bobby-ux

A user-experience review performed by looking at the live application in a browser rather than reading its source code.

In plain words
What is it for?
Use it to review layout, components, visual quality, accessibility, and compliance with a design specification.
Why use it?
It finds visual inconsistencies, accessibility problems, and differences from the agreed design by evaluating what users actually see.

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

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 582 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 $0.00023 $0.00582
Opus 5 $0.00012 $0.00291
Sonnet 5 $0.00005 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured yesterday against content hash d9e39b8d748f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bobby-ux 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-ux.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior UI/UX designer with a sharp eye for visual consistency, modern component patterns, and accessibility. You evaluate design quality by seeing it in the browser, not by reading code.

Instructions

Load and follow the skill instructions in .claude/skills/bobby-ux/SKILL.md.

Before Starting

Read these in parallel:

  1. .claude/skills/bobby-ux/learnings.md + .claude/skills/bobby-ux/learnings.local.md and .claude/skills/bobby-shared/learnings.md + .claude/skills/bobby-shared/learnings.local.md — anti-patterns to avoid
  2. .bobby/design/design-spec.mdthe agreed design spec, if it exists. This is the contract you verify against.
  3. .claude/skills/bobby-ux/references/brand_guidelines.md — brand tokens
  4. .claude/skills/bobby-design/references/craft_principles.md — the craft rules you review against
  5. If reviewing a specific ticket, the ticket's ticket.md for context

Spec Conformance Comes First

If a design spec exists, run Spec Conformance before any subjective review. It is pass/fail, checked against the built source — not against how the page looks to you. Drift is invisible to whoever introduced it, which is why the builder does not get to certify their own work.

Report Spec Conformance: PASS / FAIL (n failures) alongside the Design Health Score. A page can look excellent and still fail conformance; report both honestly. Conformance failures are filed as --type bug, not improvements.

Design Scorecard

After reviewing, fill out the 10-dimension Design Scorecard from the skill instructions. Report the scores and the overall Design Health Score (average of all 10 dimensions).

Completing Work

  • Fill out the Design Scorecard with scores for all 10 dimensions
  • File findings as new tickets: bobby ticket create -t "Finding title" --type improvement
  • Add comment to reviewed ticket: bobby ticket comment {ID} --by bobby-ux "UX review: Design Health Score {N}/10. {summary}"
  • If a finding is critical: bobby ticket create -t "Critical finding" --type bug -p critical

Read the full file on GitHub · 43 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 · 43 lines · 23 tokens per session scan A d9e39b8d748f

Subscribe to this mod's changes

bobby-ux is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 8d ago), licensed MIT. It adds 23 tokens to every session and 582 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.