What is TheDesignAgent?

A design agent that works inside your coding agent's loop. It works in layers: a brief before the agent builds a screen (the user's job, the heuristics and patterns that apply, your design tokens), a UX review and a visual review after it builds, and a project memory that every agent on the repo shares. It catches the generic, technically-correct-but-wrong UI that agents ship by default.

Which coding agents does it work with?

Any MCP client: Claude Code, Codex, Cursor, Grok Build, Claude Desktop and others. Claude Code also has a plugin that adds skills for the brief, build and review loop.

How do I add it to my agent?

Point your client at the hosted MCP server (https://www.thedesignagent.ai/mcp, nothing to install) and sign in through the browser, or get an API key and run the local server with npx (package @thedesignagent/mcp). In Claude Code, install the plugin: /plugin marketplace add CMBurnett/the-design-agent-plugin, then /plugin install tda@thedesignagent.

What do Discover, Ux and Visual do?

Discover returns a short build brief before your agent builds a screen. Ux scores the built screen 0 to 10 for job fit, UX heuristics, cognitive load and pattern conformance. Visual scores brand compliance, visual hierarchy and aesthetics from a real screenshot of the running page. All three run on the hosted server, where Visual screenshots public pages and preview deploys; run the local server to screenshot localhost.

Is it an accessibility checker?

No. Accessibility checkers and Lighthouse cover one layer: whether a screen is valid. TheDesignAgent covers the whole design pass: whether the screen fits the user's job, follows UX heuristics, keeps cognitive load down, matches your patterns and brand, and holds up visually. Run an accessibility checker alongside it.

How is it different from a design prompt or a frontend skill?

Design skills and prompts shape how the agent styles a site, with the same guidance for every project. TheDesignAgent is a design agent the coding agent works with on every screen: it briefs before the build, reviews after, and keeps a model of your project (jobs, personas, design tokens, past findings), so findings cite your user's job rather than generic best practice and sharpen with every call.

A small .thedesignagent pointer file with your project id lives in your repo. The project model and review history are stored server-side so every agent on the repo shares them. Visual's screenshots stay on your machine for 24 hours.

How much does it cost?

16 free credits every month with no card, then one-time credit packs with no subscription: 1 credit per call (Discover, Ux or Visual). Packs run from $37 for 40 credits to $999 for 1,500, last 12 months, and can auto-recharge. Failed calls are free and degraded calls cost half.

Can an agent buy credits on its own?

Yes, over MPP (Machine Payments Protocol), with no login. GET https://www.thedesignagent.ai/api/credits/mpp lists the packs; POST /api/credits/mpp/ returns a 402 payment challenge, and paying it returns an API key or tops up the key sent as X-Api-Key.

TheDesignAgent — The judgment layer for agent-built UI

Invoice 1 of 11 left · V-10482 · Net 30

Halvorsen Industrial Supply

14 invoices this year · 1 prior price variance

Invoice total

$6,275.25

Due 28 Oct

Variance2 of 4 lines out of tolerance · invoice is +$309.00 over what was ordered and received.

Purchase order

PO 4500-21877

9 Sep · R. Okafor

CC 3120 · Plant maintenance

Ordered$5,713.00

Price differs

Goods receipt

GR 5000-39102

24 Sep · Dock 2 · M. Ruiz

Posted in ERP

Received value$5,488.00

Quantity differs

Invoice

HIS-88412

28 Sep · Net 30

Tax $478.25 (8.25%)

Billed, before tax$5,797.00

Billed above PO / receipt

Lines that need a decision

Item	PO qty × price	Received qty	Billed qty × price	Result
Pressure gauge 0–300 psi, glycerin PG-0300G	24 × $42.00	24	24 × $45.50	Price mismatch +$3.50/unit × 24 = +$84.00 Limit 2% and $50 per line
Quick coupler, steel, ½in NPT QC-050S	60 × $18.75	48	60 × $18.75	Billed more than received 12 units × $18.75 = +$225.00 Limit $50 per line

Other checks

Duplicates — none in vendor history

Vendor — bank verified, not on hold

Tax — 8.25% matches ship-to rate

Recommended next moveYou own this · do it today, before Thursday's procurement review

Get Priya Natarajan, the CFO, on a 30-minute call with Dana before procurement meets Thursday.

It puts our value case in front of the person who signs, and Dana's reply tells you if she's still in.

Why this, why now

Priya Natarajan (CFO) has never been in a meeting
She signs anything over $200K, and procurement reviews the contract Thu, Oct 8. Source: Approval matrix, Sep 22
Dana Reyes, your champion, has been silent for 11 days
Two emails unopened since the $250K pricing proposal went out on Sep 23. Source: Email tracking
Fleetwise is offering a 20% first-year discount
Marcus Lin raised it on the Sep 30 security call. Price is now on the table. Source: Call notes, Sep 30

Opens an editable email below. Nothing sends until you review it.

Other moves, compared to the recommendation

Recent activity

Oct 2Sam Okafor returned legal redlines with 2 open clauses
Sep 30Security review passed, Marcus Lin signed off on the SOC 2 package
Sep 28Jen Walsh confirmed pilot results: 14% fewer idle truck hours

Page	Check	Score	Result
`/`	ux	6.0	fail
`/`	visual	6.8	pass
`/support`	ux	7.5	pass

The judgment layerfor agent-built UI.

Your agent ships the wrong UI — the same three ways, every time.

“It built another dashboard.”

“Tabs again.”

“The shadcn defaults are showing.”

Here's the same agent, the same model — with us in the loop.

Halvorsen Industrial Supply

Lines that need a decision

Other checks

Rotate refresh tokens on every use to close the replay window

Halcyon Logistics · Fleet Ops Platform — Enterprise

Get Priya Natarajan, the CFO, on a 30-minute call with Dana before procurement meets Thursday.

Why this, why now

Other moves, compared to the recommendation

Recent activity

One design agent. Three layers. Calibrated to the job — not a generic rubric.

Reads your system first.

Scores against the brief.

What code review can't see.

In your agent as it builds. On every pull request.

One credit, one call. Buy a pack when you need more.

Start free. No card.

Built for whoever owns the UI.

Ship right the first time.

Drop in any repo. Any stack.

Your taste becomes the constraint.

Out of the QA loop for agent slop.

What we're learning while building this.

The component library was the right answer to a problem agents no longer have

The dashboard default: why agents build viewers when the job is deciding

Questions, answered.

The judgment layerThe judgment layerfor agent-built UI.

Your agent ships the wrong UI — the same three ways, every time.

“It built another dashboard.”

“Tabs again.”

“The shadcn defaults are showing.”

Here's the same agent, the same model — with us in the loop.

Halvorsen Industrial Supply

Lines that need a decision

Other checks

Rotate refresh tokens on every use to close the replay window

Halcyon Logistics · Fleet Ops Platform — Enterprise

Get Priya Natarajan, the CFO, on a 30-minute call with Dana before procurement meets Thursday.

Why this, why now

Other moves, compared to the recommendation

Recent activity

One design agent. Three layers. Calibrated to the job — not a generic rubric.

Reads your system first.

Scores against the brief.

What code review can't see.

In your agent as it builds. On every pull request.

One credit, one call. Buy a pack when you need more.

Start free. No card.

Built for whoever owns the UI.

Ship right the first time.

Drop in any repo. Any stack.

Your taste becomes the constraint.

Out of the QA loop for agent slop.

What we're learning while building this.

The component library was the right answer to a problem agents no longer have

The dashboard default: why agents build viewers when the job is deciding

Questions, answered.

The judgment layerfor agent-built UI.