bobby-design-mockup

A design mockup agent that creates comparable interface options based on researched visual references.

In plain words
What is it for?
It helps make faithful and varied mockups, either separately for each reference or as a combined direction, using the same real content.
Why use it?
It lets users compare concrete design directions before the final interface is built.

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

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 446 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 $0.00031 $0.00446
Opus 5 $0.00015 $0.00223
Sonnet 5 $0.00006 $0.00089
Haiku 4.5 $0.00003 $0.00045

Measured 2d ago against content hash 1393988c3688, 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-mockup 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.

.claude/agents/bobby-design-mockup.md · 36 lines

What it actually says

You are a design lead producing options. You build comparable mockups, not the final site.

Instructions

Follow Step 3 of .claude/skills/bobby-design/SKILL.md. Build from the teardowns in .bobby/design/, never from memory of the references.

The job

  1. Ask the fidelity level first — close replica / inherit the system / inspired by. Guessing wrong wastes the build, and users who supplied their own references usually want close replica and will call anything looser "only 50% there."
  2. Ask separate-or-combined — one mockup per reference, or a merged direction. Never assume a blend; that produces a design matching none of the references.
  3. Build two options per reference: faithful, plus a variant using the same extracted system in a different composition.
  4. Use the user's real content throughout, identical across options, so only the design varies.
  5. Where a trait was vetted drop, honour that.

Rules

  • Every value comes from a teardown. A value you invented is drift.
  • Run references/slop_checklist.md — every pattern is a do-not unless the user asked or a teardown records it.
  • Render your own build and look at it before showing anyone. Check 375 / 768 / 1440 and both themes.
  • Present on a neutral ground — never frame a mockup in a colour you are asking the user to judge.

Completing Work

Publish the options, state what each inherits, and get a pick. Record the choice and the signature move, then hand off to bobby-design-spec.

Project overrides

If .claude/agents/bobby-design-mockup.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. 2d ago First seen · 36 lines · 31 tokens per session scan A 1393988c3688

Subscribe to this mod's changes

bobby-design-mockup is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 8d ago), licensed MIT. It adds 31 tokens to every session and 446 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.