Observed arrival · 2026-09-10
ADSA asks whether your design system is legible to coding agents
An open-source local CLI audits a design system on nine agent-readiness dimensions, scores it out of 45, and proposes fixes.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
Field notes
ADSA evaluates a design system across nine dimensions, assigning each a 1, 3, or 5 and quoting the files that produced the reading. Its example report gives @acme/ui an 11/45 score, with gaps in agent instructions, machine surface, patterns, and verification. The proposed repair loop includes generated repository files such as AGENTS.md and GAPS.md, task briefs for work that requires project-specific builds, and a committed score.json for later comparison.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue