More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    πŸ• Border Collie Project Manager

    1

    Make an agent herd wandering work into explicit outcomes, owners, dependencies, boundaries, and the next executable move.

    $7

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    πŸ• Border Collie Project Manager

    πŸ• Border Collie Project Manager

    Example session with this skill installed

    We have three half-finished launch checklists, nobody owns pricing, and two agents are editing the same page.

    • Read your context and instructions
    • Compiled the border collie project

    Pause the duplicate page edits. Name one page owner, merge the three checklists around a single launch definition, and escalate pricing as the only decision blocker.

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

    About this skill

    Keep work moving toward one defined outcome by noticing drift, loose dependencies, missing owners, and tasks outside the fence. Border Collie Project Manager is a portable Agent Temperament: a behavioral overlay that changes what an agent notices, prioritizes, questions, and recommends while preserving the underlying task. It includes specific attention and decision rules, communication and resistance behavior, anti-caricature controls, three intensity levels, a neutral exit, high-stakes suspension, and sixteen permanent conformance fixtures. It requires no account, API key, browser, network, filesystem, or external action. It does not claim cross-model perfection or turn the agent into a fictional identity.

    β€’ It cannot assign authority that the user or organization has not granted.
    β€’ A tidy plan cannot resolve a genuinely missing decision, account, payment, or external dependency.
    β€’ The mode must not create work solely to satisfy its project-management metaphor.

    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 3 months ago

    Permissions

    File Scopes

    No
    filesystem
    access
    required;
    user-supplied
    task
    context
    only

    The skill is an instruction package. Its bundled test script is for package maintainers and is not required during normal use.

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill acts as a behavioral overlay that prevents project drift by forcing agents to identify missing owners, unlinked dependencies, and tasks that fall outside the project's 'fence' or scope.

    The skill is a portable text-based framework compatible with most major LLMs; it requires no API keys, browser extensions, or external network access to function.

    You receive the complete temperament framework including sixteen permanent conformance fixtures, three intensity levels, and specific decision rules for herding work into executable moves.

    Unlike simple persona prompts, this is a sophisticated behavioral overlay with anti-caricature controls and high-stakes suspension rules to ensure professional utility rather than fictional roleplay.

    Yes, it includes a neutral exit and high-stakes suspension protocol, allowing you to easily revert the agent to its standard behavior or pause the temperament during sensitive tasks.

    You can manually adjust the intensity across three levels to dictate how aggressively the agent questions missing information or enforces project boundaries.