wcagent

wcagent gates every AI-generated change on passing tests, successful builds, and recorded diffs, so an agency can hand a client evidence instead of a promise. At $4.99 USD per month per seat, the extension is the cheapest line item in the stack, yet it is the one that makes AI-assisted delivery defensible in a client audit. The catch is that model access is not bundled: the agency or client still carries a separate ChatGPT, Claude, Gemini, Grok, or DeepSeek subscription.

wcagent does not gate completion on what the model says, it gates on what the repository proves: passing tests, successful builds, recorded diffs, and diagnostics. That single design choice reshapes how an agency prices and staffs AI-assisted delivery. A retainer client paying $4.99 USD per seat per month for the extension still needs their own ChatGPT, Claude, Gemini, Grok, or DeepSeek subscription, so the agency's real cost is seat fee plus model access plus the review time saved. On a 16-hour Starter Code Audit billed at $1,800, the evidence history becomes the deliverable: the handoff summary carries diffs and test results the client can inspect without re-running the work. Agencies that treat wcagent as a verification layer, not an autocomplete layer, can defend a higher audit fee because every claim in the report traces to a recorded artifact rather than a model assertion.

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.

Adopt wcagent only when the client repo already has tests and builds to gate on, and price the seat into the retainer rather than eating it.

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 delivers AI-assisted code changes to clients who already work in desktop VS Code and maintain test/build infrastructure, THEN wcagent at $4.99 USD per month per seat (or $4.17 USD annualized) is a low-cost way to gate every AI change on passing tests, successful builds, and recorded diffs. IF clients expect the tool to bundle model access or work outside VS Code, THEN skip it, because wcagent requires separate ChatGPT, Claude, Gemini, Grok, or DeepSeek subscriptions and runs only as a desktop VS Code extension.

Agency retainer that deploys wcagent inside client VS Code environments so every AI-assisted code change ships with test, build, and diff evidence the client can audit. Priced as a per-developer monthly service on top of the $4.99 USD seat cost.