Clonecode

Clonecode prices per page capture, not per seat: $9 buys 12 credits and $29 buys 40, so an agency's cost scales with how many client rebuilds it ships rather than how many designers log in. That structure makes it a project accelerator you can bill as a fixed add-on, not recurring MRR, which means the margin question is how many captures each engagement consumes. Agencies running 5+ rebuilds a month are the ones where the time saved on design specification extraction outweighs the credit spend.

Clonecode bills in credits, not seats: Starter at $9 monthly gives 12 credits, Pro at $29 gives 40, and the free tier allows 3 copies a day with 2 page downloads at signup. The framework asks an agency to model credits as a per-project input cost before quoting a rebuild. Take a five-page client site: capture consumes roughly five credits, so a Starter month covers two such rebuilds and a Pro month covers eight. Against the $1,800 Clonecode Site Starter offer, credit cost is trivial, but the real constraint is throughput, since a 16-hour setup plus build time caps how many captures a single operator can run. Agencies doing 5+ site rebuilds monthly should price Pro into every proposal and track credits per engagement; below that volume, the free tier's 3 daily copies is enough to prototype before committing. Dynamic pages (logins, live feeds, search results) never capture, so scope those out of any credit estimate.

AI code tools compress the cost of producing a first working version, but they do not compress the cost of owning it. The Scaffold Versus Steward Split separates two jobs agencies have historically billed as one: scaffolding (generating a full-stack app, wiring auth and payments, standing up a prototype) and stewardship (architecture decisions, review, and keeping consumer code in sync when contracts change). Scaffolding is where the speed advantage lives. Stewardship is where retainer value and liability live. Verdent illustrates the first half, turning a plain-English description into a working product with authentication, payments, and an admin dashboard. Ripple illustrates the second, detecting a breaking API change and opening pull requests across every affected repository. Agencies that price both halves at the same rate give away the margin on scaffolding and undercharge for stewardship. Split the two in your statements of work, and staff them differently.

The Agent Output Liability Line is the boundary between code an agency can ship under its own name and code that still needs a human signature. Agentic tools now generate full-stack applications from prompts and auto-fix breaking API changes across repositories, which moves the liability question from 'did we write it' to 'who reviewed it.' Agencies that blur this line absorb client risk without pricing it. A practical test: if an agent opens a pull request at 2am and no human reads the diff before merge, that code sits above the line and belongs in a maintenance retainer, not a fixed-scope build. Tools like Agent Monitor and Agent Desk exist specifically to make that review boundary visible by surfacing per-file risk levels and session histories. The framework matters because delivery speed without a defined liability line converts margin into unpaid warranty work.

Run the 2 free page downloads on a live client site first, then commit to Pro at $29 only once your monthly page captures exceed the 12 credits Starter gives you at $9.

Set a hard blast-radius limit per agent run, then require a named human reviewer before any change merges into a client branch.

IF your agency runs 5+ client site rebuilds or redesigns per month and each project needs design tokens, fonts, and component structure handed to Claude Code, Cursor, or v0, THEN start on Clonecode Pro at $29/month for 40 credits so per-page cost drops below the Starter rate. IF rebuild volume is under roughly 3 pages a month, stay on the Free tier (3 copies a day, first 2 page downloads) or Starter at $9/month for 12 credits and defer the paid commitment until a paid client engagement justifies it.

A productized rebuild offer where agencies capture a reference site's full blueprint with Clonecode, hand the packaged prompts and design tokens to Claude Code or Cursor, and deliver a client-ready site in under two weeks.