More screenshots
Works with the AI Agents you already use
Agent Memory Retention & Deletion Preflight Pack
Preflight local AI-agent memory metadata for purpose, consent, retention and deletion-reference conflicts without connecting to or changing a memory store.
$5
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
| Request | Memory | Decision | Reason |
|---|---|---|---|
| D1 | M1 | HOLD_FOR_REFERENCE_REVIEW | Active 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
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:
- result.json
- memory-disposition.csv
- deletion-request-matrix.csv
- reference-conflicts.csv
- issues.jsonl
- MEMORY_PREFLIGHT.md
- 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.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
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
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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
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
- Software
Python