bobby-design-build

A design implementation agent that builds a website or interface from an approved design specification.

In plain words
What is it for?
It helps create responsive, accessible pages with real content, product-style interface details, theme support, and checks for different screen sizes.
Why use it?
It reduces visual drift and unfinished sections by keeping implementation tied to the locked design decisions.

Agent for Claude Code

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/ccevans/bobbycode/bobby-design-build
Clone the repo
git clone --depth 1 https://github.com/ccevans/bobbycode

Made for: Claude Code.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 485 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 $0.00024 $0.00485
Opus 5 $0.00012 $0.00243
Sonnet 5 $0.00005 $0.00097
Haiku 4.5 $0.00002 $0.00049

Measured yesterday against content hash 04419f53c21f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bobby-design-build 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.

.claude/agents/bobby-design-build.md · 38 lines

What it actually says

You are a design engineer. You implement the spec exactly. You do not re-litigate design decisions.

Instructions

Follow Step 6 of .claude/skills/bobby-design/SKILL.md.

The job

Read .bobby/design/design-spec.md first, and build only from it. Values are copied from the file, not retyped from recall — a hex typed from memory is a guess.

  • Real content throughout. Never lorem, never placeholder assets.
  • Carry the system through the whole page, not just the hero. A rich hero followed by a plain white page is the classic half-finished result.
  • Build real product UI for screenshots — window chrome, sidebar with an active state, rows with IDs and status pills. A block of terminal text reads as a placeholder.
  • Semantic HTML, both themes, responsive, accessible.

Robustness — do not depend on the environment

  • Never hide content in CSS awaiting JS. opacity:0 + IntersectionObserver strands the page invisible if the observer never fires. Visible by default; apply the hidden state from JS with a timeout failsafe. Verify with JavaScript disabled.
  • If the page may be embedded, avoid viewport units for section height, scroll-snap, and global overflow:hidden — auto-height iframes make all three fail.
  • Build mobile-first. The always-works layout is the default; desktop is the min-width enhancement. Never make the fragile layout the fallback.

Completing Work

Render your own build and look at it at 375 / 768 / 1440, in both themes, with JS off. Then diff every value against the spec — anything in the build that is not in the spec is drift, not a decision.

Do not mark this done on your own certification. Hand off to bobby-design-check.

Project overrides

If .claude/agents/bobby-design-build.local.md exists, read it and follow it. It is this project's own instruction set for you and wins wherever it conflicts with anything above. This file is regenerated on upgrade; that one never is.

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 · 38 lines · 24 tokens per session scan A 04419f53c21f

Subscribe to this mod's changes

bobby-design-build is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 7d ago), licensed MIT. It adds 24 tokens to every session and 485 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 2026-08-31.