chore(agents): sync agent configs — model updates to nemotron-3-super

- Update agent model assignments (nemotron-3-ultra -> nemotron-3-super) across .kilo/agents, kilo-meta.json, kilo.jsonc, capability-index.yaml
- Sync agent descriptions in KILO_SPEC.md

.kilo/KILO_SPEC.md

@@ -296,10 +296,10 @@ User types `/plan` in Kilo interface to activate the command.
 
 | Command | Description | Model |
 |---------|-------------|-------|
-| `/plan` | Creates detailed task plans | ollama-cloud/deepseek-v4-pro |
+| `/plan` | Creates detailed task plans | ollama-cloud/nemotron-3-super |
 | `/ask` | Answers codebase questions | ollama-cloud/qwen3.5:397b |
 | `/debug` | Analyzes and fixes bugs | ollama-cloud/gpt-oss:20b |
-| `/code` | Quick code generation | ollama-cloud/deepseek-v4-pro |
+| `/code` | Quick code generation | ollama-cloud/nemotron-3-super |
 
 ---
 
@@ -528,51 +528,51 @@ Provider availability depends on configuration. Common providers include:
 
 | Agent | Role | Model |
 |-------|------|-------|
-| `@IntakeAgent` | Conversational interface — receives natural language from users, clarifies ambiguous requirements, produces structured tasks for orchestrator. | ollama-cloud/nemotron-3-ultra |
+| `@IntakeAgent` | Conversational interface — receives natural language from users, clarifies ambiguous requirements, produces structured tasks for orchestrator. | ollama-cloud/nemotron-3-super |
-| `@ContextCompressor` | Intelligently manages token budget by summarizing conversation history, preserving critical State, and pruning redundant information before context overflow occurs. | ollama-cloud/nemotron-3-ultra |
+| `@ContextCompressor` | Intelligently manages token budget by summarizing conversation history, preserving critical State, and pruning redundant information before context overflow occurs. | ollama-cloud/nemotron-3-super |
-| `@PatternMatcher` | Proactively finds similar successful solutions from past projects BEFORE work starts, providing recommendations instead of just duplicate detection. | ollama-cloud/nemotron-3-ultra |
+| `@PatternMatcher` | Proactively finds similar successful solutions from past projects BEFORE work starts, providing recommendations instead of just duplicate detection. | ollama-cloud/nemotron-3-super |
-| `@StakeholderBridge` | Translates technical outputs into business language for non-technical stakeholders, generates executive summaries and progress reports. | ollama-cloud/nemotron-3-ultra |
+| `@StakeholderBridge` | Translates technical outputs into business language for non-technical stakeholders, generates executive summaries and progress reports. | ollama-cloud/nemotron-3-super |
 | `@RequirementRefiner` | Converts vague ideas and bug reports into strict User Stories with acceptance criteria checklists. | ollama-cloud/minimax-m3 |
 | `@HistoryMiner` | Analyzes git history to find duplicates and past solutions, preventing regression and duplicate work. | ollama-cloud/deepseek-v4-flash:0731 |
 | `@SystemAnalyst` | Designs technical specifications, data schemas, and API contracts before implementation. | ollama-cloud/minimax-m3 |
-| `@SdetEngineer` | Writes tests following TDD methodology. | ollama-cloud/kimi-k2.7-code |
+| `@SdetEngineer` | Writes tests following TDD methodology. | ollama-cloud/nemotron-3-super |
 | `@LeadDeveloper` | Primary code writer for backend and core logic. | ollama-cloud/deepseek-v4-pro |
-| `@FrontendDeveloper` | Handles UI implementation with multimodal capabilities. | ollama-cloud/qwen3.5:397b |
+| `@FrontendDeveloper` | Handles UI implementation with multimodal capabilities. | ollama-cloud/deepseek-v4-flash:0731 |
 | `@BackendDeveloper` | Backend specialist for Node. | ollama-cloud/deepseek-v4-pro |
-| `@GoDeveloper` | Go backend specialist for Gin, Echo, APIs, and database integration. | ollama-cloud/kimi-k2.7-code |
+| `@GoDeveloper` | Go backend specialist for Gin, Echo, APIs, and database integration. | ollama-cloud/nemotron-3-super |
-| `@DevopsEngineer` | DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management. | ollama-cloud/minimax-m3 |
+| `@DevopsEngineer` | DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management. | ollama-cloud/nemotron-3-super |
-| `@CodeSkeptic` | Adversarial code reviewer. | ollama-cloud/kimi-k2.7-code |
+| `@CodeSkeptic` | Adversarial code reviewer. | ollama-cloud/nemotron-3-super |
-| `@TheFixer` | Iteratively fixes bugs based on specific error reports and test failures. | ollama-cloud/kimi-k2.7-code |
+| `@TheFixer` | Iteratively fixes bugs based on specific error reports and test failures. | ollama-cloud/nemotron-3-super |
-| `@PerformanceEngineer` | Reviews code for performance issues. | ollama-cloud/minimax-m3 |
+| `@PerformanceEngineer` | Reviews code for performance issues. | ollama-cloud/nemotron-3-super |
-| `@SecurityAuditor` | Scans for security vulnerabilities, OWASP Top 10, dependency CVEs, and hardcoded secrets. | ollama-cloud/kimi-k2.7-code |
+| `@SecurityAuditor` | Scans for security vulnerabilities, OWASP Top 10, dependency CVEs, and hardcoded secrets. | ollama-cloud/nemotron-3-super |
-| `@VisualTester` | Visual regression testing agent that compares screenshots and detects UI differences using pixelmatch and image diff. | ollama-cloud/kimi-k2.7-code |
+| `@VisualTester` | Visual regression testing agent that compares screenshots and detects UI differences using pixelmatch and image diff. | ollama-cloud/nemotron-3-super |
 | `@Orchestrator` | Main dispatcher. | ollama-cloud/deepseek-v4-flash:0731 |
 | `@ReleaseManager` | Manages git operations, semantic versioning, branching, and deployments. | ollama-cloud/deepseek-v4-flash:0731 |
 | `@Evaluator` | Scores agent effectiveness after task completion for continuous improvement. | ollama-cloud/glm-5.2 |
-| `@PromptOptimizer` | Improves agent system prompts based on performance failures. | ollama-cloud/minimax-m3 |
+| `@PromptOptimizer` | Improves agent system prompts based on performance failures. | ollama-cloud/nemotron-3-super |
-| `@ProductOwner` | Manages issue checklists, status labels, tracks progress and coordinates with human users. | ollama-cloud/nemotron-3-ultra |
+| `@ProductOwner` | Manages issue checklists, status labels, tracks progress and coordinates with human users. | ollama-cloud/nemotron-3-super |
-| `@AgentArchitect` | Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis. | ollama-cloud/minimax-m3 |
+| `@AgentArchitect` | Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis. | ollama-cloud/nemotron-3-super |
-| `@CapabilityAnalyst` | Analyzes task requirements against available agents, workflows, and skills. | ollama-cloud/minimax-m3 |
+| `@CapabilityAnalyst` | Analyzes task requirements against available agents, workflows, and skills. | ollama-cloud/nemotron-3-super |
-| `@WorkflowArchitect` | Creates and maintains workflow definitions with complete architecture, Gitea integration, and quality gates. | ollama-cloud/minimax-m3 |
+| `@WorkflowArchitect` | Creates and maintains workflow definitions with complete architecture, Gitea integration, and quality gates. | ollama-cloud/nemotron-3-super |
-| `@MarkdownValidator` | Validates and corrects Markdown descriptions for Gitea issues. | ollama-cloud/nemotron-3-ultra |
+| `@MarkdownValidator` | Validates and corrects Markdown descriptions for Gitea issues. | ollama-cloud/nemotron-3-super |
-| `@BrowserAutomation` | Browser automation agent using Playwright MCP for E2E testing, form filling, navigation, and web interaction. | ollama-cloud/kimi-k2.7-code |
+| `@BrowserAutomation` | Browser automation agent using Playwright MCP for E2E testing, form filling, navigation, and web interaction. | ollama-cloud/nemotron-3-super |
-| `@Planner` | Advanced task planner using Chain of Thought, Tree of Thoughts, and Plan-Execute-Reflect. | ollama-cloud/minimax-m3 |
+| `@Planner` | Advanced task planner using Chain of Thought, Tree of Thoughts, and Plan-Execute-Reflect. | ollama-cloud/nemotron-3-super |
-| `@Reflector` | Self-reflection agent using Reflexion pattern - learns from mistakes. | ollama-cloud/minimax-m3 |
+| `@Reflector` | Self-reflection agent using Reflexion pattern - learns from mistakes. | ollama-cloud/nemotron-3-super |
-| `@MemoryManager` | Manages agent memory systems - short-term (context), long-term (vector store), and episodic (experiences). | ollama-cloud/minimax-m3 |
+| `@MemoryManager` | Manages agent memory systems - short-term (context), long-term (vector store), and episodic (experiences). | ollama-cloud/nemotron-3-super |
 | `@ArchitectIndexer` | Indexes and maps project codebase architecture into . | ollama-cloud/deepseek-v4-flash:0731 |
-| `@FlutterDeveloper` | Flutter mobile specialist for cross-platform apps, state management, and UI components. | ollama-cloud/qwen3.5:397b |
+| `@FlutterDeveloper` | Flutter mobile specialist for cross-platform apps, state management, and UI components. | ollama-cloud/deepseek-v4-flash:0731 |
-| `@PhpDeveloper` | PHP specialist for Laravel, Symfony, WordPress, and modular architecture. | ollama-cloud/deepseek-v4-pro |
+| `@PhpDeveloper` | PHP specialist for Laravel, Symfony, WordPress, and modular architecture. | ollama-cloud/nemotron-3-super |
-| `@PipelineJudge` | Automated pipeline judge. | ollama-cloud/kimi-k2.7-code |
+| `@PipelineJudge` | Automated pipeline judge. | ollama-cloud/nemotron-3-super |
-| `@PythonDeveloper` | Python specialist for Django, FastAPI, data processing, and ML pipelines. | ollama-cloud/deepseek-v4-pro |
+| `@PythonDeveloper` | Python specialist for Django, FastAPI, data processing, and ML pipelines. | ollama-cloud/nemotron-3-super |
-| `@IncidentResponder` | Server incident response and system hardening specialist. | ollama-cloud/minimax-m3 |
+| `@IncidentResponder` | Server incident response and system hardening specialist. | ollama-cloud/nemotron-3-super |
 | `@WorkflowCrossChecker` | Workflow cross-checker and process inspector. | ollama-cloud/glm-5.2 |
 | `@EvolutionSkeptic` | Evaluates model responses against role-specific rubrics with detailed scoring and commentary. | ollama-cloud/glm-5.2 |
-| `@EvolutionPrompt` | Generates role-specific stress-test prompts by analyzing agent definitions. | ollama-cloud/minimax-m3 |
+| `@EvolutionPrompt` | Generates role-specific stress-test prompts by analyzing agent definitions. | ollama-cloud/nemotron-3-super |
-| `@SmartadminBuilder` | SmartAdmin template builder — generates and edits admin panel EJS templates using the 721-component SmartAdmin library. | ollama-cloud/qwen3.5:397b |
+| `@SmartadminBuilder` | SmartAdmin template builder — generates and edits admin panel EJS templates using the 721-component SmartAdmin library. | ollama-cloud/deepseek-v4-flash:0731 |
 | `@SmartadminVizAgent` | Data visualization specialist for SmartAdmin. | ollama-cloud/deepseek-v4-flash:0731 |
 | `@SmartadminNotifyAgent` | Notification/feedback UI specialist for SmartAdmin. | ollama-cloud/deepseek-v4-flash:0731 |
-| `@SmartadminFormAgent` | Form engine specialist for SmartAdmin. | ollama-cloud/qwen3.5:397b |
+| `@SmartadminFormAgent` | Form engine specialist for SmartAdmin. | ollama-cloud/deepseek-v4-flash:0731 |
-| `@SmartadminInteractiveAgent` | Interactive elements specialist for SmartAdmin. | ollama-cloud/kimi-k2.7-code |
+| `@SmartadminInteractiveAgent` | Interactive elements specialist for SmartAdmin. | ollama-cloud/nemotron-3-super |
 
 
 
@@ -584,20 +584,20 @@ Provider availability depends on configuration. Common providers include:
 |---------|-------------|-------|
 | `/status` | Check pipeline status for issue. | ollama-cloud/qwen3.5:397b |
 | `/evaluate` | Generate performance report. | ollama-cloud/gpt-oss:120b |
-| `/plan` | Creates detailed task plans. | ollama-cloud/deepseek-v4-pro |
+| `/plan` | Creates detailed task plans. | ollama-cloud/nemotron-3-super |
 | `/ask` | Answers codebase questions. | ollama-cloud/qwen3.5:397b |
 | `/debug` | Analyzes and fixes bugs. | ollama-cloud/gpt-oss:20b |
-| `/code` | Quick code generation. | ollama-cloud/deepseek-v4-pro |
+| `/code` | Quick code generation. | ollama-cloud/nemotron-3-super |
 | `/research` | Run research and self-improvement. | ollama-cloud/kimi-k2.7-code |
 | `/feature` | Full feature development pipeline. | ollama-cloud/deepseek-v4-pro |
-| `/hotfix` | Hotfix workflow. | ollama-cloud/deepseek-v4-pro |
+| `/hotfix` | Hotfix workflow. | ollama-cloud/nemotron-3-super |
 | `/review` | Code review workflow. | ollama-cloud/kimi-k2.7-code |
 | `/review-watcher` | Auto-validate review results. | ollama-cloud/kimi-k2.7-code |
 | `/workflow` | Run complete workflow with quality gates. | ollama-cloud/kimi-k2.7-code |
 | `/landing-page` | Create landing page CMS from HTML mockups. | ollama-cloud/qwen3.5:397b |
-| `/commerce` | Create e-commerce site with products, cart, payments. | ollama-cloud/deepseek-v4-pro |
+| `/commerce` | Create e-commerce site with products, cart, payments. | ollama-cloud/nemotron-3-super |
-| `/blog` | Create blog/CMS with posts, comments, SEO. | ollama-cloud/deepseek-v4-pro |
+| `/blog` | Create blog/CMS with posts, comments, SEO. | ollama-cloud/nemotron-3-super |
-| `/booking` | Create booking system for services/appointments. | ollama-cloud/deepseek-v4-pro |
+| `/booking` | Create booking system for services/appointments. | ollama-cloud/nemotron-3-super |
 | `/evolve-agent` | Pre-deployment role-fit testing — evaluate which model best fits a specific agent role via stress-test prompts and rubric scoring. | ollama-cloud/kimi-k2.7-code |
 
 

.kilo/agents/agent-architect.md

@@ -1,7 +1,7 @@
 ---
 name: Agent Architect
 mode: all
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 description: Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis. Tier 2 meta-agent with self-cascade enabled.
 color: "#8B5CF6"

.kilo/agents/browser-automation.md

@@ -1,7 +1,7 @@
 ---
 description: Browser automation agent using Playwright MCP for E2E testing, form filling, navigation, and web interaction
 mode: all
-model: ollama-cloud/kimi-k2.7-code
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 permission:
   read: allow

.kilo/agents/capability-analyst.md

@@ -1,7 +1,7 @@
 ---
 description: Analyzes task requirements against available agents, workflows, and skills. Identifies gaps and recommends new components. Tier 2 meta-agent with self-cascade enabled.
 mode: all
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#6366F1"
 permission:

.kilo/agents/code-skeptic.md

@@ -1,7 +1,7 @@
 ---
 description: Adversarial code reviewer. Finds problems and issues. Does NOT suggest implementations (GNS-2 Tier 0)
 mode: all
-model: ollama-cloud/kimi-k2.7-code
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#E11D48"
 permission:

.kilo/agents/context-compressor.md

@@ -1,7 +1,7 @@
 ---
 description: Intelligently manages token budget by summarizing conversation history, preserving critical State, and pruning redundant information before context overflow occurs
 mode: subagent
-model: ollama-cloud/nemotron-3-ultra
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#7C3AED"
 permission:

.kilo/agents/devops-engineer.md

@@ -1,7 +1,7 @@
 ---
 description: DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management (GNS-2 Tier 1)
 mode: all
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#FF6B35"
 permission:

.kilo/agents/evolution-prompt.md

@@ -1,7 +1,7 @@
 ---
 description: Generates role-specific stress-test prompts by analyzing agent definitions. Reads .kilo/agents/*.md to create adversarial test scenarios that validate role adherence, edge-case handling, and instruction following. (GNS-2 Tier 1)
 mode: all
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#FF6B00"
 permission:

.kilo/agents/flutter-developer.md

@@ -1,7 +1,7 @@
 ---
 description: Flutter mobile specialist for cross-platform apps, state management, and UI components
 mode: all
-model: ollama-cloud/qwen3.5:397b
+model: ollama-cloud/deepseek-v4-flash:0731
 variant: thinking
 color: "#02569B"
 permission:

.kilo/agents/frontend-developer.md

@@ -1,7 +1,7 @@
 ---
 description: Handles UI implementation with multimodal capabilities. Accepts visual references like screenshots and mockups. Follows landing-design-interpretation skill for visual/contrast/color tasks on landing pages (MANDATORY measurement-first protocol)
 mode: all
-model: ollama-cloud/qwen3.5:397b
+model: ollama-cloud/deepseek-v4-flash:0731
 variant: thinking
 color: "#0EA5E9"
 permission:

.kilo/agents/go-developer.md

@@ -1,7 +1,7 @@
 ---
 description: Go backend specialist for Gin, Echo, APIs, and database integration (GNS-2 Tier 1)
 mode: all
-model: ollama-cloud/kimi-k2.7-code
+model: ollama-cloud/nemotron-3-super
 color: "#00ADD8"
 permission:
   read: allow

.kilo/agents/incident-responder.md

@@ -1,7 +1,7 @@
 ---
 description: Server incident response and system hardening specialist. Handles live forensics, malware removal, persistence hunting, SSH-based server cleanup, and post-incident hardening. Works with any OS and panel.
 mode: all
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#B91C1C"
 permission:

.kilo/agents/intake-agent.md

@@ -1,7 +1,7 @@
 ---
 description: Conversational interface — receives natural language from users, clarifies ambiguous requirements, produces structured tasks for orchestrator
 mode: all
-model: ollama-cloud/nemotron-3-ultra
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#0891B2"
 permission:

.kilo/agents/markdown-validator.md

@@ -1,7 +1,7 @@
 ---
 description: Validates and corrects Markdown descriptions for Gitea issues
 mode: subagent
-model: ollama-cloud/nemotron-3-ultra
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 permission:
   bash: ask

.kilo/agents/memory-manager.md

@@ -1,7 +1,7 @@
 ---
 description: Manages agent memory systems - short-term (context), long-term (vector store), and episodic (experiences)
 mode: subagent
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 color: "#8B5CF6"
 permission:
   bash: ask

.kilo/agents/pattern-matcher.md

@@ -1,7 +1,7 @@
 ---
 description: Proactively finds similar successful solutions from past projects BEFORE work starts, providing recommendations instead of just duplicate detection
 mode: subagent
-model: ollama-cloud/nemotron-3-ultra
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#059669"
 permission:

.kilo/agents/performance-engineer.md

@@ -1,7 +1,7 @@
 ---
 description: Reviews code for performance issues. Focuses on efficiency, N+1 queries, memory leaks, and algorithmic complexity (GNS-2 Tier 0)
 mode: all
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#0D9488"
 permission:

.kilo/agents/php-developer.md

@@ -1,7 +1,7 @@
 ---
 description: PHP specialist for Laravel, Symfony, WordPress, and modular architecture
 mode: all
-model: ollama-cloud/deepseek-v4-pro
+model: ollama-cloud/nemotron-3-super
 color: "#8B5CF6"
 permission:
   read: allow

.kilo/agents/pipeline-judge.md

@@ -1,7 +1,7 @@
 ---
 description: Automated pipeline judge. Evaluates workflow execution by running tests, measuring token cost and wall-clock time. Produces objective fitness scores. Never writes code - only measures and scores.
 mode: all
-model: ollama-cloud/kimi-k2.7-code
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#DC2626"
 permission:

.kilo/agents/planner.md

@@ -1,7 +1,7 @@
 ---
 description: Advanced task planner using Chain of Thought, Tree of Thoughts, and Plan-Execute-Reflect
 mode: subagent
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#F59E0B"
 permission:

.kilo/agents/product-owner.md

@@ -1,7 +1,7 @@
 ---
 description: Manages issue checklists, status labels, tracks progress and coordinates with human users
 mode: all
-model: ollama-cloud/nemotron-3-ultra
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 permission:
   read: allow

.kilo/agents/prompt-optimizer.md

@@ -1,7 +1,7 @@
 ---
 description: Improves agent system prompts based on performance failures. Meta-learner for prompt optimization
 mode: subagent
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 permission:
   bash: ask

.kilo/agents/python-developer.md

@@ -1,7 +1,7 @@
 ---
 description: Python specialist for Django, FastAPI, data processing, and ML pipelines
 mode: all
-model: ollama-cloud/deepseek-v4-pro
+model: ollama-cloud/nemotron-3-super
 color: "#3776AB"
 permission:
   read: allow

.kilo/agents/reflector.md

@@ -1,7 +1,7 @@
 ---
 description: Self-reflection agent using Reflexion pattern - learns from mistakes
 mode: subagent
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#10B981"
 permission:

.kilo/agents/sdet-engineer.md

@@ -1,7 +1,7 @@
 ---
 description: Writes tests following TDD methodology. Tests MUST fail initially (Red phase) (GNS-2 Tier 1)
 mode: all
-model: ollama-cloud/kimi-k2.7-code
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#8B5CF6"
 permission:

.kilo/agents/security-auditor.md

@@ -1,7 +1,7 @@
 ---
 description: Scans for security vulnerabilities, OWASP Top 10, dependency CVEs, and hardcoded secrets (GNS-2 Tier 0)
 mode: all
-model: ollama-cloud/kimi-k2.7-code
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#DC2626"
 permission:

.kilo/agents/smartadmin-builder.md

@@ -1,7 +1,7 @@
 ---
 description: SmartAdmin template builder — generates and edits admin panel EJS templates using the 721-component SmartAdmin library. Understands component classes, page structure, and produces backend-ready frontend pages.
 mode: subagent
-model: ollama-cloud/qwen3.5:397b
+model: ollama-cloud/deepseek-v4-flash:0731
 variant: thinking
 variant_strategy: task_size_based
 color: "#2563EB"

.kilo/agents/smartadmin-form-agent.md

@@ -1,7 +1,7 @@
 ---
 description: Form engine specialist for SmartAdmin. Generates complete form HTML with validation attributes and JS handlers using Bootstrap form groups, Select2, datepickers, and form wizards.
 mode: subagent
-model: ollama-cloud/qwen3.5:397b
+model: ollama-cloud/deepseek-v4-flash:0731
 variant: thinking
 variant_strategy: task_size_based
 color: "#10B981"

.kilo/agents/smartadmin-interactive-agent.md

@@ -1,7 +1,7 @@
 ---
 description: Interactive elements specialist for SmartAdmin. Generates HTML element snippets and event handler JS for buttons, dropdowns, nav-tabs, collapse, and modal triggers.
 mode: subagent
-model: ollama-cloud/kimi-k2.7-code
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 variant_strategy: task_size_based
 color: "#8B5CF6"

.kilo/agents/stakeholder-bridge.md

@@ -1,7 +1,7 @@
 ---
 description: Translates technical outputs into business language for non-technical stakeholders, generates executive summaries and progress reports
 mode: subagent
-model: ollama-cloud/nemotron-3-ultra
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#DC2626"
 permission:

.kilo/agents/the-fixer.md

@@ -1,7 +1,7 @@
 ---
 description: Iteratively fixes bugs based on specific error reports and test failures (GNS-2 Tier 1)
 mode: all
-model: ollama-cloud/kimi-k2.7-code
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 color: "#F59E0B"
 permission:

.kilo/agents/visual-tester.md

@@ -1,7 +1,7 @@
 ---
 description: Strategy-aware visual testing orchestrator. Selects between vlmkit, vrt, and Midscene.js based on issue content. Runs in Docker only. Requires visual-testing and docker-visual-testing skills.
 mode: all
-model: ollama-cloud/kimi-k2.7-code
+model: ollama-cloud/nemotron-3-super
 color: "#DC2626"
 variant: thinking
 permission:

.kilo/agents/workflow-architect.md

@@ -1,7 +1,7 @@
 ---
 description: Creates and maintains workflow definitions with complete architecture, Gitea integration, and quality gates
 mode: subagent
-model: ollama-cloud/minimax-m3
+model: ollama-cloud/nemotron-3-super
 variant: thinking
 permission:
   bash: ask

.kilo/capability-index.yaml

@@ -13,7 +13,7 @@ agents:
     produces: [code, documentation_inline]
 
   frontend-developer:
-    model: ollama-cloud/qwen3.5:397b
+    model: ollama-cloud/deepseek-v4-flash:0731
     variant: thinking
     mode: subagent
     capabilities: [ui_implementation, component_creation, styling, responsive_design, nextjs_development, vue_nuxt_development, react_development]
@@ -22,7 +22,7 @@ agents:
     produces: [vue_components, react_components, nextjs_pages, nuxt_pages, css_styles, frontend_tests]
 
   php-developer:
-    model: ollama-cloud/deepseek-v4-pro
+    model: ollama-cloud/nemotron-3-super
     mode: subagent
     capabilities: [php_web_development, laravel_development, symfony_development, wordpress_development, php_api_development, php_database_design, php_authentication, php_modular_architecture, php_testing, php_security]
     forbidden: [frontend_code, non_php_backend]
@@ -30,7 +30,7 @@ agents:
     produces: [laravel_routes, php_models, php_services, php_controllers, php_migrations, php_tests, wordpress_plugins]
 
   python-developer:
-    model: ollama-cloud/deepseek-v4-pro
+    model: ollama-cloud/nemotron-3-super
     mode: subagent
     capabilities: [python_web_development, django_development, fastapi_development, python_api_development, python_database_design, python_authentication, python_async_patterns, python_testing, python_security]
     forbidden: [frontend_code, non_python_backend]
@@ -47,7 +47,7 @@ agents:
     produces: [express_routes, database_schema, api_documentation]
 
   go-developer:
-    model: ollama-cloud/kimi-k2.7-code
+    model: ollama-cloud/nemotron-3-super
     mode: subagent
     capabilities: [go_api_development, go_database_design, go_concurrent_programming, go_authentication, go_microservices, postgresql_integration, sqlite_integration, clickhouse_integration]
     forbidden: [frontend_code]
@@ -55,7 +55,7 @@ agents:
     produces: [go_handlers, go_database_schema, go_api_documentation, concurrent_solutions]
 
   flutter-developer:
-    model: ollama-cloud/qwen3.5:397b
+    model: ollama-cloud/deepseek-v4-flash:0731
     variant: thinking
     mode: subagent
     capabilities: [dart_programming, flutter_ui, mobile_app_development, widget_creation, state_management]
@@ -64,7 +64,7 @@ agents:
     produces: [flutter_widgets, dart_code, mobile_app]
 
   devops-engineer:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [docker_configuration, kubernetes_setup, ci_cd_pipeline, infrastructure_automation, container_optimization]
@@ -73,7 +73,7 @@ agents:
     produces: [docker_compose, kubernetes_manifests, ci_cd_config]
 
   sdet-engineer:
-    model: ollama-cloud/kimi-k2.7-code
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [unit_tests, integration_tests, e2e_tests, test_planning, visual_regression]
@@ -82,7 +82,7 @@ agents:
     produces: [test_files, test_reports, coverage_reports]
 
   code-skeptic:
-    model: ollama-cloud/kimi-k2.7-code
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [code_review, security_review, style_check, issue_identification]
@@ -91,7 +91,7 @@ agents:
     produces: [review_comments, approval_status, issue_list]
 
   security-auditor:
-    model: ollama-cloud/kimi-k2.7-code
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [vulnerability_scan, owasp_check, secret_detection, auth_review]
@@ -100,7 +100,7 @@ agents:
     produces: [security_report, vulnerability_list]
 
   performance-engineer:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [performance_analysis, n_plus_one_detection, memory_leak_check, algorithm_analysis]
@@ -109,7 +109,7 @@ agents:
     produces: [performance_report, optimization_suggestions]
 
   the-fixer:
-    model: ollama-cloud/kimi-k2.7-code
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [bug_fixing, issue_resolution, code_correction]
@@ -118,7 +118,7 @@ agents:
     produces: [code_fixes, resolution_notes]
 
   browser-automation:
-    model: ollama-cloud/kimi-k2.7-code
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [e2e_browser_tests, form_filling, navigation_testing, screenshot_capture]
@@ -127,7 +127,7 @@ agents:
     produces: [test_results, screenshots]
 
   visual-tester:
-    model: ollama-cloud/kimi-k2.7-code
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [visual_regression, pixel_comparison, screenshot_diff, ui_validation, bbox_element_extraction, console_error_detection, network_error_detection, responsive_layout_check, button_overflow_detection, gitea_integration, docker_networking]
@@ -145,7 +145,7 @@ agents:
     produces: [architecture_docs, api_specs, database_schemas]
 
   capability-analyst:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [gap_analysis, capability_mapping, recommendation_generation, coverage_analysis]
@@ -163,7 +163,7 @@ agents:
     produces: [routing_decisions, status_updates]
 
   intake-agent:
-    model: ollama-cloud/nemotron-3-ultra
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: all
     capabilities: [natural_language_understanding, conversational_clarification, task_structuring, requirement_formulation, intent_extraction]
@@ -172,7 +172,7 @@ agents:
     produces: [structured_tasks, acceptance_criteria, orchestrator_compatible_tasks]
 
   context-compressor:
-    model: ollama-cloud/nemotron-3-ultra
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [context_summarization, state_extraction, token_efficiency, memory_pruning, checkpoint_preservation]
@@ -181,7 +181,7 @@ agents:
     produces: [compressed_checkpoint, token_savings, preserved_state]
 
   pattern-matcher:
-    model: ollama-cloud/nemotron-3-ultra
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [similar_pattern_detection, successful_solution_retrieval, cross_project_learning, proactive_recommendation]
@@ -190,7 +190,7 @@ agents:
     produces: [pattern_matches, recommendations, knowledge_graph_updates]
 
   stakeholder-bridge:
-    model: ollama-cloud/nemotron-3-ultra
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [technical_to_business_translation, executive_summary_generation, progress_report_generation, stakeholder_communication]
@@ -216,7 +216,7 @@ agents:
     produces: [performance_report, scores, recommendations]
 
   prompt-optimizer:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [prompt_analysis, prompt_improvement, failure_pattern_detection]
@@ -225,7 +225,7 @@ agents:
     produces: [improved_prompts, optimization_report]
 
   product-owner:
-    model: ollama-cloud/nemotron-3-ultra
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [issue_management, prioritization, backlog_management, workflow_completion]
@@ -234,7 +234,7 @@ agents:
     produces: [priority_order, issue_labels, issue_closures]
 
   pipeline-judge:
-    model: ollama-cloud/kimi-k2.7-code
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [test_execution, fitness_scoring, metric_collection, bottleneck_detection]
@@ -243,7 +243,7 @@ agents:
     produces: [fitness_report, bottleneck_analysis, improvement_triggers]
 
   workflow-architect:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [workflow_design, process_definition, automation_setup]
@@ -252,7 +252,7 @@ agents:
     produces: [workflow_definitions, command_files]
 
   markdown-validator:
-    model: ollama-cloud/nemotron-3-ultra
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [markdown_validation, formatting_check, link_validation]
@@ -261,7 +261,7 @@ agents:
     produces: [validation_report, corrections]
 
   agent-architect:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [agent_design, prompt_engineering, capability_definition]
@@ -270,7 +270,7 @@ agents:
     produces: [agent_definition, integration_plan]
 
   planner:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [task_decomposition, chain_of_thought, tree_of_thoughts, plan_execute_reflect, dependency_analysis]
@@ -279,7 +279,7 @@ agents:
     produces: [decomposed_steps, dependency_graph, success_criteria]
 
   reflector:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [self_reflection, mistake_analysis, lesson_extraction, trajectory_analysis, heuristic_evaluation]
@@ -288,7 +288,7 @@ agents:
     produces: [reflection_report, lessons_learned, improved_approach]
 
   memory-manager:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     mode: subagent
     capabilities: [memory_retrieval, memory_storage, memory_consolidation, relevance_scoring, episodic_management]
     forbidden: [code_changes, implementation]
@@ -312,7 +312,7 @@ agents:
     produces: [historical_findings, regression_warnings, recommended_solutions]
 
   incident-responder:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [incident_response, live_forensics, malware_removal, persistence_hunting, ssh_cleanup, post_incident_hardening, cross_platform_hardening]
@@ -321,7 +321,7 @@ agents:
     produces: [forensics_report, cleanup_actions, hardening_recommendations]
 
   evolution-prompt:
-    model: ollama-cloud/minimax-m3
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [prompt_generation, role_analysis, adversarial_scenario_design, test_case_creation]
@@ -339,7 +339,7 @@ agents:
     produces: [evaluation_scores, detailed_commentary]
 
   smartadmin-builder:
-    model: ollama-cloud/qwen3.5:397b
+    model: ollama-cloud/deepseek-v4-flash:0731
     variant: thinking
     mode: subagent
     capabilities: [smartadmin_template_building, ejs_generation, admin_panel_creation, component_library_usage]
@@ -366,7 +366,7 @@ agents:
     produces: [alert_html, toast_html, modal_html, trigger_api, dismiss_handlers]
 
   smartadmin-form-agent:
-    model: ollama-cloud/qwen3.5:397b
+    model: ollama-cloud/deepseek-v4-flash:0731
     variant: thinking
     mode: subagent
     capabilities: [form_generation, form_validation, select2, datepickers, form_wizards, field_dependencies]
@@ -375,7 +375,7 @@ agents:
     produces: [form_html, validation_js, dependency_handlers, init_code]
 
   smartadmin-interactive-agent:
-    model: ollama-cloud/kimi-k2.7-code
+    model: ollama-cloud/nemotron-3-super
     variant: thinking
     mode: subagent
     capabilities: [interactive_elements, buttons, dropdowns, nav_tabs, accordions, collapse, modal_triggers, state_toggles]

kilo-meta.json

@@ -2,12 +2,12 @@
   "$schema": "https://app.kilo.ai/config.json",
   "metaVersion": "1.0.0",
   "prompt_version": 1,
-  "lastSync": "2026-08-04T13:08:39.959Z",
+  "lastSync": "2026-08-04T21:27:18.197Z",
   "agents": {
     "intake-agent": {
       "file": ".kilo/agents/intake-agent.md",
       "description": "Conversational interface — receives natural language from users, clarifies ambiguous requirements, produces structured tasks for orchestrator",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -17,7 +17,7 @@
     "context-compressor": {
       "file": ".kilo/agents/context-compressor.md",
       "description": "Intelligently manages token budget by summarizing conversation history, preserving critical State, and pruning redundant information before context overflow occurs",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -27,7 +27,7 @@
     "pattern-matcher": {
       "file": ".kilo/agents/pattern-matcher.md",
       "description": "Proactively finds similar successful solutions from past projects BEFORE work starts, providing recommendations instead of just duplicate detection",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -37,7 +37,7 @@
     "stakeholder-bridge": {
       "file": ".kilo/agents/stakeholder-bridge.md",
       "description": "Translates technical outputs into business language for non-technical stakeholders, generates executive summaries and progress reports",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -73,7 +73,7 @@
     "sdet-engineer": {
       "file": ".kilo/agents/sdet-engineer.md",
       "description": "Writes tests following TDD methodology. Tests MUST fail initially (Red phase)",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -93,7 +93,7 @@
     "frontend-developer": {
       "file": ".kilo/agents/frontend-developer.md",
       "description": "Handles UI implementation with multimodal capabilities. Accepts visual references like screenshots and mockups. Follows landing-design-interpretation skill for visual/contrast/color tasks on landing pages (MANDATORY measurement-first protocol)",
-      "model": "ollama-cloud/qwen3.5:397b",
+      "model": "ollama-cloud/deepseek-v4-flash:0731",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -113,7 +113,7 @@
     "go-developer": {
       "file": ".kilo/agents/go-developer.md",
       "description": "Go backend specialist for Gin, Echo, APIs, and database integration",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "color": "#00ADD8",
       "category": "core"
@@ -121,7 +121,7 @@
     "devops-engineer": {
       "file": ".kilo/agents/devops-engineer.md",
       "description": "DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -131,7 +131,7 @@
     "code-skeptic": {
       "file": ".kilo/agents/code-skeptic.md",
       "description": "Adversarial code reviewer. Finds problems and issues. Does NOT suggest implementations",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -141,7 +141,7 @@
     "the-fixer": {
       "file": ".kilo/agents/the-fixer.md",
       "description": "Iteratively fixes bugs based on specific error reports and test failures",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -151,7 +151,7 @@
     "performance-engineer": {
       "file": ".kilo/agents/performance-engineer.md",
       "description": "Reviews code for performance issues. Focuses on efficiency, N+1 queries, memory leaks, and algorithmic complexity",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -161,7 +161,7 @@
     "security-auditor": {
       "file": ".kilo/agents/security-auditor.md",
       "description": "Scans for security vulnerabilities, OWASP Top 10, dependency CVEs, and hardcoded secrets",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -171,7 +171,7 @@
     "visual-tester": {
       "file": ".kilo/agents/visual-tester.md",
       "description": "Visual regression testing agent that compares screenshots and detects UI differences using pixelmatch and image diff",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -261,7 +261,7 @@
     "prompt-optimizer": {
       "file": ".kilo/agents/prompt-optimizer.md",
       "description": "Improves agent system prompts based on performance failures. Meta-learner for prompt optimization",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -270,7 +270,7 @@
     "product-owner": {
       "file": ".kilo/agents/product-owner.md",
       "description": "Manages issue checklists, status labels, tracks progress and coordinates with human users",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -279,7 +279,7 @@
     "agent-architect": {
       "file": ".kilo/agents/agent-architect.md",
       "description": "Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -288,7 +288,7 @@
     "capability-analyst": {
       "file": ".kilo/agents/capability-analyst.md",
       "description": "Analyzes task requirements against available agents, workflows, and skills. Identifies gaps and recommends new components.",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -297,7 +297,7 @@
     "workflow-architect": {
       "file": ".kilo/agents/workflow-architect.md",
       "description": "Creates and maintains workflow definitions with complete architecture, Gitea integration, and quality gates",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -306,7 +306,7 @@
     "markdown-validator": {
       "file": ".kilo/agents/markdown-validator.md",
       "description": "Validates and corrects Markdown descriptions for Gitea issues",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -315,7 +315,7 @@
     "browser-automation": {
       "file": ".kilo/agents/browser-automation.md",
       "description": "Browser automation agent using Playwright MCP for E2E testing, form filling, navigation, and web interaction",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -324,7 +324,7 @@
     "planner": {
       "file": ".kilo/agents/planner.md",
       "description": "Advanced task planner using Chain of Thought, Tree of Thoughts, and Plan-Execute-Reflect",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -334,7 +334,7 @@
     "reflector": {
       "file": ".kilo/agents/reflector.md",
       "description": "Self-reflection agent using Reflexion pattern - learns from mistakes",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -344,7 +344,7 @@
     "memory-manager": {
       "file": ".kilo/agents/memory-manager.md",
       "description": "Manages agent memory systems - short-term (context), long-term (vector store), and episodic (experiences)",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "subagent",
       "color": "#8B5CF6",
       "category": "cognitive"
@@ -360,7 +360,7 @@
     "flutter-developer": {
       "file": ".kilo/agents/flutter-developer.md",
       "description": "Flutter mobile specialist for cross-platform apps, state management, and UI components",
-      "model": "ollama-cloud/qwen3.5:397b",
+      "model": "ollama-cloud/deepseek-v4-flash:0731",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -370,7 +370,7 @@
     "php-developer": {
       "file": ".kilo/agents/php-developer.md",
       "description": "PHP specialist for Laravel, Symfony, WordPress, and modular architecture",
-      "model": "ollama-cloud/deepseek-v4-pro",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "color": "#8B5CF6",
       "category": "core"
@@ -378,7 +378,7 @@
     "pipeline-judge": {
       "file": ".kilo/agents/pipeline-judge.md",
       "description": "Automated pipeline judge. Evaluates workflow execution by running tests, measuring token cost and wall-clock time. Produces objective fitness scores. Never writes code - only measures and scores.",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -388,7 +388,7 @@
     "python-developer": {
       "file": ".kilo/agents/python-developer.md",
       "description": "Python specialist for Django, FastAPI, data processing, and ML pipelines",
-      "model": "ollama-cloud/deepseek-v4-pro",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "color": "#3776AB",
       "category": "core"
@@ -396,7 +396,7 @@
     "incident-responder": {
       "file": ".kilo/agents/incident-responder.md",
       "description": "Server incident response and system hardening specialist. Handles live forensics, malware removal, persistence hunting, SSH-based server cleanup, and post-incident hardening. Works with any OS and panel.",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -426,7 +426,7 @@
     "evolution-prompt": {
       "file": ".kilo/agents/evolution-prompt.md",
       "description": "Generates role-specific stress-test prompts by analyzing agent definitions",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "all",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
@@ -436,7 +436,7 @@
     "smartadmin-builder": {
       "file": ".kilo/agents/smartadmin-builder.md",
       "description": "SmartAdmin template builder — generates and edits admin panel EJS templates using the 721-component SmartAdmin library. Understands component classes, page structure, and produces backend-ready frontend pages.",
-      "model": "ollama-cloud/qwen3.5:397b",
+      "model": "ollama-cloud/deepseek-v4-flash:0731",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -504,7 +504,7 @@
     "smartadmin-form-agent": {
       "file": ".kilo/agents/smartadmin-form-agent.md",
       "description": "Form engine specialist for SmartAdmin. Generates complete form HTML with validation attributes and JS handlers using Bootstrap form groups, Select2, datepickers, and form wizards.",
-      "model": "ollama-cloud/qwen3.5:397b",
+      "model": "ollama-cloud/deepseek-v4-flash:0731",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -527,7 +527,7 @@
     "smartadmin-interactive-agent": {
       "file": ".kilo/agents/smartadmin-interactive-agent.md",
       "description": "Interactive elements specialist for SmartAdmin. Generates HTML element snippets and event handler JS for buttons, dropdowns, nav-tabs, accordions, collapse, and modal triggers.",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "mode": "subagent",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
@@ -566,7 +566,7 @@
     "plan": {
       "file": ".kilo/commands/plan.md",
       "description": "Creates detailed task plans",
-      "model": "ollama-cloud/deepseek-v4-pro"
+      "model": "ollama-cloud/nemotron-3-super"
     },
     "ask": {
       "file": ".kilo/commands/ask.md",
@@ -581,7 +581,7 @@
     "code": {
       "file": ".kilo/commands/code.md",
       "description": "Quick code generation",
-      "model": "ollama-cloud/deepseek-v4-pro"
+      "model": "ollama-cloud/nemotron-3-super"
     },
     "research": {
       "file": ".kilo/commands/research.md",
@@ -596,7 +596,7 @@
     "hotfix": {
       "file": ".kilo/commands/hotfix.md",
       "description": "Hotfix workflow",
-      "model": "ollama-cloud/deepseek-v4-pro"
+      "model": "ollama-cloud/nemotron-3-super"
     },
     "review": {
       "file": ".kilo/commands/review.md",
@@ -625,17 +625,17 @@
     "commerce": {
       "file": ".kilo/commands/commerce.md",
       "description": "Create e-commerce site with products, cart, payments",
-      "model": "ollama-cloud/deepseek-v4-pro"
+      "model": "ollama-cloud/nemotron-3-super"
     },
     "blog": {
       "file": ".kilo/commands/blog.md",
       "description": "Create blog/CMS with posts, comments, SEO",
-      "model": "ollama-cloud/deepseek-v4-pro"
+      "model": "ollama-cloud/nemotron-3-super"
     },
     "booking": {
       "file": ".kilo/commands/booking.md",
       "description": "Create booking system for services/appointments",
-      "model": "ollama-cloud/deepseek-v4-pro"
+      "model": "ollama-cloud/nemotron-3-super"
     },
     "evolve-agent": {
       "file": ".kilo/commands/evolve-agent.md",

kilo.jsonc

@@ -23,7 +23,7 @@
     "intake-agent": {
       "description": "Conversational interface — receives natural language from users, clarifies ambiguous requirements, produces structured tasks for orchestrator",
       "mode": "all",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "color": "#0891B2"
@@ -31,7 +31,7 @@
     "context-compressor": {
       "description": "Intelligently manages token budget by summarizing conversation history, preserving critical State, and pruning redundant information before context overflow occurs",
       "mode": "subagent",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "color": "#7C3AED"
@@ -39,7 +39,7 @@
     "pattern-matcher": {
       "description": "Proactively finds similar successful solutions from past projects BEFORE work starts, providing recommendations instead of just duplicate detection",
       "mode": "subagent",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "color": "#059669"
@@ -47,7 +47,7 @@
     "stakeholder-bridge": {
       "description": "Translates technical outputs into business language for non-technical stakeholders, generates executive summaries and progress reports",
       "mode": "subagent",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "color": "#DC2626"
@@ -75,7 +75,7 @@
     "sdet-engineer": {
       "description": "Writes tests following TDD methodology. Tests MUST fail initially (Red phase)",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "color": "#8B5CF6"
@@ -91,7 +91,7 @@
     "frontend-developer": {
       "description": "Handles UI implementation with multimodal capabilities. Accepts visual references like screenshots and mockups. Follows landing-design-interpretation skill for visual/contrast/color tasks on landing pages (MANDATORY measurement-first protocol)",
       "mode": "all",
-      "model": "ollama-cloud/qwen3.5:397b",
+      "model": "ollama-cloud/deepseek-v4-flash:0731",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "color": "#0EA5E9"
@@ -106,14 +106,14 @@
     "go-developer": {
       "description": "Go backend specialist for Gin, Echo, APIs, and database integration",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant_strategy": "task_size_based",
       "color": "#00ADD8"
     },
     "devops-engineer": {
       "description": "DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management",
       "mode": "all",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "color": "#FF6B35"
@@ -121,7 +121,7 @@
     "code-skeptic": {
       "description": "Adversarial code reviewer. Finds problems and issues. Does NOT suggest implementations",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "color": "#E11D48",
@@ -141,7 +141,7 @@
     "the-fixer": {
       "description": "Iteratively fixes bugs based on specific error reports and test failures",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "color": "#F59E0B",
@@ -163,7 +163,7 @@
     "performance-engineer": {
       "description": "Reviews code for performance issues. Focuses on efficiency, N+1 queries, memory leaks, and algorithmic complexity",
       "mode": "all",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "color": "#0D9488",
@@ -183,7 +183,7 @@
     "security-auditor": {
       "description": "Scans for security vulnerabilities, OWASP Top 10, dependency CVEs, and hardcoded secrets",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "color": "#DC2626",
@@ -203,7 +203,7 @@
     "visual-tester": {
       "description": "Visual regression testing agent that compares screenshots and detects UI differences using pixelmatch and image diff",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "permission": {
@@ -318,7 +318,7 @@
     "prompt-optimizer": {
       "description": "Improves agent system prompts based on performance failures. Meta-learner for prompt optimization",
       "mode": "subagent",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "permission": {
@@ -336,7 +336,7 @@
     "product-owner": {
       "description": "Manages issue checklists, status labels, tracks progress and coordinates with human users",
       "mode": "all",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "permission": {
@@ -356,7 +356,7 @@
     "agent-architect": {
       "description": "Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis",
       "mode": "all",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "permission": {
@@ -374,7 +374,7 @@
     "capability-analyst": {
       "description": "Analyzes task requirements against available agents, workflows, and skills. Identifies gaps and recommends new components.",
       "mode": "all",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "permission": {
@@ -390,7 +390,7 @@
     "workflow-architect": {
       "description": "Creates and maintains workflow definitions with complete architecture, Gitea integration, and quality gates",
       "mode": "subagent",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "permission": {
@@ -408,7 +408,7 @@
     "markdown-validator": {
       "description": "Validates and corrects Markdown descriptions for Gitea issues",
       "mode": "subagent",
-      "model": "ollama-cloud/nemotron-3-ultra",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "permission": {
@@ -426,7 +426,7 @@
     "browser-automation": {
       "description": "Browser automation agent using Playwright MCP for E2E testing, form filling, navigation, and web interaction",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "permission": {
@@ -445,7 +445,7 @@
     "planner": {
       "description": "Advanced task planner using Chain of Thought, Tree of Thoughts, and Plan-Execute-Reflect",
       "mode": "subagent",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "color": "#F59E0B",
@@ -463,7 +463,7 @@
     "reflector": {
       "description": "Self-reflection agent using Reflexion pattern - learns from mistakes",
       "mode": "subagent",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "color": "#10B981",
@@ -480,7 +480,7 @@
     "memory-manager": {
       "description": "Manages agent memory systems - short-term (context), long-term (vector store), and episodic (experiences)",
       "mode": "subagent",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "color": "#8B5CF6",
       "permission": {
         "read": "allow",
@@ -516,7 +516,7 @@
     "flutter-developer": {
       "description": "Flutter mobile specialist for cross-platform apps, state management, and UI components",
       "mode": "all",
-      "model": "ollama-cloud/qwen3.5:397b",
+      "model": "ollama-cloud/deepseek-v4-flash:0731",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "color": "#02569B",
@@ -539,7 +539,7 @@
     "php-developer": {
       "description": "PHP specialist for Laravel, Symfony, WordPress, and modular architecture",
       "mode": "all",
-      "model": "ollama-cloud/deepseek-v4-pro",
+      "model": "ollama-cloud/nemotron-3-super",
       "color": "#8B5CF6",
       "permission": {
         "read": "allow",
@@ -560,7 +560,7 @@
     "pipeline-judge": {
       "description": "Automated pipeline judge. Evaluates workflow execution by running tests, measuring token cost and wall-clock time. Produces objective fitness scores. Never writes code - only measures and scores.",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "color": "#DC2626",
@@ -579,7 +579,7 @@
     "python-developer": {
       "description": "Python specialist for Django, FastAPI, data processing, and ML pipelines",
       "mode": "all",
-      "model": "ollama-cloud/deepseek-v4-pro",
+      "model": "ollama-cloud/nemotron-3-super",
       "color": "#3776AB",
       "permission": {
         "read": "allow",
@@ -600,7 +600,7 @@
     "incident-responder": {
       "description": "Server incident response and system hardening specialist. Handles live forensics, malware removal, persistence hunting, SSH-based server cleanup, and post-incident hardening. Works with any OS and panel.",
       "mode": "all",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "color": "#B91C1C",
@@ -664,7 +664,7 @@
     "evolution-prompt": {
       "description": "Generates role-specific stress-test prompts by analyzing agent definitions",
       "mode": "all",
-      "model": "ollama-cloud/minimax-m3",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "always_thinking",
       "color": "#FF6B00",
@@ -686,7 +686,7 @@
     "smartadmin-builder": {
       "description": "SmartAdmin template builder — generates and edits admin panel EJS templates using the 721-component SmartAdmin library. Understands component classes, page structure, and produces backend-ready frontend pages.",
       "mode": "subagent",
-      "model": "ollama-cloud/qwen3.5:397b",
+      "model": "ollama-cloud/deepseek-v4-flash:0731",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "color": "#2563EB",
@@ -752,7 +752,7 @@
     "smartadmin-form-agent": {
       "description": "Form engine specialist for SmartAdmin. Generates complete form HTML with validation attributes and JS handlers using Bootstrap form groups, Select2, datepickers, and form wizards.",
       "mode": "subagent",
-      "model": "ollama-cloud/qwen3.5:397b",
+      "model": "ollama-cloud/deepseek-v4-flash:0731",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "color": "#10B981",
@@ -773,7 +773,7 @@
     "smartadmin-interactive-agent": {
       "description": "Interactive elements specialist for SmartAdmin. Generates HTML element snippets and event handler JS for buttons, dropdowns, nav-tabs, accordions, collapse, and modal triggers.",
       "mode": "subagent",
-      "model": "ollama-cloud/kimi-k2.7-code",
+      "model": "ollama-cloud/nemotron-3-super",
       "variant": "thinking",
       "variant_strategy": "task_size_based",
       "color": "#8B5CF6",