Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Papercliped Agent Control

    1

    Manage your Paperclip AI agents from ChatGPT, Claude, Codex or another compatible AI app. Check status, assign work, follow runs, review approvals and understand costs using the Papercliped MCP connection.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Papercliped Agent Control

    Papercliped Agent Control

    Example session with this skill installed

    Sync with my Paperclip board, show me the current status of all agents, and tell me if there are any pending approvals.

    • Read your context and instructions
    • Compiled the papercliped agent control

    I have synchronized with your Paperclip instance. I retrieved the latest snapshots for your agent company and checked for any items requiring your attention.

    Agent Company Status Overview

    Agent NameStatusCurrent RunActive IssuesPending Approvals
    Architect-01WAKE#772 - System Design20
    Coder-AlphaWAKE#775 - Bugfix/Auth11
    Tester-MainPAUSEDNone00
    Doc-GenIDLENone30

    Pending Approvals

    Agent: Coder-Alpha
    Request: Deployment of patch to production-stable branch.
    Implication: This will trigger a CI/CD pipeline and potential site downtime for 30 seconds.
    Action Required: Provide approval to proceed or reject with feedback.

    Cost Summary (Current Period)

    • Total Compute: $12.45
    • Token Usage: 850k (Input) / 210k (Output)
    • Active Runs: 2

    Next steps

    1. Review the pending deployment approval for Coder-Alpha.
    2. Wake Doc-Gen to begin processing the documentation backlog.
    3. Assign a new issue to Coder-Alpha once the current bugfix is resolved.

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

    About this skill

    Managing a fleet of autonomous agents shouldn't require jumping between dashboards and CLI tools. This skill connects your AI development environment to a Paperclip instance, allowing you to monitor and control your agent-led company directly through chat.

    What it does

    • State management Inspect agent heartbeats, live execution runs, and current duty statuses.
    • Work delegation Create issues and assign specific tasks to agents using paperclip_create_issue.
    • Financial oversight Generate detailed cost reports and activity logs to monitor budget consumption.
    • Workflow control Pause, resume, or wake agents based on live needs or completion status.
    • Approval handling Review and process pending agent requests that require human-in-the-loop confirmation.

    How it works

    1. Discovery The skill syncs with your Papercliped MCP server to identify connected companies and agent registries.
    2. Snapshotting It retrieves the current state of all runs and active issues using paperclip_sync_snapshot.
    3. Execution You issue commands to modify agent states or assign new work items.
    4. Reporting The skill formats raw data into structured performance and cost reports for review.

    Frameworks & tools

    Built for the Paperclip agent framework via the Papercliped MCP connector (https://mcp.papercliped.co/mcp). It requires a configured Paperclip instance and an AI application supporting Model Context Protocol.

    Why this beats prompting it yourself

    Writing manual prompts to interface with the Paperclip API often leads to state mismatches or improper tool sequencing. This skill handles the cursor management for incremental syncs, follows specific safety protocols for state-changing operations, and ensures human-in-the-loop approvals are never bypassed.

    Use cases

    • Check which agents are currently idling and assign them to backlogged GitHub issues.
    • Generate a weekly cost report to see which agent workflows are consuming the most API budget.
    • Intervene in a stuck execution run by pausing the agent and reviewing its pending approvals.

    Known limitations

    Requires an active Papercliped MCP server connection. State-changing operations like pausing or waking agents require specific OAuth authorization levels and cannot be bypassed.

    Requires a configured Papercliped MCP server. State-changing actions (pause/wake) require specific OAuth permissions. Does not host agents; requires an existing Paperclip instance.

    Open docs

    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 4 days ago

    Permissions

    Network Access
    Listed4 days ago

    What's inside

    Frequently Asked Questions

    This skill provides a centralized Model Context Protocol (MCP) bridge to manage Paperclip AI agents, allowing you to monitor heartbeats, delegate tasks via GitHub, and track API budgets directly within your AI-enabled workspace.

    This skill is specifically designed for agents built on the Paperclip framework and requires an active connection to a Papercliped MCP server at https://mcp.papercliped.co/mcp.

    Yes, the skill is built with human-in-the-loop safety protocols, allowing you to review, approve, or deny pending agent requests before they execute sensitive operations.

    Setup involves connecting the skill to your Papercliped MCP server and ensuring your AI application supports Model Context Protocol, followed by a quick snapshot sync to identify your agent registry.

    The skill includes automated cost reporting tools that aggregate API consumption and activity logs, helping you identify which workflows are most resource-intensive.

    New in Workflow Automation