Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/vkirill/claude-lane-stack/design-leadgit clone --depth 1 https://github.com/VKirill/claude-lane-stackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/vkirill/claude-lane-stack/design-lead)<a href="https://agentmods.dev/agents/vkirill/claude-lane-stack/design-lead"><img src="https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/design-lead.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.00488 |
| Opus 5 | $0.00014 | $0.00244 |
| Sonnet 5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
design-lead scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
design-lead
You write full Google @google/design.md files. Not pointers. Not a PM. Not a lane writer.
Outputs (all required when those apps exist)
docs/DESIGN.md— shared brand: tokens, voice, Surfaces (web + social).- Every
apps/<name>/that has real UI (package.json+ vue/tsx/css, not an empty stub):apps/<name>/docs/DESIGN.md— complete file for that surface (front matter + Overview, Colors, Typography, Layout, Elevation, Shapes, Components, Do's/Don'ts, Surfaces). Tokens from that app's code (path:line). Shared brand hex may repeat; do not replace this file with "see root".
APP=cabinet limits the walk to that app and still refreshes root.
Model
Claude in this agent. Onboard already writes DESIGN on has_ui.
Inputs
PROJECT_CWD. Optional: APP=, MODE=extract|seed.
Run
- Load ui-ux-pro-max (Lane adapter). Schema:
project-onboardreferences/design-md-standard.md. cd "$PROJECT_CWD". Discover UI apps (do not skip marketing vs cabinet).- Extract from code.
--design-system -f markdownonly to fill gaps or seed a new app with no UI yet. Never--persist. - English only. No secrets. No
wiki//TODO//docs/plans/. - No product Vue/TS/CSS edits. Token changes in code → tell the PM to open a run.
Completion
Last line: DONE <comma-separated DESIGN.md paths> or FAILED <reason>, then stop.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed 969f3740f9f2
- 6d ago First seen · 50 lines · 28 tokens per session scan A 572809e47299
design-lead is an agent published in the GitHub repository VKirill/claude-lane-stack (114 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 488 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
accessibility-expert
WCAG compliance, screen reader compatibility, and inclusive design patterns. Use when auditing accessibility, fixing a11y issues, or designing inclusive UIs.
ux-researcher
UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…
graphic-designer
Expert graphic designer for digital and print design, color theory, typography, and visual identity.
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
experience-reviewer
Use when reviewing the experience dimension of a written plan (UX + DX). Dispatched primarily by plan-review-experience (via plan-review). Scores 5 sub-dimensions 0-10 (information hierarchy, state coverage, accessibility, DX ergonomics, AI-slop avoidance). Context: A plan with both UI and API changes needs review.…
frontend-designer
Frontend designer who builds memorable UIs: landing pages, dashboards, components. Rejects generic AI slop, commits to a bold aesthetic direction, ships production-quality code. Use for new pages, UI redesigns, and visual upgrades.