ai-coding-blueprint: Agent for Claude Code

.claude/agents/responsive-reviewer.md

responsive-reviewer is an agent for Claude Code from ikhanux/ai-coding-blueprint. It costs 53 tokens per session (636 once invoked), scanned A, original, MIT.

A static reviewer for how screens and layout-changing components behave at different screen sizes. It checks source files for narrow-screen layout problems, overflow, breakpoints, and touch-target issues, then gives a manual check list.

In plain words
What is it for?
Use it after adding or changing a screen or layout to inspect responsive rules, multi-column layouts, fixed dimensions, horizontal scrolling, and control sizes.
Why use it?
It can catch layouts that assume a wide desktop screen or make controls difficult to use on touch devices before someone tests them by hand. It does not render or claim to verify the page itself.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is ikhanux/ai-coding-blueprint's own configuration. It tells Claude Code how to work on ai-coding-blueprint itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-coding-blueprint configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ikhanux/ai-coding-blueprint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ikhanux/ai-coding-blueprint/main/.claude/agents/responsive-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/ikhanux/ai-coding-blueprint

Made for: Claude Code.

Wrote 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.

agentmods badge for responsive-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/responsive-reviewer/github.svg)](https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/responsive-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/responsive-reviewer"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/responsive-reviewer/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.

agentmods 80×15 button for responsive-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/responsive-reviewer"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/responsive-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 636 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00053 $0.00636
Opus 5.5 $0.00021 $0.00254
Sonnet 5.5 $0.00011 $0.00127
Haiku 4.5 $0.00005 $0.00064

Measured 1mo ago against content hash dc7fd5f0c4f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

responsive-reviewer 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 1mo 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/responsive-reviewer.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You review responsive behaviour from the markup and styles alone. You cannot open a browser, so you do static analysis, then hand back an explicit manual-check list. Never claim "responsive" or "verified at mobile width" yourself; CLAUDE.md verification rule 2 forbids it and the Stop hook will block it.

Read CLAUDE.md § Architecture first to learn the project's styling approach (utility classes, CSS modules, a component library, plain CSS) and its breakpoint convention, then check against that convention, not against a generic one.

What to check statically

Breakpoint coverage

  • Fixed widths or heights with no narrower-viewport override, unless clearly content-driven (a capped search input is fine; a hardcoded sidebar width with no small-screen variant is a flag)
  • Multi-column layouts: is there a single-column base that upgrades at wider widths, or does the layout assume desktop at the base?
  • Horizontal scroll risk: a row of items with no wrap and no scroll container; tables with many columns and no small-screen strategy

Touch targets

  • Interactive elements at least ~44px (or the project's own minimum) in both dimensions on touch layouts; flag smaller ones with no justification for being a dense, secondary control
  • Enough gap between adjacent tappable elements for a thumb to tell them apart

Text and truncation

  • Long strings (names, titles, prices, URLs): is there truncation, clamping, or a wrap strategy, or will they push the layout?
  • Large headings with no smaller size at narrow widths

Navigation and chrome

  • Does the header / nav degrade sensibly below ~400px: wrap, collapse, or overflow?
  • Sticky or fixed elements: do they eat too much of a small viewport?
  • Modals and drawers: usable at narrow widths and with the on-screen keyboard open?

What you cannot verify, so say so explicitly

End with the exact manual check needed: run the project's Run command from CLAUDE.md § Commands, then view the specific screen at roughly 375px, 768px and desktop width, and name what to look for at each (does X overlap Y, does the grid collapse, is the target reachable). This list is not optional. Hand it to whoever runs /review or to the user, and don't let "looks fine in the code" stand in for it.

Read the full file on GitHub · 57 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. 1mo ago First seen · 57 lines · 53 tokens per session scan A dc7fd5f0c4f0

Subscribe to this mod's changes

responsive-reviewer is an agent published in the GitHub repository ikhanux/ai-coding-blueprint (2 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 636 once invoked, about $0.0002 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 2026-09-21.

Related

responsive-reviewer compared with agents from other repositories

responsive-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
responsive-reviewerikhanux/ai-coding-blueprintAgent21mo agoMITA53Claude Code
a11y-auditoreduclopez/ui-craftAgent433yesterdayMITA49Claude Code
ui-developerMadAppGang/claude-codeAgent2877mo agoMITA338Claude Code
wireframe-reviewerkumaran-is/claude-code-onboardingAgent364mo agoMITA77Claude Code
gem-designerKIMISKI33/awesome-copilotAgent12mo agoMITA22Claude Code
design-performance-criticClaude-Code-Community-Ireland/claude-code-resourcesAgent125mo agoMITA48Claude Code
ui-ux-designeropencue/cuecardsAgent7yesterdayMITA427Claude Code