superkit-mcp-server 1.1.4 → 1.2.0

package/ARCHITECTURE.md

@@ -1,102 +1,102 @@
-# Super-Kit Architecture
-
-> Comprehensive AI Agent Capability Expansion Toolkit - Merged from Gemini-Kit and Ag-Kit
-
----
-
-## 📋 Overview
-
-Super-Kit is a model-agnostic and agent-agnostic toolkit designed to provide a highly structured engineering loop alongside granular domain expertise. It merges the dynamic workflows of Gemini-Kit with the deep role-based specificities of Ag-Kit.
-
-- **Super Engineers & Domain Specialists** - A T-shaped team of AI personas.
-- **Categorized Skills** - Technical knowledge, meta-engineering, and workflow instructions.
-- **Unified Workflows** - Slash command procedures driving the Compound Engineering Loop.
-
----
-
-## 🏗️ Directory Structure
-
-```plaintext
-super-kit/
-├── ARCHITECTURE.md          # This file
-├── SUPERKIT.md              # Global rules and activation protocol
-├── .core/                   # Core engine-independent logic
-│   ├── rules/               # Universal mandates (e.g., clean-code, security-first)
-├── agents/                  # The T-Shaped AI Team Personas
-├── skills/                  # The Knowledge Modules
-│   ├── meta/                # Session-resume, compound-docs, file-todos (from gemini-kit)
-│   ├── tech/                # Node.js, React, Python, Prisma (from ag-kit)
-│   └── workflows/           # TDD, CI/CD, Code Review checklists
-└── workflows/               # Slash commands and lifecycle loops
-```
-
----
-
-## 🤖 Agents
-
-Super-Kit provides a T-Shaped AI team: a core engineering team focused on process, supported by deep domain specialists.
-
-### Core Team (Process Execution)
-- `planner`: Creates detailed implementation plans.
-- `scout`: Explores the codebase and resolves dependencies.
-- `coder`: Writes clean, efficient code following patterns.
-- `tester`: Writes unit tests and ensures quality.
-- `reviewer`: Suggests improvements and ensures security.
-- `git-manager`: Manages version control operations.
-- `orchestrator`: Coordinates complex, multi-agent tasks.
-
-### Domain Specialists (Context & Logic)
-- `database-architect`: Database schema, scaling, and ORM usage (Prisma, SQL).
-- `security-auditor`: Comprehensive security audits, OWASP checks.
-- `frontend-specialist`: React, Next.js, and complex UI/UX architectures.
-- `backend-specialist`: API layers, microservices, and Node.js/Python servers.
-- `ui-designer`: Visual layouts, animations, and Tailwind integrations.
-
-### Fintech Specialists
-- `data-engineer`: ETL pipelines, data scaling, idempotency.
-- `quant-developer`: Financial modeling, backtesting engines, and low-latency systems.
-
-*(Note: Generic tasks invoke the `coder`, who leverages `database-architect` and `quant-developer` knowledge contextually.)*
-
----
-
-## 🧩 Skills
-
-Skills are context blocks loaded by Agents based on the active task.
-
-### Tech Skills (`skills/tech/`)
-Contains granular knowledge bases for specific tools (e.g., `react-best-practices`, `api-patterns`, `python-patterns`, `docker-expert`).
-
-### Meta Skills (`skills/meta/`)
-Contains lifecycle operation patterns (e.g., `session-resume`, `compound-docs`, `file-todos`) to ensure knowledge is carried across sessions.
-
----
-
-## 🔄 Workflows
-
-Workflows are standard operating procedures invoked via slash commands (e.g. `/plan`, `/work`, `/compound`, `/explore`).
-
-### The Compound Loop
-The primary operating directive for building sustainable software:
-`/explore` → `/plan` → `/work` → `/review` → `/compound`
-
-1. **Explore**: Investigate the codebase and gather requirements.
-2. **Plan**: Write the task boundaries and solution architecture.
-3. **Work**: The Core Team executes code generation.
-4. **Review**: Automated auditing via `src/tools/checklist.ts`.
-5. **Compound**: Output reusable solutions to `docs/solutions/`.
-
-## ⚙️ Usage & Agnosticism
-
-Super-Kit is designed to be injected into any agentic platform (Cline, Cursor, Gemini, Aider, GitHub Copilot). 
-The entry point is reading `SUPERKIT.md` to establish global rules. 
-
-### How to Point Changing Agents to the Entrypoint:
-
-- **Standard Agents**: Reference `@SUPERKIT.md` in your prompt, or set its content as your persistent user rules for the project.
-- **Cursor/Windsurf**: Reference `@SUPERKIT.md` in your Composer/Chat, or set the content of `SUPERKIT.md` as your project's `.cursorrules` / `.windsurfrules`.
-- **Cline (VS Code)**: Set the content of `SUPERKIT.md` as your custom instructions in the Cline settings, or add an `@SUPERKIT.md` command in your prompt.
-- **Gemini / Google AI Studio**: Supply `SUPERKIT.md` as your System Prompt instructions.
-- **Aider**: Run aider with the message `aider --message "Read SUPERKIT.md for your system instructions before doing anything else."`
-
-Once the agent has loaded `SUPERKIT.md`, it will follow the instructions to activate the appropriate `@agent` which dynamically reads `SKILL.md` from the relevant directories.
+# Super-Kit Architecture
+
+> Comprehensive AI Agent Capability Expansion Toolkit - Merged from Gemini-Kit and Ag-Kit
+
+---
+
+## 📋 Overview
+
+Super-Kit is a model-agnostic and agent-agnostic toolkit designed to provide a highly structured engineering loop alongside granular domain expertise. It merges the dynamic workflows of Gemini-Kit with the deep role-based specificities of Ag-Kit.
+
+- **Super Engineers & Domain Specialists** - A T-shaped team of AI personas.
+- **Categorized Skills** - Technical knowledge, meta-engineering, and workflow instructions.
+- **Unified Workflows** - Slash command procedures driving the Compound Engineering Loop.
+
+---
+
+## 🏗️ Directory Structure
+
+```plaintext
+super-kit/
+├── ARCHITECTURE.md          # This file
+├── SUPERKIT.md              # Global rules and activation protocol
+├── .core/                   # Core engine-independent logic
+│   ├── rules/               # Universal mandates (e.g., clean-code, security-first)
+├── agents/                  # The T-Shaped AI Team Personas
+├── skills/                  # The Knowledge Modules
+│   ├── meta/                # Session-resume, compound-docs, file-todos (from gemini-kit)
+│   ├── tech/                # Node.js, React, Python, Prisma (from ag-kit)
+│   └── workflows/           # TDD, CI/CD, Code Review checklists
+└── workflows/               # Slash commands and lifecycle loops
+```
+
+---
+
+## 🤖 Agents
+
+Super-Kit provides a T-Shaped AI team: a core engineering team focused on process, supported by deep domain specialists.
+
+### Core Team (Process Execution)
+- `planner`: Creates detailed implementation plans.
+- `scout`: Explores the codebase and resolves dependencies.
+- `coder`: Writes clean, efficient code following patterns.
+- `tester`: Writes unit tests and ensures quality.
+- `reviewer`: Suggests improvements and ensures security.
+- `git-manager`: Manages version control operations.
+- `orchestrator`: Coordinates complex, multi-agent tasks.
+
+### Domain Specialists (Context & Logic)
+- `database-architect`: Database schema, scaling, and ORM usage (Prisma, SQL).
+- `security-auditor`: Comprehensive security audits, OWASP checks.
+- `frontend-specialist`: React, Next.js, and complex UI/UX architectures.
+- `backend-specialist`: API layers, microservices, and Node.js/Python servers.
+- `ui-designer`: Visual layouts, animations, and Tailwind integrations.
+
+### Fintech Specialists
+- `data-engineer`: ETL pipelines, data scaling, idempotency.
+- `quant-developer`: Financial modeling, backtesting engines, and low-latency systems.
+
+*(Note: Generic tasks invoke the `coder`, who leverages `database-architect` and `quant-developer` knowledge contextually.)*
+
+---
+
+## 🧩 Skills
+
+Skills are context blocks loaded by Agents based on the active task.
+
+### Tech Skills (`skills/tech/`)
+Contains granular knowledge bases for specific tools (e.g., `react-best-practices`, `api-patterns`, `python-patterns`, `docker-expert`).
+
+### Meta Skills (`skills/meta/`)
+Contains lifecycle operation patterns (e.g., `session-resume`, `compound-docs`, `file-todos`) to ensure knowledge is carried across sessions.
+
+---
+
+## 🔄 Workflows
+
+Workflows are standard operating procedures invoked via slash commands (e.g. `/plan`, `/work`, `/compound`, `/explore`).
+
+### The Compound Loop
+The primary operating directive for building sustainable software:
+`/explore` → `/plan` → `/work` → `/review` → `/compound`
+
+1. **Explore**: Investigate the codebase and gather requirements.
+2. **Plan**: Write the task boundaries and solution architecture.
+3. **Work**: The Core Team executes code generation.
+4. **Review**: Automated auditing via `src/tools/checklist.ts`.
+5. **Compound**: Output reusable solutions to `docs/solutions/`.
+
+## ⚙️ Usage & Agnosticism
+
+Super-Kit is designed to be injected into any agentic platform (Cline, Cursor, Gemini, Aider, GitHub Copilot). 
+The entry point is reading `SUPERKIT.md` to establish global rules. 
+
+### How to Point Changing Agents to the Entrypoint:
+
+- **Standard Agents**: Reference `@SUPERKIT.md` in your prompt, or set its content as your persistent user rules for the project.
+- **Cursor/Windsurf**: Reference `@SUPERKIT.md` in your Composer/Chat, or set the content of `SUPERKIT.md` as your project's `.cursorrules` / `.windsurfrules`.
+- **Cline (VS Code)**: Set the content of `SUPERKIT.md` as your custom instructions in the Cline settings, or add an `@SUPERKIT.md` command in your prompt.
+- **Gemini / Google AI Studio**: Supply `SUPERKIT.md` as your System Prompt instructions.
+- **Aider**: Run aider with the message `aider --message "Read SUPERKIT.md for your system instructions before doing anything else."`
+
+Once the agent has loaded `SUPERKIT.md`, it will follow the instructions to activate the appropriate `@agent` which dynamically reads `SKILL.md` from the relevant directories.

package/README.md

@@ -1,71 +1,71 @@
-# Super-Kit
-
-Super-Kit is a modular repository containing instructions, workflows, skills, and specializations for AI coding agents. By structuring AI agent contexts into individual files, it allows large language model agents to load specific knowledge on the fly instead of relying on massive and bloated static system prompts.
-
-While the primary purpose is to compund the knowledge of engineering, I will add more domains as I see fit.
-
-🔗 **GitHub Repository:** [dgkngk/super-kit](https://github.com/dgkngk/super-kit)
-
-🔗 **NPM Package:** [superkit-mcp-server](https://www.npmjs.com/package/superkit-mcp-server)
-
-## Directory Structure
-- `agents/`: Contains instructions and guidelines for specialized AI roles (e.g., `data-engineer`).
-- `skills/`: Contains technology-specific or meta skills (patterns, best practices) the agent can load dynamically (e.g., `react-best-practices`).
-- `workflows/`: Contains step-by-step interactive slash-commands to guide the AI workflow (e.g., `/plan`, `/explore`).
-- `src/`: The Model Context Protocol (MCP) server that exposes all these assets directly to compatible AI platforms.
-
-## Providing the Kit to Your AI
-
-The easiest way to power up your agent with this toolkit is to use the included MCP server.
-
-You can launch it directly using `npx`:
-
-```bash
-npx -y superkit-mcp-server
-```
-
-## Available Tools
-
-- **`list_superkit_assets`**: Lists all available agents, skills (tech/meta), and workflows in the Super-Kit repository.
-- **`load_superkit_agent`**: Loads the system instructions and guidelines for a specific specialist agent (e.g., `data-engineer`).
-- **`load_superkit_skill`**: Loads the skill instructions (`SKILL.md`) for a specific category and skill (e.g., category: `tech`, name: `react-best-practices`).
-- **`load_superkit_workflow`**: Loads the instructions for a specific slash-command workflow (e.g., `work`, `explore`).
-- **`call_tool_checklist`**: Executes the native TypeScript validation suite (security, web accessibility, react performance, testing, API structure) on a target project location via the MCP environment instead of generic bash loops.
-
-## Available Prompts
-
-The Super-Kit MCP server exposes all workflows inside the `workflows/` directory dynamically as **MCP Prompts**. AI agents can invoke `GetPromptRequestSchema` to instantly load complex workflows (e.g., `plan-compound`, `review-compound`) along with their security and validation tooling straight into their context.
-
-## Manual Installation and Configuration
-
-If you cloned this repository locally, you can build and use the MCP server directly:
-
-```bash
-cd super-kit
-npm install
-npm run build
-```
-
-### Configuring in AI Platforms
-
-#### Cline / Roo (VS Code)
-Add the following to your `cline_mcp_settings.json`:
-```json
-{
-  "mcpServers": {
-    "superkit": {
-      "command": "node",
-      "args": ["/absolute/path/to/super-kit/build/index.js"]
-    }
-  }
-}
-```
-
-#### Cursor / Windsurf
-Go to Settings -> Features -> MCP Servers.
-Add a new stdio server:
-- Name: `superkit`
-- Command: `node /absolute/path/to/super-kit/build/index.js`
-
-## How it works
-The built-in MCP server reads directly from the `super-kit` directory, resolving paths safely to prevent traversal attacks. It automatically parses and returns the Markdown contents of the structural elements so your AI agent always has the right context in mind.
+# Super-Kit
+
+Super-Kit is a modular repository containing instructions, workflows, skills, and specializations for AI coding agents. By structuring AI agent contexts into individual files, it allows large language model agents to load specific knowledge on the fly instead of relying on massive and bloated static system prompts.
+
+While the primary purpose is to compund the knowledge of engineering, I will add more domains as I see fit.
+
+🔗 **GitHub Repository:** [dgkngk/super-kit](https://github.com/dgkngk/super-kit)
+
+🔗 **NPM Package:** [superkit-mcp-server](https://www.npmjs.com/package/superkit-mcp-server)
+
+## Directory Structure
+- `agents/`: Contains instructions and guidelines for specialized AI roles (e.g., `data-engineer`).
+- `skills/`: Contains technology-specific or meta skills (patterns, best practices) the agent can load dynamically (e.g., `react-best-practices`).
+- `workflows/`: Contains step-by-step interactive slash-commands to guide the AI workflow (e.g., `/plan`, `/explore`).
+- `src/`: The Model Context Protocol (MCP) server that exposes all these assets directly to compatible AI platforms.
+
+## Providing the Kit to Your AI
+
+The easiest way to power up your agent with this toolkit is to use the included MCP server.
+
+You can launch it directly using `npx`:
+
+```bash
+npx -y superkit-mcp-server
+```
+
+## Available Tools
+
+- **`list_superkit_assets`**: Lists all available agents, skills (tech/meta), and workflows in the Super-Kit repository.
+- **`load_superkit_agent`**: Loads the system instructions and guidelines for a specific specialist agent (e.g., `data-engineer`).
+- **`load_superkit_skill`**: Loads the skill instructions (`SKILL.md`) for a specific category and skill (e.g., category: `tech`, name: `react-best-practices`).
+- **`load_superkit_workflow`**: Loads the instructions for a specific slash-command workflow (e.g., `work`, `explore`).
+- **`call_tool_checklist`**: Executes the native TypeScript validation suite (security, web accessibility, react performance, testing, API structure) on a target project location via the MCP environment instead of generic bash loops.
+
+## Available Prompts
+
+The Super-Kit MCP server exposes all workflows inside the `workflows/` directory dynamically as **MCP Prompts**. AI agents can invoke `GetPromptRequestSchema` to instantly load complex workflows (e.g., `plan-compound`, `review-compound`) along with their security and validation tooling straight into their context.
+
+## Manual Installation and Configuration
+
+If you cloned this repository locally, you can build and use the MCP server directly:
+
+```bash
+cd super-kit
+npm install
+npm run build
+```
+
+### Configuring in AI Platforms
+
+#### Cline / Roo (VS Code)
+Add the following to your `cline_mcp_settings.json`:
+```json
+{
+  "mcpServers": {
+    "superkit": {
+      "command": "node",
+      "args": ["/absolute/path/to/super-kit/build/index.js"]
+    }
+  }
+}
+```
+
+#### Cursor / Windsurf
+Go to Settings -> Features -> MCP Servers.
+Add a new stdio server:
+- Name: `superkit`
+- Command: `node /absolute/path/to/super-kit/build/index.js`
+
+## How it works
+The built-in MCP server reads directly from the `super-kit` directory, resolving paths safely to prevent traversal attacks. It automatically parses and returns the Markdown contents of the structural elements so your AI agent always has the right context in mind.