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.
git clone --depth 1 https://github.com/ccevans/bobbycodeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/ccevans/bobbycode/bobby-design-mockup)<a href="https://agentmods.dev/agents/ccevans/bobbycode/bobby-design-mockup"><img src="https://agentmods.dev/badge/agents/ccevans/bobbycode/bobby-design-mockup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ccevans/bobbycode/bobby-design-mockup"><img src="https://agentmods.dev/badge/agents/ccevans/bobbycode/bobby-design-mockup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00455 |
| Opus 5.5 | $0.00012 | $0.00182 |
| Sonnet 5.5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
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 today.
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.
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
- 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."
- 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.
- Build two options per reference: faithful, plus a variant using the same extracted system in a different composition.
- Use the user's real content throughout, identical across options, so only the design varies.
- 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.
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.
- today Changed · +2 lines ac1c6b3471d5
- 1mo ago First seen · 36 lines · 31 tokens per session scan A 1393988c3688
bobby-design-mockup is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 455 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
aiox-ux
AIOX UX Design Expert autônomo. Frontend architecture, UI/UX design, wireframes, design system, accessibility, component design. 5 fases completas.
aiox-ux-design-expert
🎨 UX/UI Designer & Design System Architect (Uma). Complete design workflow - user research, wireframes, design systems, token extraction, component building, and quality assurance Activate with /aiox-ux-design-expert or spawnsubagent subagenttype="aiox-ux-design-expert".
meto-epic-{{EPIC_ID}}
Use to implement tasks belonging to {{EPICNAME}} ({{EPICID}}). Owns {{EPICDOMAIN}}. Picks tasks tagged {{EPICID}} from tasks-todo.md and runs independent tasks in parallel. Reports checkpoint status to SWARMAWARENESS.md every 3 completed tasks. Do NOT use for tasks belonging to other epics.
meto-tester
Validate work in tasks-in-testing.md. Full acceptance criteria are in the task block. One item at a time, always sequential. Never fixes bugs, only flags and sends back.
meto-pm
Planning, backlog management, epic definition, and task slicing. Reads context files and writes full task definitions into the backlog. Use before any new feature work.
visual-director
Visual director - visual briefs, color palettes, composition, AI prompt creation.