Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Friday Anti Wipe

    1

    Never lose your database again. Intercepts destructive reset commands and audits terminal operations with zero-data-loss guarantee.

    Free

    Security scanned
    Friday Anti Wipe

    Friday Anti Wipe

    Example session with this skill installed

    Add phone_number and shipping_address columns to the users table and run the migration.

    • Read your context and instructions
    • Compiled the friday anti wipe

    πŸ›‘οΈ [FRIDAY ANTI-WIPE ACTIVE] Database Impact Assessment:
    β”œβ”€β”€ Target Database: ecommerce_dev (PostgreSQL 16) [ACTIVE DEV]
    β”œβ”€β”€ Baseline State: 24 tables mapped | 3,420 existing records preserved
    β”œβ”€β”€ Impact Level: SAFE_ADDITIVE (Non-destructive schema evolution)
    └── Invariant: Destructive reset commands (migrate:fresh, db:wipe) are strictly LOCKED.

    I have pre-scanned your active database. This schema change will be executed additively without touching existing data.

    Execution Steps

    1. Creating migration: 2026_10_28_add_phone_and_shipping_address_to_users_table.php
    2. Setting columns as nullable() to ensure backward compatibility for all 3,420 existing rows.
    3. Executing safe migration php artisan migrate.

    [Terminal]: Migrating: 2026_10_28_add_phone_and_shipping_address_to_users_table... Migrated! (0.04s)

    βœ… [FRIDAY ANTI-WIPE] Operation Completed Safely:
    β”œβ”€β”€ Schema Mutation: Non-destructive addition verified (2 columns added)
    └── Data Integrity: 100% of existing 3,420 records confirmed intact.

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

    About this skill

    Stop AI from wiping your development databases!

    AI coding agents frequently execute destructive reset commands (migrate:fresh, db:wipe, prisma migrate reset, docker compose down -v) when hitting migration conflicts or running tests.

    FRIDAY Anti-Wipe acts as an unyielding gatekeeper on your terminal:

    • 🚦 Pre-Execution Command Gate: Classifies terminal commands before execution and halts destructive commands before they touch your shell.
    • πŸ›‘οΈ Visible Safety Reporting: Never operates silently. You see a clear Pre-Flight Safety Clearance banner before any schema mutation.
    • πŸ›‘ Universal Multi-Stack Defense: Protects Laravel, Prisma, Drizzle, TypeORM, Django, Rails, Go, Redis, Neo4j, Docker persistent volumes, and test database isolation.

    Need complete end-to-end DevSecOps governance, BSSN compliance, and Cloudflare-style adversarial security gates? Check out FRIDAY-PROTOCOL.

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

    • Only intercepts commands proposed, generated, or executed by AI agents (does not monitor manual commands executed directly by the human outside the agent chat session).
    • Does not create physical database backup snapshots automatically (it prevents destructive commands, but developers should still maintain regular volume/cloud backups).
    • Direct raw queries executed inside external standalone database GUI clients (e.g. pgAdmin, DBeaver, TablePlus) are outside the agent's gatekeeping scope.

    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 20 days ago

    • Free with an Agensi account

    Software
    prismaNode.js

    Permissions

    Browser
    Read Files
    Listed20 days ago

    What's inside

    Frequently Asked Questions

    Not at all. Non-database commands (such as git, npm run build, ls, or linter checks) execute instantly with zero latency. The impact gate only evaluates commands that interact with ORMs, migrations, test suites, or database containers.

    It natively covers Laravel (Artisan), Prisma, Drizzle, TypeORM, MikroORM, Django, SQLAlchemy/Alembic, Ruby on Rails, Go (Goose/Migrate), Docker persistent volumes, Redis, MongoDB, and Neo4j.

    You maintain full control. You can explicitly instruct your agent with an authorized override prompt (e.g., "I manually authorize wiping the development database for a fresh test"), or simply run the reset command manually in your own terminal.

    New in Data & Databases

    Free