ║
 ║     NO  → ToolSearch + save now                                  ║
 ║                                                                   ║
-║  3. Did I attempt episodic-memory verification?                  ║
-║     YES → Continue (even if it failed)                           ║
-║     NO  → ToolSearch + verify now  ← THIS IS THE COMMONLY       ║
-║           SKIPPED STEP. DO NOT SKIP IT.                          ║
+║  Note: episodic-memory auto-indexes conversations after session  ║
+║  ends. No manual action needed — do NOT search as "verification" ║
 ║                                                                   ║
-║  ALL THREE must be attempted before confirming to user.          ║
+║  BOTH steps must be completed before confirming to user.         ║
 ║  "Attempted" means called the tool — failure is OK, skipping     ║
 ║  is NOT.                                                          ║
 ╚══════════════════════════════════════════════════════════════════╝
@@ -209,5 +207,4 @@ MCP tools (claude-mem, episodic-memory) are **orchestrator-scoped** and not inhe
 
 - MCP saves are **non-blocking**: memory failure MUST NOT prevent session from ending
 - If claude-mem unavailable: skip, log warning
-- If episodic-memory unavailable: skip, log warning
-- If both unavailable: warn user, proceed with session end
+- episodic-memory: no action needed (auto-indexed after session)

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.35.1",
+  "version": "0.35.3",
   "lastUpdated": "2026-03-14T00:00:00.000Z",
   "components": [
     {