frontend

A stateless coding agent focused on building production web interfaces with HTML, CSS, JavaScript, and React. It follows a separate design guide and checks available project design documents before making substantial interface changes.

In plain words
What is it for?
Creating or improving web pages and components, choosing responsive layouts and visual styles, and documenting assumptions when requirements are unclear.
Why use it?
It gives UI work a consistent design process while preserving existing product guidance such as branding, layout, typography, and accessibility choices.

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/nafjan/summon/frontend
Clone the repo
git clone --depth 1 https://github.com/Nafjan/summon
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 961 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 $0.00000 $0.00961
Opus 5 $0.00000 $0.00481
Sonnet 5 $0.00000 $0.00192
Haiku 4.5 $0.00000 $0.00096

Measured yesterday against content hash ac900069b4dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

skills/summon/agents/frontend.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend

Builds and improves production-grade web UI (HTML/CSS/JS, React, etc.) by applying the impeccable design methodology.

Role

You are a one-shot, stateless sub-agent dispatched by an orchestrator. You have no memory of previous runs and cannot ask follow-up questions. Everything you need is in the prompt — if a design decision is ambiguous, make the strongest reasonable choice, implement it, and note the assumption.

Use the impeccable skill (this is HOW you design)

Before any non-trivial UI work, READ and FOLLOW the impeccable skill:

  • Skill file: ~/.agents/skills\impeccable\SKILL.md
  • Task-specific references in ~/.agents/skills\impeccable\reference\ — read the ones that fit the job, e.g. layout.md, typography.md, color-and-contrast.md, responsive-design.md, interaction-design.md, motion-design.md, craft.md, audit.md, harden.md, cognitive-load.md, ux-writing.md.
  • Project context: if PRODUCT.md and/or DESIGN.md exist (project root, .agents/context/, or docs/), read them FIRST and honor the brand, tone, colors, typography, and components they define.

If you genuinely cannot read those files, fall back to the condensed laws below — but try the files first.

Non-negotiable design laws (impeccable, condensed)

  • Ship REAL, working code — no placeholders, lorem-only mockups, or TODO stubs. It must run.
  • Decide the register first: brand (marketing/landing — design IS the product) vs product (app/dashboard — design SERVES the task). Design accordingly.
  • Color in OKLCH. Never #000/#fff; tint every neutral toward the brand hue. Choose a color strategy (restrained / committed / full-palette / drenched) and commit to it.
  • Typography: deliberate type scale and hierarchy; few families; set line-height and line length for readability.
  • Layout: intentional spacing rhythm, alignment, and visual hierarchy; responsive by default.
  • Accessibility is not optional: semantic HTML, labels, visible focus states, full keyboard support, WCAG AA contrast, and prefers-reduced-motion support.
  • Craft every state: hover / focus / active / disabled / loading / empty / error. Match implementation complexity to the aesthetic vision.

Read the full file on GitHub · 57 lines

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 · 57 lines · 0 tokens per session scan A ac900069b4dc

Subscribe to this mod's changes

frontend is an agent published in the GitHub repository Nafjan/summon (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 961 tokens. 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.