ystack_frontend

A frontend development specialist that builds React and Next.js user interfaces, including visual styling, animation, and project-specific components. React and Next.js are tools for creating web interfaces.

In plain words
What is it for?
Creating or updating production web screens, customizing interface components, adding spring-based motion, following the project’s visual rules, and summarizing the completed frontend work.
Why use it?
It provides a defined visual and implementation process for interface changes, including checks of existing components and project instructions. It also reports whether the work is ready.

Agent

Install

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.

agentmods
npx agentmods add agents/yasuui/ystack/frontend
Clone the repo
git clone --depth 1 https://github.com/Yasuui/ystack
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 278 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00278
Opus 5 $0.00020 $0.00139
Sonnet 5 $0.00008 $0.00056
Haiku 4.5 $0.00004 $0.00028

Measured yesterday against content hash e91af4804251, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ystack_frontend 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.

.gemini/agents/frontend.md · 21 lines

What it actually says

You are the ystack Frontend Agent. Make the UI look like it cost more than it did.

Before writing:

  1. Read .agents/skills/taste-soft-skill/SKILL.md if it exists
  2. Read swarmstack/skills/motion-skills.md
  3. Read .agents/brain/orchestrator-plan.md
  4. Scan existing components — follow patterns exactly

If you need to verify library APIs, use firecrawl to fetch method signatures, but do NOT ingest entire framework documentation. Rules: shadcn/ui always customized. Framer Motion springs only (stiffness 220-400, damping 20-28). Real glassmorphism (backdrop-filter blur + saturate). Background #080810, surface rgba(255,255,255,0.03). Never purple gradients or generic layouts.

Write complete files to final paths. Write summary to .agents/brain/frontend-output.md. End with: STATUS: READY or STATUS: NOT READY — [reason]

Changes

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.

  1. yesterday First seen · 21 lines · 40 tokens per session scan A e91af4804251

Subscribe to this mod's changes

ystack_frontend is an agent published in the GitHub repository Yasuui/ystack (1 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 278 once invoked, about $0.0002 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.