Agent Ship Gate — Launch Gate for Coding Agents
35 evidence-backed launch checks (Security, Stripe, Auth, SEO/AEO, Ops). Your agent returns GO/NO-GO before you charge or go public.
$12
Works with the AI Agents you already use
Agent Ship Gate — Launch Gate for Coding Agents
Example session with this skill installed
Run ship-gate on my Next.js app. I'm planning to launch on Product Hunt in two hours and need to make sure Stripe and Supabase RLS are safe.
- Read your context and instructions
- Compiled the agent ship gate
- Generated the document
I have completed the 35-point launch gate audit for your project. I identified two critical security failures regarding RLS policies and Stripe webhook verification that currently block deployment.
SHIP-GATE-REPORT.md
| ID | Category | Verdict | Evidence | Recommended Fix |
|---|---|---|---|---|
| AG-SEC-01 | Security | PASS | .env.example contains no real keys; .gitignore includes .env | None |
| AG-SEC-03 | Security | FAIL | supabase/migrations/..._initial.sql: public.profiles has RLS enabled but no policies, defaulting to public read. | Add USING (auth.uid() = id) policy. |
| AG-AUTH-01 | Auth | PASS | middleware.ts:14 correctly redirects unauthenticated users to /login. | None |
| AG-PAY-03 | Billing | FAIL | app/api/webhook/route.ts:22 processes req.json() without stripe.webhooks.constructEvent. | Implement signature verification using the STRIPE_WEBHOOK_SECRET. |
| AG-OPS-05 | Ops | WARN | app/terms/page.tsx is a placeholder with "Lorem Ipsum". | Replace with actual Terms of Service before charging. |
| AG-SEO-01 | SEO | PASS | layout.tsx includes Metadata API with title and description templates. | None |
Verdict
NO-GO · DON'T LAUNCH · see SHIP-GATE-REPORT.md
Blocking FAIL IDs: AG-SEC-03, AG-PAY-03
Next steps
- Fix the RLS policy in your Supabase migration file to prevent unauthorized data access.
- Update your Stripe webhook route to use official signature verification.
- Once fixed, ask me to "re-run checks AG-SEC-03 and AG-PAY-03" to clear the NO-GO status.
page.tsx
PDF · document
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
Stop shipping on “the AI said it’s fine.” Install this skill, say “Run Agent Ship Gate,” get a report with stable IDs (AG-PAY-02 …), file:line evidence, and a fix for every failure. Blocking fails in Security, Billing, or Auth = don’t launch.
Real sample report (not a synthetic demo table): full NO-GO run on vercel/nextjs-subscription-payments — https://agent-ship-gate.shengxiaodai0528.workers.dev/ship-gate-sample
vs free “Code Reviewer” skills: those do open-ended review. This pack is a fixed 35-check launch gate with stable IDs, required file:line evidence, and an explicit GO / NO-GO. Same agent, different job: launch risk before you charge cards — not general PR comments.
Built for Cursor, Claude Code, Lovable, Bolt, v0-style stacks. Read-only by default. Not a pentest or compliance cert.
Read-only access limits checks to local code and public endpoints. Cannot verify private production dashboard settings or live DNS configurations.
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 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 16 days ago
Requires