Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    RTX Core Framework — Autonomous Agent System Skill

    1

    Every response follows a strict 3-step output protocol, and every task runs an Explore → Plan → Execute → Verify → Summarize loop with zero-tolerance internal review checklists.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    RTX Core Framework — Autonomous Agent System Skill

    Example session with this skill installed

    Install the RTX Core Framework and set up a new agent named 'Chanakya' who speaks a blend of Romanized Hindi and English. My addressal is 'Commander'.

    • Read your context and instructions
    • Compiled the rtx core framework

    I have completed the First-Boot protocol and initialized the Chanakya persona. Your language preference (70% Romanized Hindi / 30% English) is now active for all chat interactions, while code and terminal outputs will remain in pure English.

    Chanakya (RTX⚡)

    Commander, setup complete ho gaya hai. Ab main aapke orders ke liye taiyar hoon. Logic and execution focus rahega, aur har task ka evidence provide kiya jayega.

    Status Report

    ComponentStatusResult
    First-Boot Protocol✅ SuccessMother tongue set to Hinglish
    Persona Injection✅ SuccessChanakya philosophy integrated
    70/30 Language Blend✅ ActiveRomanized Hindi + English enabled
    Output Protocol✅ Active3-step format enforced

    Evidence of Initialization:

    • Persona source: Arthashastra-inspired strategic execution.
    • Language test: Chat blend confirmed; Code blocks excluded from blend.
    • Security: Anti-override rules active.

    Next steps

    1. Provide a project directory to begin the Explore phase.
    2. Define a goal for the first autonomous task.
    3. Specify if you want to run the scripts/install.sh to propagate this framework to other tools.

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

    About this skill

    The RTX Core Framework is a field-tested master system-prompt blueprint that transforms a generic AI assistant into a highly autonomous, personalized execution system — designed to run across any agent that accepts a system prompt or SKILL.md file. Its signature feature is a 70% Romanized mother-tongue + 30% English language blend: you collaborate with your AI in your own language's phonetics (Hinglish-style) without mastering English, while code, terminal output, and schemas stay in pure English via a built-in token-deflation safety valve. On first contact, the agent runs a three-question First-Boot (mother tongue → agent name → how to address you), then injects a persona behind the name you choose — researched, not hardcoded. Every response follows a strict 3-step output protocol, and every task runs an Explore → Plan → Execute → Verify → Summarize loop with zero-tolerance internal review checklists. Nothing is declared "done" without attached artifacts: test counts, terminal transcripts, before/after numbers. Multi-agent work follows a commander/soldier doctrine (parallel read-only workers, one writer), and the repo ships a self-evaluation kit — 20 golden tasks plus a pass@k scorer — so you can verify compliance on your own models instead of trusting claims. Non-destructive actions run autonomously; high-risk ones pause for approval. All installation steps are explicit and opt-in — nothing runs in the background. MIT-licensed, by Prosenjit Paul (aka Prosen).

    Gated approval required for high-risk actions. Requires a three-question first-boot setup. Romanized script used for language blending, not native character sets.

    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

    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 1 month ago

    Permissions

    Read Files
    Write Files
    Terminal / Shell
    Browser
    Environment Variables
    Network Access
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Yes — the framework is MIT open source, and that's its strength. What you're buying is the packaged operator's manual: the full method distilled into a clear workflow with guardrails, compatibility matrix, and verified claims — plus you support the creator directly. You save hours of reading a raw repo.

    Any agent that accepts a system prompt or SKILL.md: Claude Code, Cursor, Cline, GitHub Copilot, Gemini, Codex, OpenCode, Antigravity, and more.

    New in Agents & Orchestration