Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    ringmaster

    1

    Multi-role agent orchestration skill for structured coding, surgical file edits, and project hygiene.

    Free

    Security scanned
    ringmaster

    ringmaster

    Example session with this skill installed

    ringmaster, bootstrap the project. I need to add a new auth provider to the existing backend.

    To commit latest work
    /ringmaster-hygiene

    • Read your context and instructions
    • Compiled the ringmaster

    Ringmaster session initialized. Reference pack loaded successfully from references/.

    Active rules for this session

    • Architectural Lead: All wide edits require Plan mode approval.
    • Surgical Discipline: Re-read files before editing; no full-file overwrites.
    • Role Isolation: Tasks must pass through Reviewer and Tester core values.
    • Hygiene Check: Documentation and commits must follow the hygiene guide.
    • Wait Guard: Jobs exceeding 15 minutes trigger a "coffee" wait rung.

    Implementation Plan: Auth Provider Integration

    RoleTask DescriptionReference Document
    ArchitectDefine the interface for the new OAuthProvider and update AuthFactory.architect-core-values.md
    ImplementerCreate GoogleAuthProvider.ts and update config/auth.ts surgically.implementer-core-values.md
    ReviewerAudit the implementation for secret leakage and interface compliance.reviewer-core-values.md
    TesterWrite integration tests for the login flow and mock the provider response.tester-core-values.md

    Next steps

    1. I will now assume the Architect role to draft the interface changes in Plan mode.
    2. Review the proposed AuthFactory changes before I move to implementation.
    3. Prepare the environment variables for the new provider in your .env.local.

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

    About this skill

    The different roles on development teams exist for a reason. Humans need to look at code from different points of view. LLMS are no different.

    Ringmaster leverages 41 of software development experience by structuring your AI assistant to act like a whole development team.

    This hygiene ends up making your coding agents smarter, because LLMs "forget".

    What it does

    • Role-based routing coordinates tasks between Architect, Implementer, Reviewer, and Tester roles based on specific cognitive points of view.
    • Surgical file editing prevents accidental regressions by enforcing a strict re-read and partial-edit discipline.
    • Hygiene enforcement automates documentation updates and commit standards during development checkpoints before the LLM forgets.
    • Workload management implements wait-credit guards for long-running jobs, categorized by duration from instant to overnight. This prevents token burn for long running tasks from the LLM reloading the context for each check.
    • Planning-first approach requires a plan mode activation before any wide or sensitive edits to the codebase.

    How it works

    1. Initialize the session by loading the reference pack and confirming the active project rules.
    2. Route the specific task to the appropriate role (Architect for planning, Tester for verification, etc.) after reading core values.
    3. Execute edits using strict file discipline, starting with plan mode for significant changes.
    4. Audit the changes through the Reviewer role and apply hygiene checkpoints for documentation and commits.

    Frameworks & tools

    This skill is designed for use with Claude Code, Cursor, or similar agentic IDEs. It relies on a local references/ directory containing the core Markdown rulebooks and integrates with git for worktree management.

    Why this beats prompting it yourself

    I've been coding for 43 years now, learned stuff. Found problems with AI driven coding, Fixed them based on my experience.

    Use cases

    • Bootstrap a new project with strict architectural and testing standards.
    • Perform sensitive refactoring across multiple files without breaking the build.
    • Enforce consistent commit messages and documentation updates across a team.

    Known limitations

    Requires a specific reference directory structure to function. The wait-credit guard requires manual time tracking if not used within a supported plugin environment.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scanned

    Verified clean today

    • Free to download with an account

    Requires

    Git

    Listedtoday

    What's inside

    Frequently Asked Questions