snow-flow 4.5.19 → 4.5.20

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/dist/cli.js +24 -6
  2. package/package.json +1 -1
package/dist/cli.js CHANGED
@@ -1054,12 +1054,30 @@ Your Queen Agent orchestration is successful when:
1054
1054
 
1055
1055
  ## 💡 Queen Agent Best Practices
1056
1056
 
1057
- 1. **Spawn agents concurrently** when tasks are independent
1058
- 2. **Use Memory with JSON.stringify/parse** to avoid key collisions
1059
- 3. **Update TodoWrite** frequently for visibility
1060
- 4. **Monitor agent health** and restart if needed
1061
- 5. **Validate outputs** before marking complete
1062
- 6. **Store all decisions** in Memory for audit trail
1057
+ ### **Workflow Orchestration:**
1058
+ 1. **NEVER parallel foundation work** - research, planning, architecture must be sequential
1059
+ 2. **Foundation → Development → Validation** - strict phase progression
1060
+ 3. **Parallel development only** after foundation complete
1061
+ 4. **Use Memory to share foundation outputs** to development agents
1062
+ 5. **Coordinate parallel agents** through shared Memory state
1063
+
1064
+ ### **Agent Coordination:**
1065
+ 1. **Sequential Agents**: researcher → planner → architect (must wait for each other)
1066
+ 2. **Parallel Agents**: widget-developer + script-writer + ui-builder (can work simultaneously)
1067
+ 3. **Foundation Dependencies**: All development agents depend on architecture completion
1068
+ 4. **Shared Memory**: Store research findings, plans, architecture for all agents to access
1069
+
1070
+ ### **Task Management:**
1071
+ 1. **Update TodoWrite** with phase progression
1072
+ 2. **Mark foundation complete** before starting development
1073
+ 3. **Monitor parallel agent progress** and coordinate conflicts
1074
+ 4. **Validate outputs** before marking complete
1075
+ 5. **Store all decisions** in Memory for audit trail
1076
+
1077
+ ### **Example Workflow:**
1078
+ **Phase 1 (Sequential):** researcher → architect → planner
1079
+ **Phase 2 (Parallel):** widget-dev + script-writer + ui-builder (use foundation outputs)
1080
+ **Phase 3 (Parallel):** tester + reviewer + documenter (validate development outputs)
1063
1081
 
1064
1082
  ## 🚀 Begin Orchestration
1065
1083
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "snow-flow",
3
- "version": "4.5.19",
3
+ "version": "4.5.20",
4
4
  "description": "Conversational ServiceNow development platform using Claude Code. Multi-agent orchestration with 20+ MCP servers providing 200+ ServiceNow tools for comprehensive platform development.",
5
5
  "main": "dist/index.js",
6
6
  "type": "commonjs",