fb552e0020
- Update 30 agents to v3 heatmap maximum-score models: * go-dev: qwen3-coder -> deepseek-v4-pro-max (85->88 +3) * planner: nemotron -> deepseek-v4-pro-max (80->88 +8) * perf-engineer: nemotron -> deepseek-v4-pro-max (78->84 +6) * reflector: nemotron -> deepseek-v4-pro-max (78->84 +6) * security: nemotron -> deepseek-v4-pro-max (76->80 +4) * memory-manager: nemotron -> qwen3.6-plus (86->87 +1) * frontend: kimi-k2.5 -> minimax-m2.5 (92) * the-fixer: minimax-m2.5 -> kimi-k2.6 (88->90 +2) * browser-auto: kimi-k2.6 -> qwen3-coder (86->87 +1) * prompt-opt: glm-5.1 -> qwen3.6-plus (82->83 +1) * backend: deepseek-v3.2 -> qwen3-coder (91) * capability-analyst: nemotron -> glm-5.1 (85) * release-man: devstral-2 -> glm-5.1 (82) * evaluator: nemotron -> glm-5.1 (86) * workflow-arch: gpt-oss -> glm-5.1 (84) - Add Model Evolution Guard: * fitness-gate.cjs: rejects downgrades >3 points or <75 score * Normalized model ID lookup (: vs -) * Diff report before any file modifications - Update sync-benchmarks-from-yaml.cjs with fitness gate - Sync kilo-meta.json, kilo.jsonc, .md agent files - Rebuild research-dashboard.html (104KB, 30 agents, 11 models) Total improvement: +105 points across 11 agents Source: v3.html heatmap IF-adjusted composite scores
464 lines
14 KiB
JSON
464 lines
14 KiB
JSON
{
|
|
"$schema": "https://app.kilo.ai/config.json",
|
|
"instructions": [
|
|
".kilo/rules/global.md",
|
|
".kilo/rules/agent-patterns.md",
|
|
".kilo/rules/docker.md",
|
|
".kilo/rules/go.md",
|
|
".kilo/rules/history-miner.md",
|
|
".kilo/rules/lead-developer.md",
|
|
".kilo/rules/nodejs.md",
|
|
".kilo/rules/prompt-engineering.md",
|
|
".kilo/rules/release-manager.md",
|
|
".kilo/rules/sdet-engineer.md",
|
|
".kilo/rules/code-skeptic.md",
|
|
".kilo/rules/evolutionary-sync.md"
|
|
],
|
|
"skills": {
|
|
"paths": [".kilo/skills"]
|
|
},
|
|
"agent": {
|
|
"requirement-refiner": {
|
|
"description": "Converts vague ideas and bug reports into strict User Stories with acceptance criteria checklists",
|
|
"mode": "all",
|
|
"model": "ollama-cloud/kimi-k2-thinking",
|
|
"color": "#4F46E5",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"history-miner": "allow",
|
|
"system-analyst": "allow"
|
|
}
|
|
}
|
|
},
|
|
"history-miner": {
|
|
"description": "Analyzes git history to find duplicates and past solutions, preventing regression and duplicate work",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/glm-5.1"
|
|
},
|
|
"system-analyst": {
|
|
"description": "Designs technical specifications, data schemas, and API contracts before implementation",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/glm-5.1"
|
|
},
|
|
"sdet-engineer": {
|
|
"description": "Writes tests following TDD methodology. Tests MUST fail initially (Red phase)",
|
|
"mode": "all",
|
|
"model": "ollama-cloud/qwen3-coder:480b",
|
|
"color": "#8B5CF6",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"lead-developer": "allow"
|
|
}
|
|
}
|
|
},
|
|
"lead-developer": {
|
|
"description": "Primary code writer for backend and core logic. Writes implementation to pass tests",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/qwen3-coder:480b",
|
|
"color": "#DC2626",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"code-skeptic": "allow"
|
|
}
|
|
}
|
|
},
|
|
"frontend-developer": {
|
|
"description": "Handles UI implementation with multimodal capabilities. Accepts visual references like screenshots and mockups",
|
|
"mode": "all",
|
|
"model": "ollama-cloud/minimax-m2.5",
|
|
"color": "#0EA5E9",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"code-skeptic": "allow"
|
|
}
|
|
}
|
|
},
|
|
"backend-developer": {
|
|
"description": "Backend specialist for Node.js, Express, APIs, and database integration",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/minimax-m2.5",
|
|
"color": "#10B981",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"code-skeptic": "allow"
|
|
}
|
|
}
|
|
},
|
|
"go-developer": {
|
|
"description": "Go backend specialist for Gin, Echo, APIs, and database integration",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/minimax-m2.5",
|
|
"color": "#00ADD8",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"code-skeptic": "allow"
|
|
}
|
|
}
|
|
},
|
|
"devops-engineer": {
|
|
"description": "DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/minimax-m2.5",
|
|
"color": "#FF6B35",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"code-skeptic": "allow",
|
|
"security-auditor": "allow"
|
|
}
|
|
}
|
|
},
|
|
"code-skeptic": {
|
|
"description": "Adversarial code reviewer. Finds problems and issues. Does NOT suggest implementations",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/deepseek-v4-pro-max",
|
|
"color": "#E11D48",
|
|
"permission": {
|
|
"read": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"the-fixer": "allow",
|
|
"performance-engineer": "allow"
|
|
}
|
|
}
|
|
},
|
|
"the-fixer": {
|
|
"description": "Iteratively fixes bugs based on specific error reports and test failures",
|
|
"mode": "all",
|
|
"model": "ollama-cloud/kimi-k2.6:cloud",
|
|
"color": "#F59E0B",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"code-skeptic": "allow",
|
|
"orchestrator": "allow"
|
|
}
|
|
}
|
|
},
|
|
"performance-engineer": {
|
|
"description": "Reviews code for performance issues. Focuses on efficiency, N+1 queries, memory leaks, and algorithmic complexity",
|
|
"mode": "all",
|
|
"model": "ollama-cloud/kimi-k2.6:cloud",
|
|
"color": "#0D9488",
|
|
"permission": {
|
|
"read": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"the-fixer": "allow",
|
|
"security-auditor": "allow"
|
|
}
|
|
}
|
|
},
|
|
"security-auditor": {
|
|
"description": "Scans for security vulnerabilities, OWASP Top 10, dependency CVEs, and hardcoded secrets",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/kimi-k2.6:cloud",
|
|
"color": "#DC2626",
|
|
"permission": {
|
|
"read": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"the-fixer": "allow",
|
|
"release-manager": "allow"
|
|
}
|
|
}
|
|
},
|
|
"visual-tester": {
|
|
"description": "Visual regression testing agent that compares screenshots and detects UI differences using pixelmatch and image diff",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/glm-5.1",
|
|
"permission": {
|
|
"read": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"orchestrator": {
|
|
"description": "Main dispatcher. Routes tasks between agents based on Issue status and manages the workflow state machine",
|
|
"mode": "all",
|
|
"model": "ollama-cloud/kimi-k2.6:cloud",
|
|
"color": "#7C3AED",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"history-miner": "allow",
|
|
"system-analyst": "allow",
|
|
"sdet-engineer": "allow",
|
|
"lead-developer": "allow",
|
|
"code-skeptic": "allow",
|
|
"the-fixer": "allow",
|
|
"performance-engineer": "allow",
|
|
"security-auditor": "allow",
|
|
"release-manager": "allow",
|
|
"evaluator": "allow",
|
|
"prompt-optimizer": "allow",
|
|
"product-owner": "allow",
|
|
"requirement-refiner": "allow",
|
|
"frontend-developer": "allow",
|
|
"browser-automation": "allow",
|
|
"visual-tester": "allow",
|
|
"planner": "allow",
|
|
"reflector": "allow",
|
|
"memory-manager": "allow",
|
|
"devops-engineer": "allow"
|
|
}
|
|
}
|
|
},
|
|
"release-manager": {
|
|
"description": "Manages git operations, semantic versioning, branching, and deployments. Ensures clean history",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/qwen3.6-plus",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"webfetch": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"evaluator": {
|
|
"description": "Scores agent effectiveness after task completion for continuous improvement",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/glm-5.1",
|
|
"color": "#047857",
|
|
"permission": {
|
|
"read": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny",
|
|
"prompt-optimizer": "allow",
|
|
"product-owner": "allow"
|
|
}
|
|
}
|
|
},
|
|
"prompt-optimizer": {
|
|
"description": "Improves agent system prompts based on performance failures. Meta-learner for prompt optimization",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/glm-5.1",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"product-owner": {
|
|
"description": "Manages issue checklists, status labels, tracks progress and coordinates with human users",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/glm-5.1",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"webfetch": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"agent-architect": {
|
|
"description": "Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/kimi-k2.6:cloud",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"capability-analyst": {
|
|
"description": "Analyzes task requirements against available agents, workflows, and skills. Identifies gaps and recommends new components.",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/glm-5.1",
|
|
"permission": {
|
|
"read": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"workflow-architect": {
|
|
"description": "Creates and maintains workflow definitions with complete architecture, Gitea integration, and quality gates",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/glm-5.1",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"markdown-validator": {
|
|
"description": "Validates and corrects Markdown descriptions for Gitea issues",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/deepseek-v4-pro-max",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"browser-automation": {
|
|
"description": "Browser automation agent using Playwright MCP for E2E testing, form filling, navigation, and web interaction",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/qwen3-coder:480b",
|
|
"permission": {
|
|
"read": "allow",
|
|
"edit": "allow",
|
|
"write": "allow",
|
|
"bash": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"planner": {
|
|
"description": "Advanced task planner using Chain of Thought, Tree of Thoughts, and Plan-Execute-Reflect",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/deepseek-v4-pro-max",
|
|
"color": "#F59E0B",
|
|
"permission": {
|
|
"read": "allow",
|
|
"write": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"reflector": {
|
|
"description": "Self-reflection agent using Reflexion pattern - learns from mistakes",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/deepseek-v4-pro-max",
|
|
"color": "#10B981",
|
|
"permission": {
|
|
"read": "allow",
|
|
"grep": "allow",
|
|
"glob": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
},
|
|
"memory-manager": {
|
|
"description": "Manages agent memory systems - short-term (context), long-term (vector store), and episodic (experiences)",
|
|
"mode": "subagent",
|
|
"model": "ollama-cloud/qwen3.6-plus",
|
|
"color": "#8B5CF6",
|
|
"permission": {
|
|
"read": "allow",
|
|
"write": "allow",
|
|
"glob": "allow",
|
|
"grep": "allow",
|
|
"task": {
|
|
"*": "deny"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |