Feature spec
Goal: Send a clear invoice after finishing a job.
- Add a client, line items, a due date, and payment instructions.
- Preview the total before exporting a PDF.
- Keep an editable draft if export fails.
Your AI coding agents are already running on your Mac
Free
Evidence scope: No current overall US chart position is available. Category-chart positions shown in discovery are a separate scope. Revenue is a directional model estimate, not verified earnings.
A product spec, screen plans, and build steps for your coding agent.
First kit free with a verified email
Combine features and design from your favorite apps.
Kit ready. Verify your email to download it.
Generating… usually about a minute.
What should your app do differently? Your note travels with the kit so your coding agent builds around your idea.
A product spec, phased build plan, differentiation notes, and screen references.
Illustrative example: an invoice app for independent contractors. Your kit is tailored to the app you choose; this is not its generated content.
Goal: Send a clear invoice after finishing a job.
Invoice editor: Client at the top, editable line items in the middle, total and preview action at the bottom.
States: Empty draft, validation errors beside each field, exporting, and a retry action that preserves the draft.
Hypothesis: Contractors need faster repeat invoices more than more templates.
First experiment: Test duplicating a previous job with five contractors. Watch where they hesitate before expanding the feature set.
The full kit adds a phased build plan, evidence notes, tool prompts, and implementation guidance. It is a plan for your coding agent, not a finished app.
Usage: Mechanics are fair game; never reuse the original name, branding, assets, or verbatim copy.
JavaScript is required to complete mailbox verification.
Good fit for mobile-first iOS and Android prototypes with managed app scaffolding.
Rork plan preview for Port22: Coding Agents Anywhere: map the core Developer Tools workflow, choose the smallest differentiated feature set, define the data and monetization boundaries, then prototype the riskiest user journey first.
Preview ready. Verify your email to reveal and copy the full prompt.
JavaScript is required to complete mailbox verification. Return to this prompt preview.
Affiliate link: CloneChart may earn a commission at no extra cost
These are generated suggestions, not verified review quotations. Check current App Store reviews and speak with users before treating a possible gap as a requirement.
Hypothesis 1
Assumption to check: Limited agent filtering options
Validate with people who use this workflow before building.
Hypothesis 2
Assumption to check: Lack of user feedback mechanisms
Validate with people who use this workflow before building.
Hypothesis 3
Assumption to check: No in-app messaging system
Validate with people who use this workflow before building.
Hypothesis 4
Assumption to check: Uncertain request statuses
Validate with people who use this workflow before building.
Original App Store material. Ratings and screenshots describe the existing app, not proof of demand for your version.
Your AI coding agents are already running on your Mac. Port22 doesn't launch, wrap, or replace them — it attaches to what's there and puts every session on your phone, including a permission prompt you can answer in a tap. Start Claude Code, Codex, or OpenCode in whatever terminal you like. Nothing about your setup changes. Port22 just gives you the whole fleet from anywhere. HOW IT WORKS 1. Install the free Port22 agent on your Mac — it's a menu-bar app, no configuration. 2. Pair your phone by typing a six-character code. No account, no sign-up. 3. Your sessions appear. Start them however you already do. MISSION CONTROL FOR YOUR FLEET See every session at a glance: which agent is working, which one is blocked on you, which one is done. No log tailing, no raw error strings — just states a human can read. WHEN AN AGENT IS BLOCKED Your phone tells you the moment an agent needs permission. Open Port22 and every option the agent actually offered is there as a real button — never a guessed keystroke, never an inferred choice. Answer it and the agent carries on. THE REAL CONVERSATION Read the full transcript exactly as it happened — prose, tool calls, diffs. Send a new prompt. Answer a multiple-choice question with real buttons instead of guessed keystrokes. Nothing is truncated. WORKS OFF YOUR NETWORK On your network it connects directly over your LAN. Off it, it fails over automatically to an encrypted relay, and you keep working from anywhere. Taurine, our keep-awake mode, stops your Mac napping mid-run so a long job survives the walk to the coffee shop. END-TO-END ENCRYPTED Your Mac and your iPhone verify each other's identity when they connect, then talk over an AES-256-GCM encrypted channel that the relay in between cannot read. There is no account and no sign-up — pairing is a code you type once. FREE FOREVER One Mac and two sessions, with every feature unlocked. Not a trial and not a crippled tier: off-network access, permission approvals, Taurine, and the full conversation are all included. The two sessions you're using stay free. PORT22 UNLIMITED Unlimited Macs and unlimited sessions, so you can drive the whole fleet at once. An annual subscription that renews automatically until cancelled. Pricing is shown in the app. REQUIRES THE MAC AGENT Port22 needs the free Port22 companion app running on your Mac. Download it at tryport22.com. Terms: tryport22.com/terms Privacy: tryport22.com/privacy
Written user reviews are not shown here. Check current App Store reviews >
Plan a focused first version with your coding agent. These are planning assumptions, not a delivery guarantee.
Choose one audience and one core workflow. Use the kit to agree on its screens, data, and acceptance criteria before building.
Decide which secondary features, integrations, and platform support can wait. Your version does not need to reproduce everything in the original.
Validate external services, specialist technology, data access, and ongoing costs for your chosen scope.
From the Build Kit assessment.
A reliable timeline needs an agreed scope and a technical check. Ask your agent to estimate the phases in BUILD_PLAN.md after that review.