Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Agent Memory Privacy Check

    2

    Audit AI agent memory files for privacy risk and bloat.

    Free

    17 usesSecurity scanned

    Agent Memory Privacy Check

    Example session with this skill installed

    Analyze my MEMORY.md and USER.md files for privacy risks and bloat. They contain my project logs and personal settings, including a developer key I might have left in there.

    • Read your context and instructions
    • Compiled the agent memory privacy

    Status: CONCERN

    Must Remove

    • API key found in line 14 (sk-proj-...)
    • User's home address in USER.md

    Compress

    • Project 'Alpha' logs from 2023 (800 chars)
      Suggested Replacement for MEMORY.md:
      "User prefers Python 3.11 for ML tasks. Currently migrating Project Alpha to FastAPI."
    User's home address in USER.md

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

    About this skill

    A quick privacy check for agent memory

    Agent Memory Privacy Check audits durable AI memory files such as SOUL.md, MEMORY.md, USER.md, AGENT.md, USER_PROFILE.md, WORKING_MEMORY.md, HANDOFF.md, and OBSERVATIONS.md.

    What it finds

    It flags secrets, stale assumptions, unsupported personal claims, raw transcript hoarding, sensitive personal data, and memory bloat that can make an agent less useful or less safe.

    Hermes-aware

    For Hermes-style memory, it checks the known hot-memory budgets: MEMORY.md at 2,200 characters and USER.md at 1,375 characters.

    Trust builder

    This free skill is a lightweight audit. It helps users see the value of clean memory before moving to a deeper continuity-curation workflow.

    • Scan is pattern-based; may miss obfuscated secrets.
    • Does not automatically rewrite files; provides suggestions only.
    • Limited to files under 100k characters for optimal performance.

    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

    17 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 5 months ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed5 months ago

    What's inside

    Frequently Asked Questions

    This skill scans durable memory files (like SOUL.md or USER.md) to detect sensitive data leaks, stale assumptions, and bloated character counts that can degrade agent performance.

    The skill is specifically optimized for agents using Markdown-based memory systems, including those following Hermes-style memory budgets and standard files like AGENT.md or WORKING_MEMORY.md.

    Yes, it specifically monitors MEMORY.md and USER.md against their respective 2,200 and 1,375 character limits to ensure your agent stays within optimal 'hot-memory' budgets.

    This skill acts as a diagnostic auditor; it will flag secrets, raw transcript hoarding, and unsupported personal claims so you can manually curate or automate your memory cleanup.

    You receive the full diagnostic skill capable of auditing eight specific memory file types, ensuring your agentic workflows remain secure, lean, and trustworthy.

    Updates are handled through the marketplace platform, ensuring the privacy check remains current with evolving memory management standards and new common file naming conventions.

    New in Agents & Orchestration