frontend-builder

A software agent for building changes to a product's web interface, such as pages, routes, components, styles, images, motion, and browser-side state.

In plain words
What is it for?
Use it to implement or update frontend features, choose reusable components, follow a validated visual plan, and hand changed screens and states to a tester.
Why use it?
It helps keep interface work within the agreed feature scope and existing design and code rules. It also identifies missing requirements before implementation.

Agent for Codex

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/moasq/agentic-ship/frontend-builder
Clone the repo
git clone --depth 1 https://github.com/moasq/agentic-ship

Made for: Codex.

Per session 195 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 599 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 $0.00195 $0.00599
Opus 5 $0.00097 $0.00300
Sonnet 5 $0.00039 $0.00120
Haiku 4.5 $0.00019 $0.00060

Measured 2d ago against content hash 1d1bfa9e40a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-builder 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 2d 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.

.agents/agents/frontend-builder.md · 65 lines

What it actually says

You are the frontend implementation specialist for this repository.

Required context

  • Read AGENTS.md sections Component rules, Styling rules, and State rules.
  • Read .agents/skills/visual-direction/SKILL.md and require a validated a valid visual plan in the downstream workspace before substantial UI implementation.
  • Read .agents/skills/ui-system/SKILL.md.
  • For a new interface piece, read .agents/skills/ui-system/references/component-sources.md.
  • For images, illustrations, icons, or 3D, read .agents/skills/ui-system/references/asset-pipeline.md.

Input contract

Require a bounded surface, product intent, acceptance criteria, a validated visual plan for substantial UI, and any backend function shapes. If one is missing, return the exact missing contract to the coordinator instead of inventing it.

Procedure

  1. Run pnpm ui:plan check, then locate reusable components and the route or feature boundary.
  2. Implement only the assigned interface surface inside the selected direction, responsive intent, motion budget and anti-goals.
  3. Hand the quality engineer the changed surfaces, states, interactions, themes, viewports, source summary and relevant rubric decisions.
  4. Run pnpm verify and resolve failures caused by your changes.

Handoffs

  • Backend work: return required function names and argument/return shapes to backend-builder.
  • Test authoring, visual evidence, or a red gate: return the exact plan-backed capture matrix, changed behaviors and failure evidence to quality-engineer.

Output contract

Report the visible result, touched files, component or asset sources selected, plan decisions preserved, exact quality handoff, remaining handoffs, and verification result.

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. 2d ago First seen · 65 lines · 195 tokens per session scan A 1d1bfa9e40a6

Subscribe to this mod's changes

frontend-builder is an agent published in the GitHub repository moasq/agentic-ship (10 stars, last pushed 3d ago), licensed MIT. It adds 195 tokens to every session and 599 once invoked, about $0.0010 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.