concreto

A frontend design and review skill for websites, dashboards, applications, and other visual interfaces. It uses project context and existing design files to guide layout, styling, accessibility, and responsive behavior.

In plain words
What is it for?
Use it to design or audit pages, components, design systems, landing pages, product interfaces, and responsive frontend implementations.
Why use it?
It gives an agent a structured way to inspect an existing interface and improve it consistently instead of making isolated visual changes.

Skill for Claude CodeCodex

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 skills/bigrapb/concreto/skill
Any agent
npx skills add Bigrapb/Concreto --skill skill
Clone the repo
git clone --depth 1 https://github.com/Bigrapb/Concreto

Made for: Claude Code, Codex.

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,509 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 $0.00093 $0.01509
Opus 5 $0.00046 $0.00754
Sonnet 5 $0.00019 $0.00302
Haiku 4.5 $0.00009 $0.00151

Measured 2d ago against content hash 7c4ca2e81ae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

concreto 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 2d 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.

skill/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Advanced design intelligence for production-grade frontend interfaces. Deterministic rules, ML-enhanced detection, and comprehensive design guidance.

Setup

REQUIRED BEFORE PROCEEDING:

  1. Run node {{scripts_path}}/context.mjs once per session. If you've seen its output, skip. The script outputs PRODUCT.md (and DESIGN.md when present). If output reports NO_PRODUCT_MD, stop and run init before continuing.
  2. If user invoked a sub-command, read reference/<command>.md next. Non-optional. The reference defines the command flow.
  3. Read at least one project file (CSS/tokens/theme/component). Required even with a sub-command reference loaded. Use existing patterns.
  4. Read the matching register reference:
    • brand (marketing, landing, portfolio) → reference/brand.md
    • product (app UI, dashboard, tool) → reference/product.md Pick by: task cue → surface in focus → register in PRODUCT.md.
  5. If no committed brand colors exist, run node {{scripts_path}}/palette.mjs for color seed and composition guidance. Use OKLCH throughout.

Core Principles

Production-Grade Output

Ship complete, polished implementations. Not prototypes. Not starting points. Every page, component, and interaction is battle-tested.

The Test: Would You Sign It?

If you wouldn't put your name on the code, it's not done. This means:

  • Zero warnings in browser console
  • No placeholder content
  • Responsive at every breakpoint
  • Keyboard navigable
  • Screen reader tested

Design Rules

Color

[A01-CRITICAL] Verify contrast ≥4.5:1 for body text
[A02-CRITICAL] Verify contrast ≥3:1 for large text
[V01-HIGH] Never gray text on colored backgrounds
[V02-MEDIUM] Tint neutrals toward brand hue, not warmth-default
[V03-LOW] Document color strategy before picking colors

Color Strategy Commitment Axis:

  • Restrained: Tinted neutrals + one accent ≤10%
  • Committed: One color covers 30-60%
  • Full Palette: 3-4 named roles
  • Drenched: Surface IS the color

Read the full file on GitHub · 166 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 166 lines · 93 tokens per session scan A 7c4ca2e81ae7

Subscribe to this mod's changes

concreto is a skill published in the GitHub repository Bigrapb/Concreto (2 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 1,509 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.