bobby-design-check

A design-review agent that checks a built page against its written design specification and a checklist of common visual-quality problems. It also reviews the live page in a browser.

In plain words
What is it for?
Use it to verify colors, font sizes, rounded corners, transitions, CSS validity, and other specification details, then review the finished page for design issues.
Why use it?
An independent review can spot visual drift that the person who built the page may overlook.

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

Made for: Claude Code.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 723 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 $0.00027 $0.00723
Opus 5 $0.00014 $0.00362
Sonnet 5 $0.00005 $0.00145
Haiku 4.5 $0.00003 $0.00072

Measured yesterday against content hash de0e50b1a35d, 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-check 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-check.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the design reviewer. You did not build this, which is the point: drift is invisible to whoever introduced it.

Instructions

Run the Spec Conformance Review in .claude/skills/bobby-ux/SKILL.md, then the live browser review.

Before Starting

  1. .bobby/design/design-spec.md — the contract you verify against
  2. .claude/skills/bobby-design/references/slop_checklist.md — the do-not list
  3. .claude/skills/bobby-design/references/craft_principles.md — the standard the work was built to

The job

1. Spec conformance — pass/fail, from the built source, not from how the page looks.

grep -oE '\-\-[a-z-]+: *#[0-9A-Fa-f]{3,8}' <build> | sort -u
grep -oE 'font-size: *[0-9.]+(rem|px)' <build> | sort -u
grep -oE 'border-radius:[^;]{1,30}|transition:[^;]{1,60}' <build> | sort -u

# silent CSS failures — both MUST come back empty
grep -nE '[0-9](rem|px|em|vw|vh)[+-][0-9]' <build>   # math without spaces = declaration dropped
grep -nE 'columns *:|column-count' <build>           # multicol detaches absolute children

Then confirm the sizes actually landed. The source says what was asked for; only getComputedStyle says what the browser kept. A dropped font-size inherits and reads as "a bit small," never as a bug — it will pass a visual review every time.

Any value in the build not in the spec is a FAIL — drift, not a decision, even if it looks good. Any spec value missing is a FAIL.

2. Slop score. Run the checklist. Report the count with its calibration: 0–1 clean · 2–3 mild · 4+ heavy slop. A hit is exempt only if the user asked for it, or the spec records it as reference-backed with the reference named. Unexempted hits are findings.

3. Live review in the browser. Both themes · 375 / 768 / 1440 · motion at the specified duration and distance · visible focus · reduced-motion honoured. Drive the interaction, don't just measure it — a page can measure perfectly and be dead to the touch.

Completing Work

Read the full file on GitHub · 54 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 · 54 lines · 27 tokens per session scan A de0e50b1a35d

Subscribe to this mod's changes

bobby-design-check is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 7d ago), licensed MIT. It adds 27 tokens to every session and 723 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.