Kilo Kit MCP

=20">

Kilo-Kit: Autonomous Cognitive Flow & Quality Engine for AI Coding Agents

Version: 1.9.1
Author: Kilo-Kit Team
License: Apache 2.0

Kilo-Kit is an agentic MCP runtime and curated 180-skill catalog designed to enforce grounded diagnosis, Tree-of-Thoughts architectural planning, adversarial red-teaming, 4D quality verification, and continuous SQLite self-improvement for AI coding assistants.

🧠 Core Architectural Pillars:

1. Division of Labor (Cortex vs Limbs): Kilo-Kit acts as the high-level cognitive brain (Tree of Thoughts, 5-Whys root cause analysis, adversarial stress-testing, context compaction) while host clients handle surgical I/O.
2. Kilo-Sentinel Supervisor & Circuit Breaker: Real-time middleware enforcing Pre-flight Grounding Locks (no editing unread files), loop tripwires (identical call and edit-thrashing detection), and SQLite trajectory logging (katl_trajectories).
3. Triangulated Cognitive Synthesis & Low-Confidence Escalation: Combines internal SQLite memory recall, GitHub 10k+ stars patterns, and ToT DAG benchmarking (kilo_triangulate_research), with automatic subagent delegation when confidence < 0.70.
4. Fuzzy Skill & Alias Resolver: Instant, resilient skill loading with support for aliases (brainstorming, diagnose, playwright, clean-code, tdd, grounded-research-benchmark).
5. 4D Quality Assurance & Playwright E2E Gate: Validates Given-When-Then acceptance criteria, clean code interfaces, UI/UX aesthetics, and automated Playwright browser/DOM verification before work is marked complete.

🏛️ System Architecture & Division of Labor

Kilo-Kit enforces a strict architectural boundary between High-Level Cognitive Reasoning (Cortex) and Surgical I/O Execution (Limbs):

flowchart TD
    Clients["🖥️ Host AI Clients<br/>(Claude Code / Antigravity / Cursor / Gemini CLI)"]
    
    Sentinel["🛡️ Kilo-Sentinel Supervisor & Circuit Breaker<br/>(Pre-flight Grounding Lock • Loop Tripwire • Step Budget)"]
    
    subgraph Cortex["🧠 Kilo-Kit Cognitive Cortex (MCP Runtime)"]
        direction TB
        C4["🏛️ C4 5-Gate Lifecycle Controller"]
        Engines["⚙️ 6 Cognitive Engines<br/>(ToT DAG • Adversarial Grill • 5-Whys • Grounded Synthesis)"]
        Skills["📚 180 Curated Skills Catalog"]
        Limbs["🛠️ Safe Execution Limbs<br/>(Atomic Write • AST Edit • Security Filtered Exec)"]
        C4 --> Engines
        C4 --> Skills
        C4 --> Limbs
    end
    
    DB[("💾 SQLite Atomic Memory<br/>(cognitive_triangulations • katl_trajectories • facts)")]
    
    Clients <-->|MCP Protocol / stdio| Sentinel
    Sentinel <--> Cortex
    Cortex <--> DB

🔄 C4 Cognitive Lifecycle & Low-Confidence Escalator

All agent tasks flow through a deterministic 5-Gate state machine. Unauthorized file mutations prior to Gate 3 approval are blocked at the server level:

flowchart LR
    G1["<b>Gate 1: Grounded Probe</b><br/>• Memory Recall<br/>• Codebase Probe"]
    
    G2["<b>Gate 2: Cognitive Reasoning</b><br/>• 3-Option ToT DAG<br/>• Adversarial Grill<br/>• Low-Confidence Escalator"]
    
    G3["<b>Gate 3: Approval</b><br/>• Plan Locked<br/>• Skills Injected"]
    
    G4["<b>Gate 4: Execution</b><br/>• Defense-in-Depth<br/>• Sentinel Guarded"]
    
    G5["<b>Gate 5: 4D QA</b><br/>• Playwright E2E<br/>• SQLite Reflection"]

    G1 --> G2
    G2 -->|Confidence >= 0.70| G3
    G2 -.->|Confidence < 0.70<br/>Escalation| Subagent["🔬 Research Subagent<br/>(GitHub & Docs Sandbox)"]
    Subagent -.-> G2
    G3 --> G4
    G4 --> G5
    G4 -.->|3x Loop Detected| Breaker["🛑 Circuit Breaker<br/>(Supervised Reset)"]
    Breaker -.-> G1

🛡️ Protocol-Level Hard-Gate Enforcement

Traditional prompt rules (.cursorrules, CLAUDE.md) suffer from prompt drift. Kilo-Kit enforces safety via JSON-RPC Interceptor Middleware:

flowchart TD
    Req["👤 User Prompt"] --> Agent["🤖 Host AI Agent"]
    
    Agent -->|1. Unauthorized Edit Attempt| GateCheck{"🛡️ Kilo-Sentinel<br/>Pre-Flight Lock"}
    GateCheck -->|❌ Uninitialized / Unread File| Blocked["🛑 403 Hard-Gate Blocked<br/>(Forces Planning First)"]
    
    Blocked --> Plan["🧠 Gate 1 & 2: C4 Planning<br/>(kilo_orchestrate_task + kilo_triangulate_research)"]
    Plan --> SaveDB[("💾 Commit CoT to SQLite")]
    SaveDB --> Approval["👤 User Approves Plan"]
    
    Approval -->|2. Authorized Execution| GateCheck
    GateCheck -->|✅ State = READY| Exec["🚀 Gate 4: Safe Execution<br/>(kilo_write_file / kilo_edit_file)"]
    Exec --> Verify["✅ Gate 5: 4D Verification & SQLite Reflection"]

🧰 The 24 All-in-One MCP Tools Suite

Kilo-Kit provides a complete, self-contained execution and cognitive runtime:

📚 180 Curated Skills Catalog Taxonomy

Skills are organized into 6 functional modules with instant alias mapping:

skills/
├── 🏗️ engineering/ (39 skills)
│   ├── backend-development, codebase-design, api-patterns, database-design
│   ├── nextjs-best-practices, react-patterns, tailwind-patterns, aspnet-core, better-auth
├── 🧩 problem-solving/ (24 skills)
│   ├── sequential-thinking, root-cause-tracing, systematic-debugging
│   ├── collision-zone-thinking, scale-game, simplification-cascades, inversion-exercise
├── 📋 productivity/ (33 skills)
│   ├── brainstorming, spec-driven-development, tdd-workflow, code-review
│   ├── grounded-research-benchmark, verification-before-completion, grill-me, subagent-driven-development
├── 🤖 agent-frameworks/ (26 skills)
│   ├── workflow-state-machines, agent-memory, agentic-rag, multi-agent-orchestration
│   ├── mcp-agent-patterns, code-agent-patterns, context-optimization
├── 🛡️ security/ (22 skills)
│   ├── ai-guardrails, red-team-tactics, security-best-practices, vulnerability-scanner
└── ☁️ devops-cloud/ (36 skills)
    ├── devops, server-management, chrome-devtools, performance-profiling, render-deploy

Fuzzy Alias Resolution: Calling kilo_get_skill("brainstorming") automatically loads productivity/brainstorming/SKILL.md.

⚡ Quick Start

1. Fast Setup (Recommended)

Install globally and automatically configure all detected AI clients (Cursor, Claude, Windsurf, Antigravity, Gemini):

npm install -g @vodailocz/kilo-kit-mcp
kilo-kit-init global

Verify system health:

kilo-kit-doctor

2. Zero-Install NPX (IDE Direct Integration)

Add Kilo-Kit directly to your client's MCP configuration without installing globally:

{
  "mcpServers": {
    "kilo-kit": {
      "command": "npx",
      "args": ["-y", "@vodailocz/kilo-kit-mcp"]
    }
  }
}

Supported in Cursor (.cursor/mcp.json), Claude Desktop (claude_desktop_config.json), Windsurf, and Antigravity / Gemini CLI.

3. Team Repository Rollout

Bootstrap the Kilo-Kit C4 Cognitive Protocol into your project repository (CLAUDE.md, AGENTS.md, GEMINI.md):

kilo-kit-init init --client all
git add CLAUDE.md AGENTS.md GEMINI.md
git commit -m "chore: configure Kilo-Kit C4 protocol"

Or use the global git alias: git kilo-init

📊 Empirical Verification & Quality Benchmarks

📖 Documentation Directory Index

For detailed specifications, protocol definitions, and developer guides, explore the docs/ directory:

• 🏛️ **Architecture Overview** - System topology, Cortex vs Limbs, and Memory schema.
• 📜 **C4 Protocol Specification** - 5-Gate lifecycle state transitions and invariant rules.
• 🧰 **MCP Tooling Reference** - JSON schemas, error codes, and tool calling examples.
• 📚 **Skills Taxonomy & Authoring** - Skill catalog guidelines and authoring standard.
• 📊 **Benchmarks & Methodology** - Token reduction experiments and SWE-bench alignment.
• 🛡️ **Security & Guardrails** - Circuit breaker, input sanitization, and blast-radius control.

🧪 Development, Testing & Verification

# Clone repository
git clone https://github.com/VoDaiLocz/KILO-KIT.git
cd KILO-KIT
npm install

# Run unit test suites (15/15 test files, 68/68 tests passing)
npm test

# Run full health diagnostics
npm run doctor

# Validate 100% of 180 skills against structural quality gates
node src/tools/validate-skill.js --all skills

📄 License

Distributed under the Apache 2.0 License. See LICENSE for more details.