More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Skills Switch

    1

    A plugin that adds a Skill Switch page to the Settings window: see every skill installed in the profile, flip each one on or off, switch a whole pack at once, and give skills your own display names.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    Many large-scale skill packs are designed for complex projects, but in small-to-medium tasks, you typically only need a small fraction of them. Even loading just two or three heavier skills—such as brainstorming, writing-plans, and TDD—can add 6k–9k tokens of context overhead, roughly 30%–40% of the cost of a focused conversation. In subagent-driven development scenarios, this overhead is amplified even further, since every task may spawn a new subagent with its own independent context. In practice, total costs often rise by 2–4x.

    The goal of dsh-skills-switch is to turn these subagents and skills into controllable toggles. Only the skills and subagents genuinely needed for the current task are loaded, significantly reducing token consumption, cutting out useless context, improving development efficiency, and making agent-driven workflows more controllable and better suited to real-world projects.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.

    Token estimates are approximations. Native frontmatter flags only work in DeepSeek Harness; other runtimes require directory quarantine. Requires Node.js for bundled scripts.

    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 buying a skill.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Permissions

    Read Files
    Write Files
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    The Skill Hygiene Pack programmatically audits and disables unused tool definitions that otherwise bloat your system prompt. By moving inactive skills to a quarantine directory, it prevents the LLM from 'seeing' them, which drastically reduces token costs per turn and eliminates execution errors caused by naming conflicts.

    It is designed to work with major developer-focused agent runtimes including Claude Code, DeepSeek Harness, Cursor, and Copilot CLI. The scripts interface with standard skill directory structures on macOS and Linux to manage how these tools are exposed to the model.

    Yes, the 'Skill Packs' feature allows you to define custom JSON profiles (e.g., 'React Development' or 'Security Audit'). You can switch between these profiles in seconds to ensure your agent only has the relevant tools active for your current task.

    Unlike a standard delete, this pack uses a 'Lossless Quarantine' method that moves files to a .disabled directory. This preserves all your scripts, metadata, and history, allowing you to re-enable a skill instantly without having to reinstall or reconfigure it.

    The purchase includes the core Node.js management toolkit (audit, toggle, and group scripts), documentation for configuration, and a template for creating your own Skill Packs. You receive all the utility scripts necessary to manage your agent's runtime environment.

    New in Prompt & Skill Engineering