Yappr for Coding Agents

    1

    Get coding progress on a paired device and answer your agent’s questions from your phone or browser. The skill shows the agent how to check Yappr, post updates, and read your decisions.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Yappr for Coding Agents

    Example session with this skill installed

    Run the build checks and send me a Yappr update when they finish. If browser setup times out, ask whether to run the checks again or wait.

    • Read your context and instructions
    • Compiled the yappr for coding

    On the paired device

    If the checks pass, the agent posts Build checks passed. The body names the check that ran and what comes next.

    If browser setup times out, the agent sends

    Run the checks again? with the detail “The first run timed out during browser setup.” The options are

    Run again and

    Wait. The agent also offers these choices in the current chat.

    What the agent gets back

    Select

    Run again on the paired device. yappr wait prints retry and exits successfully. The agent can then run the checks again. If the question expires, the agent reports that it is waiting for a decision and leaves the retry on hold. If you answer in chat, the agent cancels the pending Yappr question before acting.

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

    About this skill

    Use Yappr to follow coding work while you are away from your terminal. Ask your agent to post when checks finish, work is blocked, or the task is done. If the agent needs a decision, it can send a question with choices or an approval request. You can answer in Yappr or in the current chat.

    The skill uses the Yappr CLI on the machine where your agent runs. Pair a browser or phone before you use it. Keep the receiving app open for live updates and questions. The skill also explains how to check for existing hooks if you already use Yappr for tool permission prompts.

    Keep the paired receiver open and connected for live delivery. An expired question requires a new request. Whether an answer can wake the agent depends on how the agent handles background tasks.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 6 days ago

    • Free with an Agensi account

    Requires

    Yappr
    Yappr CLI 0.1.7 or later
    A paired Yappr receiver
    An agent with shell access

    Permissions

    Terminal / Shell
    Network Access

    Allowed Hosts

    yappr.run

    The agent uses a shell to run the Yappr CLI. The CLI reads the configured feed and peer list, saves posts and questions locally, and connects to paired devices to deliver them and receive decisions. Tool permission hooks require separate setup.

    Listed6 days ago

    What's inside

    Frequently Asked Questions

    The agent can post progress and blockers, ask a question with choices, or request approval for a decision. Tool permission prompts use separately configured Yappr hooks.

    Install Yappr 0.1.7 or later on the machine where your agent runs. Pair a receiver, such as the browser app at https://yappr.run/. Your agent needs permission to run shell commands.

    Yes. Keep Yappr open on your paired device to receive and answer questions. You can also answer the same question in the current chat.

    New in Agents & Orchestration