More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Claude Auto Dream - Setup & Health Check

    1

    Set up and troubleshoot Claude Auto Dream in Claude Code: check provider configuration, trace skipped hooks, and verify actual memory changes.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Claude Auto Dream - Setup & Health Check

    Claude Auto Dream - Setup & Health Check

    Example session with this skill installed

    Inspect the installed Claude Auto Dream version and run an isolated synthetic test of its memory-write tool cycle. Explain what proves a useful update and which checks still require a real provider or automatic hook execution.

    • Read your context and instructions
    • Compiled the claude auto dream

    Controlled diagnostic example

    This records an actual local inspection and synthetic validation of runtime v1.1.1. The fixture uses a local mock endpoint; it is not a customer benchmark or a live-provider success claim.

    Installation observed

    Claude Code 2.1.296 reported Claude Auto Dream 1.1.1 installed and enabled. The active plugin path was under a router profile rather than the default cache root, so the inspection used the registered installation path.

    Memory-write tool cycle

    In an isolated temporary directory, a two-request tool cycle wrote one synthetic topic memory and the MEMORY.md index. Tool results were returned to the mock model, the runtime finished, the lock was released, and the completion timestamp was written. The fixture loaded synthetic configuration and did not use personal credentials, conversation history, or real project memories.

    Completion is not the same as a useful update

    A separate one-request no-op scenario also wrote a completion timestamp while creating no memory files. Therefore, a log saying completed or an updated timestamp is not enough: compare actual memory artifacts before and after the run.

    Verification boundary

    The local fixture verifies tool plumbing and observable file changes. It does not verify real model-provider authentication, model compatibility, automatic Stop/SessionEnd registration, or the quality of memories from real conversations.

    Next checks for a real installation

    Verify one bounded synthetic tool-call cycle against the user's chosen working provider. Then confirm separate Stop and SessionEnd events in an isolated Claude Code project, inspect the actual target memory directory, and compare the resulting files. Report installation, mock results, provider results, and hook-driven changes separately.

    tool cycle wrote one synthetic topic memory and the MEMORY.md

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

    About this skill

    Claude Auto Dream adds incremental memory extraction and session-end consolidation to Claude Code through a separate open-source plugin. This companion skill helps your agent install it correctly, choose sensible settings, and work out why a memory did or did not appear.

    The runtime plugin is freely available under MIT at https://github.com/MeCKodo/claude-auto-dream. You are paying for the setup and diagnostic workflow, not exclusive access to that code.

    What you get

    • Guided installation with checks for the active plugin version and enabled hooks.
    • Provider configuration review without dumping your API key or environment.
    • Independent tuning of per-turn extraction and session-end consolidation.
    • Diagnosis of missing configuration, wrong project paths, cursor state, locks, skip conditions, and provider errors.
    • Verification that distinguishes a local check, a mock run, a real provider call, and an actual hook-driven memory update.

    How it works

    Ask your agent to set up the plugin or explain a failure. The skill starts from the actual local installation and configuration, makes a focused change when authorized, and reports what the evidence proves. It uses isolated synthetic checks before touching real project memories where possible.

    Requirements

    • Claude Code as the target runtime, with plugin support.
    • macOS or Linux, Bash, and a supported Node.js version.
    • An agent with terminal and local filesystem access; a browser-only chat cannot perform installation.
    • A separately configured LLM provider and a tool-capable model. API usage is billed by that provider.

    Scope and limitations

    The automatic hooks require Claude Code. This listing does not add automatic memory to Cursor, Copilot, or every agent advertised by the marketplace. Current guidance is based on upstream v1.1.1 at commit 9bfa94139ba9b3554c7bc191b3a3a9ae2150a035; the skill instructs the agent to inspect a different installed version before relying on version-specific behavior.

    Direct Anthropic compatibility in the reviewed runtime needs further verification. OpenAI-compatible providers also require a real tool-call test for the selected endpoint and model. Local mock verification does not prove a paid provider or current Claude Code hooks work end to end.

    The plugin can read local memories and transcripts and send relevant content to your chosen model provider during actual runs. Memory changes depend on the model and input. No perfect recall, fixed API cost, hosted service, or human support SLA is included.

    Requires Claude Code hooks on macOS or Linux. The free runtime is installed separately; model API access and usage charges are not included. Automatic hooks for Cursor or Copilot are not provided. Guidance was reviewed against runtime v1.1.1. Direct Anthropic compatibility needs further verification, and each OpenAI-compatible endpoint/model needs a real tool-call test. Published validation covers a controlled local mock; it does not establish real provider, automatic hook, or Agensi delivery compatibility. Memory quality and API costs depend on model and context. No hosted service, perfect recall, fixed-cost guarantee, or human support SLA is included.

    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

    Requires

    GitHub
    Claude Code
    macOS
    Linux
    Bash
    Node.js
    Claude Auto Dream runtime
    LLM provider with tool calling

    Permissions

    Read Files
    Write Files
    Network Access
    Terminal / Shell
    Environment Variables

    Allowed Hosts

    github.com

    File Scopes

    ~/.claude-auto-dream/config.json
    ~/.claude-auto-dream.json
    ~/.claude/projects/*/memory/**
    ~/.claude/projects/*/*.jsonl
    ~/.claude/plugins/cache/claude-auto-dream/**

    Uses shell and file access for installation, redacted configuration checks, logs, and isolated tests. Reads only relevant DREAM_* settings; no environment dump or credential export. Installation may contact github.com, raw.githubusercontent.com, or codeload.github.com. Actual model requests go only to the endpoint explicitly chosen and authorized by the user; that host is configurable. The runtime may send selected memory/transcript context and tool results to that provider. Real memory writes and configuration changes require task authorization. No email, payment, wallet, or financial-account access is needed. The paid companion is loaded through Agensi; the separate public MIT runtime is installed from upstream.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Yes. Claude Auto Dream is public and MIT-licensed at github.com/MeCKodo/claude-auto-dream. This product is a companion setup, tuning, diagnosis, and verification workflow.

    No. You configure your own provider and tool-capable model. The provider charges separately; this purchase does not include API credit or a hosted model service.

    No. The automatic runtime requires Claude Code plugin hooks on macOS or Linux. A separate companion agent can help manage that installation when it has terminal and local file access.

    No. Configure the key locally. The workflow avoids printing credentials in reports. Actual runtime requests send relevant context to the model endpoint you choose.

    No. Memory quality depends on the model and input. The workflow distinguishes actual file changes from completion logs and uses isolated tests and recovery options where appropriate.

    Through Agensi's agent connection under its current terms. The separate free runtime is installed from its public upstream repository or Claude Code plugin marketplace.

    New in Agents & Orchestration