Why Dude? — Decision Framing for AI Agents

    1

    Challenge the assumption behind a consequential decision before your AI agent helps execute it. Reach one clear, justified next move.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Why Dude? — Decision Framing for AI Agents

    Example session with this skill installed

    Developer-authored synthetic illustration from the project README; not a recorded user session or evidence of usefulness.

    $why-dude should I rebuild this in Next.js?

    • Read your context and instructions
    • Compiled the why dude

    Synthetic illustration, not a recorded agent run:

    Why Dude: A rebuild only follows if the current stack fails a requirement that matters. What verified requirement can the current stack not meet?

    You: None. No requirement is blocked.

    Why Dude: Do not rebuild on this basis. The necessary premise is absent, so drop the rebuild option (abandon).

    Why Dude is complete for this decision.

    This example illustrates the intended question pacing and stopping behavior. It does not establish improved decisions or reliable usefulness.

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

    About this skill

    Why Dude is an explicitly invoked agent skill that helps test whether a proposed action follows from the right objective, evidence, constraints, options and values.

    Rather than repeatedly asking “why,” it traces only the nearest assumption capable of changing the decision. It can ask one discriminating question at a time, then ends with one bounded outcome: retain the decision, reframe the problem, abandon an unsupported option, or investigate the smallest unresolved fact.

    It leaves cheap, reversible choices alone, respects values you've already examined and hands control back to your normal agent after concluding.

    This is a public beta (v0.11.0). Developer-authored synthetic tests passed, but the skill has not been independently shown to improve real-world decision quality. Feedback and failure reports are welcome.

    Author: Aadi Dash. MIT License, copyright (c) 2026 Aadi Dash. Canonical source and installation instructions: https://github.com/aad1dash/why-dude

    Public beta v0.11.0. Developer-authored synthetic checks are not independent evidence of improved real-world decision quality or superiority to ordinary prompting. Behavior depends on the host agent and supplied context. Not a substitute for medical, legal or financial advice.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 25 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed25 days ago

    What's inside

    Frequently Asked Questions

    No. v0.11.0 is a public beta. Developer-authored synthetic checks passed, but they do not establish improved real-world decisions, reliable usefulness, or superiority to ordinary prompting.

    Invoke explicitly on one bounded decision, for example: $why-dude should I rebuild this in Next.js? The README documents direct installation for Codex. Equivalent behavior across other SKILL.md-compatible agents has not been tested.

    The canonical public source is https://github.com/aad1dash/why-dude, by Aadi Dash, under the MIT License. The skill itself records nothing and adds no telemetry or external network calls. Your host agent platform may still process the conversation. Do not include sensitive information unless that platform is appropriate.

    New in Productivity