- Home
- Skills
- Agents & Orchestration
- Invitation Lifecycle Contract Repair
More screenshots
Works with the AI Agents you already use
Invitation Lifecycle Contract Repair
Repair invitation lifecycle drift across tenant scope, tokens, roles, expiry, resend, revoke, acceptance, account linking, and retries.
$1
Invitation Lifecycle Contract Repair
Example session with this skill installed
Tokens are plaintext and resend keeps old links valid. Recipient check is missing at acceptance. Repair locally in our Node/Prisma repo without touching production.
- Read your context and instructions
- Compiled the invitation lifecycle contract
I have identified token storage risks and a recipient-binding gap. I will now generate a patch to hash tokens, implement versioned supersession for resends, and add a transactional check to verify the authenticated user matches the invited email before committing the membership.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Invitation logic often drifts across tenants, roles, and authentication paths, leading to leaked access or duplicate memberships. Security risks arise when tokens are stored in plaintext, resend actions fail to invalidate old links, or inviter authority is never revalidated at the moment of acceptance.
What it does
- Identifies cross-tenant invitation risks and guessable token vulnerabilities.
- Fixes broken lifecycles where resending or revoking leaves legacy links active.
- Repairs transactional gaps that mark invitations as accepted before membership is successfully committed.
- Centralizes role-ceiling and domain-restriction logic across registration and login flows.
- Implements idempotent dispatch commands to prevent duplicate emails and audit events during retries.
Frameworks & tools
Works with repository-local materials including Prisma, TypeORM, SQLAlchemy, Django ORM, Redis, Celery, BullMQ, Auth0, Clerk, and standard email adapters.
Why this beats prompting it yourself
General prompts often miss edge cases like revoke-accept races or seat-limit revalidation during concurrent requests. This skill uses a structured contract register to ensure every state transition, from dispatch to audit, is transactionally sound and tenant-safe.
Use cases
- Preventing a user from accepting an invitation into the wrong organization or workspace.
- Rotating and versioning tokens so that resending an invite supersedes all previous links.
- Ensuring inviter authority is checked at acceptance, not just at initial creation.
- Reconciling duplicate membership attempts when users accept invitations via multiple tabs or retries.
Known limitations
Does not access production databases, send live emails, or perform production migrations. Policy decisions regarding role hierarchy or guest access require human approval.
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.
No access to production DBs, identity providers, or live email. Cannot run migrations or deploy. Policy decisions like role delegation require developer confirmation.
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 3 months ago
Permissions
Permissions are limited to the active local workspace. They are used to inspect user-supplied or local project files; create or modify bounded local fixes, tests, documentation, or review artifacts; run repository-supported local tests, checks, builds, or parsing commands. The skill package does not require bundled credentials, unrestricted external network access, or automatic production changes.