Architector Onboard Repo

    1

    Phased import of a codebase into MCP Architector — structure first, then one module at a time with facts, then validate — without dumping the whole repo into context.

    Free

    2 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Architector Onboard Repo

    Example session with this skill installed

    Onboard the current workspace into Architector, it is a TypeScript backend called "nexus-api".

    • Read your context and instructions
    • Compiled the architector onboard repo

    I have started the onboarding process for the

    nexus-api workspace. I identified the project and have mapped out the initial module structure based on the directory hierarchy.

    Onboarding Status: nexus-api

    CategoryValue
    Project ID_qs_nexus-api (Created)
    Current PhasePhase 1 (Structure)
    Modules Detectedauth, billing, users, gateway, shared
    Last ValidationValid (0 issues)
    Data FlowInferred from module-dependencies

    Proposed Module Order

    1. shared: Common utilities and types.
    2. auth: Identity management and JWT logic.
    3. users: User profiles and persistence.
    4. billing: Stripe integration and subscription logic.
    5. gateway: Public HTTP endpoints and routing.

    Next steps

    1. Confirm the module list and order above.
    2. I will proceed to Phase 2, reading the shared module files first to extract entities and constants.
    3. Say "continue" to begin the incremental module import.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Phased import of a codebase into MCP Architector — structure first, then one module at a time with facts, then validate — without dumping the whole repo into context. Use when the user asks to onboard or import a repo into architector, document architecture module by module, or sync a fresh clone into ~/.mcp-architector.

    Requires Node.js 18 and mcp-architector MCP server. Cannot diagnose existing broken graphs or perform domain lookups. Optimized for batches of ~50 entries to maintain context hygiene.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Architector MCP
    Node.js
    Architect MCP

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill automates the discovery and indexing of large codebases into a structured architectural graph, solving the problem of context overflow and manual documentation rot by processing repositories in manageable, validated modules.

    You must have the `mcp-architector` MCP server (Node.js 18+) installed and configured in your AI agent's environment, as this skill acts as a specialized workflow layer for that server.

    Yes, the 'Discovery' and 'Scaffolding' phases are designed to analyze top-level directories and dependency edges, making it ideal for mapping out complex legacy monoliths into distinct vertical slices.

    The skill maps project structures and dependency flows by reading local files, but it does not perform automated domain term lookups or post-hoc diagnosis of pre-existing broken graphs.

    Purchasing this skill grants you access to the optimized multi-step workflow logic and prompt sequences required to orchestrate the Architector server for repository ingestion.

    While optimized for TypeScript projects, the skill utilizes standard filesystem operations and dependency edge analysis that can be applied to most structured codebases compatible with the MCP Architector server.

    New in LLM Ops