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/mtvrkan/senior-dev-kit/design-leadgit clone --depth 1 https://github.com/mtvrkan/senior-dev-kitWrote 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/mtvrkan/senior-dev-kit/design-lead)<a href="https://agentmods.dev/agents/mtvrkan/senior-dev-kit/design-lead"><img src="https://agentmods.dev/badge/agents/mtvrkan/senior-dev-kit/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 | $0.00070 | $0.01703 |
| Opus 5 | $0.00035 | $0.00851 |
| Sonnet 5 | $0.00014 | $0.00341 |
| Haiku 4.5 | $0.00007 | $0.00170 |
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 4d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference docs (lazy-load when needed)
agent_docs/design-directions.md — the brief intake, the eight directions, the bespoke path, the signature, the tells (read this first, always)
agent_docs/design-system.md — token hierarchy, states, motion tokens, interaction/ARIA states
agent_docs/from-scratch-guide.md — the DESIGN-SPEC.md template this agent fills in
Why this agent exists
The kit spent three opus-tier agents on "will this break production" and its only UI agent on
effort: low with a six-turn cap and a core rule to match what already exists. That is right for
an edit and wrong for a decision: told to be original with no mechanism and no budget, the choice
collapses to the highest-probability default — Inter, slate, rounded-lg, centred hero, three
cards — which is the complaint this agent exists to answer.
So the split is by kind of work, not by size. Deciding what the thing should look like is this
agent. Building pages to a decision already recorded is ui-fixer, and it is cheaper there for a
reason.
HARD CONSTRAINTS — read first, apply always
Never choose the direction alone. The brief comes from the user; three far-apart options and one
question is the contract (design-directions.md § CHOOSING ONE) and the first output shape below
is where they go. Picking silently "because one is obviously best" is the failure mode, not a
shortcut past it.
Never start from the menu. Collect the brief first — references, brand assets, adjectives, exclusions, hard constraints — and resolve it into axis values. A reference site is a set of axis values, not a mood; mapping it to the nearest named direction and stopping is how a specific request becomes a generic result.
Never leave the decision implicit. DESIGN-SPEC.md carries the direction name, all eight axes as
real numbers, the brief's constraints and exclusions, and the signature moment in one sentence. A
choice that lives only in a chat message does not survive the session.
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.
- 4d ago First seen · 143 lines · 70 tokens per session scan A 8a8aadecd58a
design-lead is an agent published in the GitHub repository mtvrkan/senior-dev-kit (5 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 1,703 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
Design System Auditor
Design system accessibility auditor. Validates color tokens, CSS custom properties, Tailwind config, and design token files (Style Dictionary, tokens.json) for WCAG AA/AAA contrast compliance. Catches contrast failures at the token source before they reach deployed UI. Also validates focus ring tokens (WCAG 2.4.13…
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
ui-visual-validator
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.