MCP server Claude Code
One of 8 in .mcp.json
MCP server "telegram-relay" as configured in oimiragieo/agent-studio. Runs scripts/channels/telegram-relay.mjs with node. Needs 1 environment variable to run.
MCP server Claude Code
One of 8 in .mcp.json
Gives the agent read and write access to a set of allowed directories on the local filesystem. Runs locally from the @modelcontextprotocol/server-filesystem npm package.
MCP server Claude Code
One of 8 in .mcp.json
MCP server "git" as configured in oimiragieo/agent-studio. Runs locally from the @modelcontextprotocol/server-git npm package.
MCP server Claude Code
One of 8 in .mcp.json
Gives the agent a persistent knowledge graph it can write facts to and recall across sessions. Runs locally from the @modelcontextprotocol/server-memory npm package.
MCP server Claude Code
One of 8 in .mcp.json
Adds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package.
MCP server Claude Code
One of 8 in .mcp.json
Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package.
MCP server Claude Code
One of 8 in .mcp.json
MCP server "sqlite" as configured in oimiragieo/agent-studio. Runs locally from the @modelcontextprotocol/server-sqlite npm package.
MCP server Claude Code
One of 8 in .mcp.json
NPX wrapper for Microsoft's MarkItDown MCP server - run without Docker. Provides the same file conversion capabilities (PDF, Word, Excel, images, etc.) as the original Docker version but with easier setup and direct file system access. Runs locally from the markitdown-mcp-npx npm package.
Agent Claude Code
The agent system contains 119 specialized AI agents organized into 4 tiers. Each agent is a markdown file defining its role, tools, model preference, and behavioral instructions. Agents are spawned by the router via Task() — they never run independently.
Command Claude Code
Documentation index for all user-facing slash commands.
Command Claude Code
Ensure accessibility in UI (WCAG, semantic HTML, keyboard navigation).
Command Claude Code
Use advanced elicitation for meta-cognitive reasoning and refined outputs.
Command Claude Code
Invoke the agent-creator skill to create specialized agents.
Command Claude Code
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations.
Command Claude Code
The Agent Tool Contract — 5 principles for designing tools agents call reliably: predictable signature, rich errors, token-efficient output, idempotency, graceful degradation. Includes anti-pattern table with 8 common mistakes.
Command Claude Code
Refresh existing agent prompts/frontmatter with risk scoring and TDD gates.
Command Claude Code
Invoke the AI/ML expert skill for PyTorch, LangChain, and LLM integration.
Command Claude Code
Analyze project structure, tech stack, and health.
Command Claude Code
Invoke the Android expert skill for Jetpack Compose and Kotlin.
Command Claude Code
Angular framework expert including components, services, RxJS, templates, and testing.
Command Claude Code
Invoke the API development expert skill for REST and OpenAPI.
Command Claude Code
Invoke the architecture-review skill for design validation and anti-patterns.
Command Claude Code
Invoke the artifact-integrator skill for deep integration analysis.
Command Claude Code
Unified lifecycle management for all framework artifacts (skills, agents, hooks, workflows, templates, schemas).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: