responsive-adapter

responsive-adapter is a skill for Claude Code, Codex from sergeyizmailov/knowledge-delta-skills. It costs 109 tokens per session (2,640 once invoked), scanned A, original, MIT.

A set of changes that makes an existing webpage adapt to screens from small phones to very wide monitors while keeping its established visual design. It adjusts layout, widths, menus, and other mobile behavior without redesigning the page.

In plain words
What is it for?
Use it to make landing pages, admin panels, and dashboards responsive, repair mobile layouts and breakpoints, and adapt wide tables or off-canvas menus.
Why use it?
It fixes pages that overflow, become hard to use, or break at different screen sizes while preserving the desktop appearance as the reference.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to make landing pages, admin panels, and dashboards responsive, repair mobile layouts and breakpoints, and adapt wide tables or off-canvas menus.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sergeyizmailov/knowledge-delta-skills/responsive-adapter
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.

Any agent
npx skills add sergeyizmailov/knowledge-delta-skills --skill responsive-adapter
Clone the repo
git clone --depth 1 https://github.com/sergeyizmailov/knowledge-delta-skills

Made for: Claude Code, Codex.

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-adapter

README.md
[![agentmods](https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/responsive-adapter/github.svg)](https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/responsive-adapter)
Your own site
<a href="https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/responsive-adapter"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/responsive-adapter/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-adapter

Your own site · 80×15
<a href="https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/responsive-adapter"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/responsive-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,640 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 $0.00109 $0.02640
Opus 5 $0.00055 $0.01320
Sonnet 5 $0.00022 $0.00528
Haiku 4.5 $0.00011 $0.00264

Measured 9d ago against content hash 97881040d92f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

responsive-adapter 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/scan.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/responsive-adapter/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Responsive Adapter

$SKILL_DIR = this SKILL.md's directory; set once per session. All script paths are relative to it.

The desktop visual is the source of truth; every other width is a graceful adaptation — layout adapts, style does not. Fixing what wasn't broken on responsiveness grounds is scope creep — report it, don't touch it.

Allowed vs forbidden

Allowed Forbidden
Any CSS / Tailwind utility class Color palette, brand colors
Adding <meta name="viewport"> if missing Font families
Wrapping elements (overflow-x-auto around a wide table) Iconography, illustrations, content, copy
hidden md:block / md:hidden toggles for off-canvas menu New components or redesigns of existing ones
A small hamburger toggle (≤15 lines, or native <dialog>) Swapping the established UI library
Restructuring grid columns (grid-cols-3grid-cols-1 md:grid-cols-3) Removing sections that "don't fit" — adapt them
Replacing fixed px widths with fluid units Refactor beyond what responsiveness demands
aria-label where mobile UX needs it for an icon button

Desktop screenshots before and after must be indistinguishable except where you intentionally stacked or collapsed.

Breakpoints (Material 3-aligned)

xs 320  — ultra-small, foldable cover
sm 390  — iPhone baseline (12–16)
md 600  — M3 Compact→Medium (iPad mini portrait, phone landscape)
lg 840  — M3 Medium→Expanded (iPad portrait, foldable inner)
xl 1200 — M3 Expanded→Large (laptop)
2xl 1600 — M3 Large→XL (desktop)

If the project already has a system (Tailwind 640/768/1024/1280/1536, Bootstrap), extend it, never run a second one in parallel.

Phase 1 — Discover

  1. Identify project root; ask once if unstated.
  2. Detect stack per file — .html + .css → vanilla (references/vanilla-css.md); tailwind.config.* / @tailwind / md: classes → Tailwind (references/tailwind.md); styled-components / @emotion / .styled.ts → CSS-in-JS (references/css-in-js.md); *.module.css → treat as vanilla. Mixes are common.
  3. Enumerate pages/routes in scope.
  4. Note the existing breakpoint conventions.
  5. Open at 1440px via agent-browser and capture the baseline screenshot — the visual contract.

Read the full file on GitHub · 156 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. 9d ago First seen · 156 lines · 109 tokens per session scan A 97881040d92f

Subscribe to this mod's changes

responsive-adapter is a skill published in the GitHub repository sergeyizmailov/knowledge-delta-skills (3 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 2,640 once invoked, about $0.0005 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.