More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Agent Memory Retention & Deletion Preflight Pack

    1

    Preflight local AI-agent memory metadata for purpose, consent, retention and deletion-reference conflicts without connecting to or changing a memory store.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Agent Memory Retention & Deletion Preflight Pack

    Agent Memory Retention & Deletion Preflight Pack

    Example session with this skill installed

    Deletion request D1 targets subject S1 in tenant T1. Memory M1 belongs to S1/T1, and active reference R1 still points to M1. Preflight the supplied metadata and write a local evidence packet without changing the memory store.

    • Read your context and instructions
    • Compiled the agent memory retention
    • Generated the data export

    Agent Memory Preflight

    Status: BLOCK

    RequestMemoryDecisionReason
    D1M1HOLD_FOR_REFERENCE_REVIEWActive reference R1 remains

    Files created

    The local run writes result.json, memory-disposition.csv, deletion-request-matrix.csv, reference-conflicts.csv, issues.jsonl, MEMORY_PREFLIGHT.md and evidence-receipt.json. The receipt binds every supplied input and generated output with SHA-256.

    Owner action

    Resolve or explicitly preserve the active reference under the supplied policy before an authorized operator performs deletion. This package did not inspect memory content, connect to a store, retrieve or delete anything, mutate records, unlearn a model, verify identity or provide proof of erasure.

    memory-disposition.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    This downloadable local package turns authorized buyer-supplied files into a fixed, reproducible review packet. It includes an installable Python CLI, a local stdio MCP adapter and a companion Agent Skill. One run creates:

    1. result.json
    2. memory-disposition.csv
    3. deletion-request-matrix.csv
    4. reference-conflicts.csv
    5. issues.jsonl
    6. MEMORY_PREFLIGHT.md
    7. evidence-receipt.json

    The deterministic core preflights memory metadata for purpose, consent, retention windows, deletion requests and active-reference conflicts. It rejects unsafe paths and malformed inputs, never overwrites an existing packet, escapes formula-active CSV cells and binds every input and output with SHA-256. Processing stays local. No API key, login, upload, telemetry or live external action is included.

    Best for agent platform builders and privacy operators preparing retention reviews or deletion workflows; teams needing reviewable evidence before risky actions; and agencies preparing reproducible client handoffs. Requires Windows 11, Python 3.11–3.14 and authorized local evidence files. Optional mcp==2.2.0 enables the local adapter.

    Limitations: no memory content inspection, legal decision, identity verification, store connection, retrieval, deletion, mutation, model unlearning or proof that data was erased. This is a one-time local V1.

    Requires local JSON evidence files. Cannot perform remote API calls or actual deletions. Does not infer missing identity or consent data.

    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 2 months ago

    Requires

    Python

    Permissions

    Network Access
    Listed2 months ago

    What's inside

    Frequently Asked Questions

    This skill performs a non-destructive audit of memory metadata to identify retention policy violations and consent conflicts. It solves the problem of 'orphaned data' by ensuring you only keep memory fragments that are legally and logically compliant before you trigger a final deletion command.

    It is designed to be agent-agnostic and works with any AI agent that can export memory metadata into local evidence files. As long as your agent stores memory with reference IDs or timestamps, this skill can analyze those structures for compliance.

    To maintain a strict security boundary, this skill does not have permission to modify databases or call external APIs. It analyzes local data and provides a 'preflight packet' that your existing systems use to execute the actual deletions safely.

    The purchase includes the core auditing logic, schema templates for local evidence files, and a guide on generating verifiable compliance receipts. You also receive documentation on integrating the output into automated LLM-ops workflows.

    Unlike a general prompt, this skill uses a deterministic, evidence-based approach that prevents the AI from 'hallucinating' consent. It strictly flags items where metadata is missing or expired, ensuring you meet GDPR/CCPA standards without relying on probabilistic LLM guesses.

    New in LLM Ops