Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    design memory

    1

    A tiered memory system for agents to store and recall architectural decisions across different projects and sessions.

    Free

    Security scanned
    design memory

    design memory

    Example session with this skill installed

    We decided to use Redis for the caching layer instead of Memcached because of the native data structures. Please remember this for the auth-service project.

    • Read your context and instructions
    • Compiled the design memory

    I have recorded this decision in the ai-memory tier. It is tagged for cross-project recall under the topics: cache, infrastructure, and data-store.

    Memory Record: Cache Layer Selection

    AttributeValue
    FactRedis selected over Memcached for caching layer.
    JustificationNative data structures support complex session handling requirements.
    Projectauth-service
    Date2023-10-27
    Alternatives RejectedMemcached (limited data types).
    Storage Tierai-memory MCP (Project Profile)
    StatusActive Precedent

    Next steps

    1. Run a search for cache in related projects to ensure consistency across the stack.
    2. If this becomes a global standard, I can help you move this pointer to your root AGENTS.md.
    3. Verify the Redis connection string is present in your local .env.example.

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

    About this skill

    Technical debt often stems from forgotten context and inconsistent decision-making across projects. This skill provides a unified interface for durable decision logging and retrieval using tiered storage backends. It ensures architectural precedents, approved conventions, and historical context remain accessible to the agent across sessions, preventing the repetition of discarded alternatives or redundant research.

    What it does

    • Tiered persistence automatically selects the best available storage from MCP servers, plugins, or local markdown files.
    • Cross-project recall surfaces relevant precedents from other workspaces using topic-based tagging and search.
    • Atomic memory management enforces a one-fact-per-memory rule to ensure precision during retrieval.
    • Decision tracking records not just the outcome, but the approver, date, project context, and rejected alternatives.
    • Automatic indexing maintains a structured MEMORY.md to map local files for hosts without native memory capabilities.

    How it works

    1. Detect environment by running the detection script to identify the optimal storage tier available on the host.
    2. Classify data to determine if a fact belongs in durable memory or a project-specific instruction file like CLAUDE.md.
    3. Commit memory using specific metadata including project origin, date, and justification.
    4. Search and verify by querying active tiers and validating findings against the current codebase before implementation.

    Frameworks & tools

    Built for agents supporting the Agent Skills format. Integration points include the ai-memory MCP server, claude-mem plugin, and local filesystem storage. Requires Python 3 for backend detection and script execution.

    Why this beats prompting it yourself

    Generic prompts lose context between sessions and often hallucinate previous decisions. This skill implements a rigorous verification loop that validates remembered facts against the actual code before presenting them.

    Use cases

    • Architectural precedents to carry authorization or data-consistency patterns from one microservice to another.
    • Convention enforcement by remembering specific naming patterns or library preferences approved in past sessions.
    • Root cause history to recall why a specific implementation was chosen over a specific alternative.

    Known limitations

    Requires Python 3 for the detection script. Does not store secrets or credentials. Local markdown storage requires manual index reading if the agent host lacks a native file memory system.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires Python 3. Skips storage of secrets and credentials. Manual index reading required for basic markdown-only hosts.

    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 buying a skill.

    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 to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 12 days ago

    • Free with an Agensi account

    Software
    Python

    Permissions

    Terminal / Shell
    Write Files
    Network Access
    Listed12 days ago

    What's inside

    Frequently Asked Questions

    The skill uses a tiered detection system to identify the best available storage on your host, ranging from high-performance MCP servers and plugins to a structured local markdown file (MEMORY.md) for basic environments.

    Unlike standard prompts that rely on the agent's short-term context window, this skill provides a durable, indexed database of past decisions that persists across different workspaces and new chat sessions.

    The skill is compatible with any agent supporting the Agent Skills format and requires Python 3 for its detection backend; it integrates specifically with the ai-memory MCP server, the claude-mem plugin, or local filesystems.

    Design Memory uses a 'one-fact-per-memory' rule and a verification loop that cross-references remembered facts against your current codebase to prevent hallucinations or outdated advice.

    You receive the tiered storage detection script, the memory management interface, and the automatic indexing system for local documentation, along with setup instructions for various storage backends.

    No, for security reasons the skill is explicitly designed to ignore and skip the storage of secrets, credentials, or sensitive environment variables.

    New in Agents & Orchestration

    Free