More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Product Loop

    1

    An autonomous development loop that iterates on products until they meet measurable, sellable quality bars.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Product Loop

    Product Loop

    Example session with this skill installed

    Run the product loop on this repo. Use the current config to fill two build slots and one design-ahead slot. Exit when the wave is recorded.

    • Read your context and instructions
    • Compiled the product loop

    Wave started. I have verified the loop state and initiated three concurrent tasks.

    Wave Summary: Session 882af1

    Item IDStatusTrackResult
    I-102buildingproductLane 1 (API) and Lane 2 (UI) started in separate worktrees.
    I-103breakingmeasurementLevel 0 smoke tests passed; Breaker role currently analyzing diff.
    I-104speccedinfraDesign-ahead spec written; passed Spec-critic review for next wave.

    Cycle Details

    • Log Entry: 2023-10-27 02:00:01 Z 882af1 wave: I-102(build) I-103(break) I-104(design-ahead)
    • State: docs/loop/.lock active.
    • Repair: preflight.py restored missing items/I-103/spec.md from git.

    Next steps

    • Monitor docs/loop/needs-human.md for any new ACTION items.
    • Review the scoreboard.jsonl for bar movements once scoring completes.
    • Check log.md for final wave timings and merge results.

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

    About this skill

    Stop shipping features that nobody wants to pay for. This skill implements an autonomous build loop that iterates on your product until it meets concrete, measurable "sellable" bars. It replaces vague development goals with a rigorous cycle of planning, building, and adversarial testing that runs unattended, even while you sleep.

    What it does

    • Autonomous build waves runs parallel development lanes in separate worktrees to advance multiple features simultaneously.
    • Measurable "done" bars defines success through scripted checks and model-based evaluations rather than subjective feelings.
    • Adversarial role separation assigns different models to plan, build, break, and score code to prevent self-grading bias.
    • Automated state repair uses preflight scripts to detect missing documentation or broken configurations and self-heals the loop state.
    • Contract-driven integration establishes strict interfaces between codebase areas so parallel builders don't collide.

    How it works

    1. Setup mode conducts an interview to define the buyer, the "sellable" bars, and the rules for unattended decision-making.
    2. Readiness gate runs live checks on builds, tests, and concurrency limits to ensure the loop can run without human intervention.
    3. Cycle mode executes waves of work, including design-ahead planning, parallel building, and multi-stage breaking/scoring.

    Frameworks & tools

    The skill requires a project structure with a docs/loop/ directory and utilizes Python-based utility scripts (preflight.py, check_lanes.py, loop_status.py). It is designed to run in headless environments like Claude Code, cron jobs, or CI runners.

    Why this beats prompting it yourself

    Standard prompting leads to agents that grade their own work and stall when they hit a minor ambiguity. This skill enforces a multi-role architecture and a "never wait" policy, ensuring the agent makes progress according to preset rules instead of idling for feedback.

    Use cases

    • Running nightly iteration cycles that improve a product's "sellable" metrics overnight.
    • Moving a prototype toward a stable alpha version through continuous automated smoke testing.
    • Benchmarking product usefulness using simulated buyer panels and new-customer personas.

    Known limitations

    Requires initial manual setup to define bars and human-only boundaries. Does not support real-world customer interaction, production deployments, or spending money without external triggers.

    Requires Python for preflight scripts. Cannot perform real production deploys or external spending. Initial setup of "sellable" bars requires manual human input.

    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 13 days ago

    Requires

    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed13 days ago

    What's inside

    Frequently Asked Questions

    Traditional agents often "self-grade," claiming a task is done when it merely compiles. This skill uses adversarial role separation, where different models are assigned to build, break, and score the work against objective "sellable" metrics you define during setup.

    The skill includes a suite of Python utility scripts (like preflight.py and check_lanes.py) and a structured directory template. You will need a development environment capable of running Python and a project structure that supports concurrent worktrees.

    Yes, the skill is designed for headless operation in environments like Claude Code, CI/CD runners, or cron jobs. Its "readiness gate" ensures the loop can handle decision-making and state repair without human intervention once the initial bars are set.

    The skill works best with projects that can be validated via scripted checks or model-based evaluations. It requires a `docs/loop/` directory within your repository to manage state and instructions, making it compatible with most modern, version-controlled codebases.

    While the loop is highly autonomous, it cannot interact with real-world customers, execute production deployments, or authorize financial transactions. It is strictly a development and iteration engine designed to bring prototypes to a sellable state within a sandbox or staging environment.

    New in Agents & Orchestration