08 /How it was built
Built in two days, with AI. The judgment stayed mine.
Claude Code wrote most of the files. I decided what to build, what was true, and what was good enough to ship. Five moments from the build show how that split works.
“Where agents write the code and design keeps the judgment.”
Coding agents write the code.
messay.ai brings the design team.
A Claude Code plugin that gives your agent a product design team’s judgment, keeps it inside your design system, and remembers every decision.
Early access. Free and open source (Apache 2.0) at launch.
[ Works with ]
- Claude Code
- Figma
- Jira
- Azure DevOps
- GitHub
Guardrails on every edit.
The token guard and commit gate keep the agent inside your design system and accessibility bar.
A team's disciplines, on demand.
Say what you're building. It chains the research, design and engineering steps, and skips what's done.
Memory across sessions.
About 800 tokens of rules, status and handoff load at start, so nobody re-explains yesterday.
- /messay:plan
- /messay:setup
- /messay:whereami
- /messay:research
- /messay:synthesize
- /messay:problem
- /messay:clarify
- /messay:frame
- /messay:personas
- /messay:spec
- /messay:prioritize
- /messay:backlog
- /messay:visual
- /messay:system
- /messay:ia
- /messay:flow
- /messay:blueprint
- /messay:onboarding
- /messay:explore
- /messay:content
- /messay:figma
- /messay:think
- /messay:decide
- /messay:ship
- /messay:verify
- /messay:review
- /messay:a11y
- /messay:usability
- /messay:wrap
- /messay:retro
- /messay:promote
- Affordance and feedback
- Restraint
- Self-evident clarity
- Usability heuristics
- Goal-directed design
- Mobile first
- Design system structure
- Content design
- Plain writing, without AI tells
- Forms and input
- Trust
- Data display
- Web interface guidelines (Vercel)
- Accessibility, WCAG 2.2 AA
- UI states in code
- Trust in AI features
- Four product risks
- Opportunity solution tree
- Validated learning
- Jobs to be done
- Service blueprint
- Research interviews
- Test-driven development
- Refactoring
- Deep modules
- Use cases
- Shared domain language
- Threat modeling
31
commands, from research to retro
28
lenses, from Norman to WCAG
~800
tokens of startup context
0
dependencies in the hooks
01 /The problem
AI gave founders a team's output. Not a team's taste.
One person with a coding agent can now ship what used to take a small team. But the team brought more than hands: someone who asked who it's for, someone who sketched three ideas before building one, someone who guarded the design system, and someone who made sure everyone could use it. Without them, you get products that work and feel generic.
One person plus an agent ships like a team. messay.ai connects the roles the team used to bring.
02 /Try it · the token guard
Your design system, enforced on every edit.
This is the same check the plugin runs before the agent writes a file. Edit the code, add a color, break it on purpose. Then hit Use tokens.
src/components/book-button.tsx
Edit blocked · 5 raw values
- L2
bg-[#ff4800]one-off Tailwind value - L2
text-[#fff]one-off Tailwind value - L2
px-[13px]one-off Tailwind value - L2
py-[9px]one-off Tailwind value - L2
rounded-[7px]one-off Tailwind value
03 /Where the tokens go
Spend tokens building, not figuring out how to build.
Re-orienting
The agent re-reads the repo and you re-explain the product and yesterday's decisions.
Building the wrong thing
The agent commits to its first idea. You reject it and pay for the rebuild.
Design drift
Hardcoded colors and one-off sizes pile up until a later session spends a pass cleaning them.
Late accessibility fixes
Missing labels and keyboard traps surface in QA, after the code has moved on.
04 /How it works · 31 commands
Say what you’re building. It picks the disciplines.
/messay:planturns one sentence into a chain of steps a design team would take, and skips what’s already done. Every step is also a command you can run on its own.
/messay:planSay what you're building; get a chain of disciplines.
/messay:setupRead the repo, find the design tokens, write the rules. Once.
/messay:whereamiCurrent work, chain, gates and next step in 15 lines.
05 /Guardrails · 4 hooks
Quality that doesn’t depend on remembering to ask.
- 01
Session start
Every session
Loads rules, a trimmed brief, status and the last handoff, so nobody re-explains.
- 02
Token guard
Every file edit
Blocks raw colors and one-off sizes in UI code, and names the token to use.
- 03
Commit gate
Every git commit
Checks design tokens and accessibility for UI, and tests for logic if you turn them on.
- 04
Session end
Every close
If nobody wrapped up, writes a factual handoff from git.
06 /28 lenses
Review your work through the eyes of the people who wrote the books.
/messay:review looks at any screen, spec or pull request through named lenses, and every finding cites the principle behind it.
Drag to spin Click a lens
Design01 / 28
Affordance and feedback (after Don Norman)
Ask whether a person can tell what to do, do it, and know it worked, without being told.
/messay:review norman-affordance07 /Works where your team works
From the ticket to the canvas and back.
Figma
Directions go into your Figma file, built from your library. Edit by hand; pull the edits back through your tokens.
Jira
Start from a ticket. Triage the backlog for design readiness before developers pick it up.
Azure DevOps
The same, read-only by default. Every write to the tracker is shown and approved first.
09 /Get started
Two commands to install. One to set up.
Setup reads your repo, finds your design tokens and writes the rules once. After that, every session starts where the last one ended.
The repository opens at launch. Ask for early access to try it now.
# Add the marketplace and install
/plugin marketplace add messaydesign/messay.ai/plugin install messay@messay-ai
# Then, in your project
/messay:setup/messay:plan a booking flow for corporate travel coordinators
Building with AI? Bring a designer who does too.
I design products and the AI workflows that build them. If your team wants both, let’s talk.