build-and-look

build-and-look is a skill for Claude Code, Codex from AkshitIreddy/agent-skills. It costs 57 tokens per session (665 once invoked), scanned A, original, MIT.

A visual-work practice for coding agents: build a small real version, inspect the result, then make focused changes. It also recommends creating several design variations and comparing them.

In plain words
What is it for?
Use it for interfaces, artwork, animations, sound, layouts, and colour choices. It guides the agent to render, inspect, identify a concrete problem, and iterate.
Why use it?
It avoids spending too long guessing whether a visual or audio result will work before anything exists. Comparing actual outputs makes aesthetic problems easier to spot.

Skill for Claude CodeCodex

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

Good fit Use it for interfaces, artwork, animations, sound, layouts, and colour choices. It guides the agent to render, inspect, identify a concrete problem, and iterate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akshitireddy/agent-skills/build-and-look
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 AkshitIreddy/agent-skills --skill build-and-look
Clone the repo
git clone --depth 1 https://github.com/AkshitIreddy/agent-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 build-and-look

README.md
[![agentmods](https://agentmods.dev/badge/skills/akshitireddy/agent-skills/build-and-look/github.svg)](https://agentmods.dev/skills/akshitireddy/agent-skills/build-and-look)
Your own site
<a href="https://agentmods.dev/skills/akshitireddy/agent-skills/build-and-look"><img src="https://agentmods.dev/badge/skills/akshitireddy/agent-skills/build-and-look/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 build-and-look

Your own site · 80×15
<a href="https://agentmods.dev/skills/akshitireddy/agent-skills/build-and-look"><img src="https://agentmods.dev/badge/skills/akshitireddy/agent-skills/build-and-look.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 665 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 $0.00057 $0.00665
Opus 5 $0.00028 $0.00332
Sonnet 5 $0.00011 $0.00133
Haiku 4.5 $0.00006 $0.00067

Measured 12d ago against content hash 0f706219bc5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

build-and-look 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 12d 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.

skills/build-and-look/SKILL.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.

Build it, look at it, try another

For anything you can see or hear, judgement beats prediction. You cannot reason your way to "does this look good" — you can only look. Long deliberation before the first render is usually wasted: the answer only appears once something exists.

If you have been thinking for a while without producing an artifact, stop and build the crudest version now.

The loop

  1. Build the smallest real thing — not a plan, an artifact you can render.
  2. Look at it. Screenshot it, read the image, play the sound, watch the animation.
  3. Name what is wrong in concrete terms ("values are all mid-tone", "the easing lands too abruptly").
  4. Change one thing and look again.

Three rounds of this beat an hour of reasoning, every time.

Try variations in parallel, not in sequence

When a choice is aesthetic, do not agonise over which option is best — make several and compare them side by side. Render 4–8 variants into a single contact sheet: different palettes, spacings, easing curves, densities, light angles. Looking at them together makes the answer obvious in seconds, and often reveals a better option you would not have reasoned your way to.

This is cheap. A variant is usually a parameter change and a re-render. Generate generously.

Do not reduce motion to stills

Still frames are excellent for composition and poor proof of temporal correctness. A transition can look perfect at every chosen checkpoint and still flicker between them, reorder layers for one frame, or pop on commit. For motion, watch the real interaction repeatedly at normal and rapid input, then inspect the code's preparation/ownership/commit order. Treat automated captures as aids; a repeatable human observation on the real app wins over a headless non-reproduction.

Bias to action

  • Prototype before specifying. A rough render answers questions a document cannot.
  • When stuck between two approaches, build both crudely rather than debating.
  • When a change is reversible and quick, just try it.
  • Keep the feedback loop short: one harness you can re-run in seconds beats an elaborate pipeline.
  • Do not polish an approach you have not yet validated visually.

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. 12d ago First seen · 54 lines · 57 tokens per session scan A 0f706219bc5d

Subscribe to this mod's changes

build-and-look is a skill published in the GitHub repository AkshitIreddy/agent-skills (1 stars, last pushed 15d ago), licensed MIT. It adds 57 tokens to every session and 665 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

openai-frontend-design

Use for new frontend applications, dashboards, games, creative websites, hero sections, and visually driven UI from scratch, or when the user explicitly asks for a redesign/restyle/modernization. Builds from clean, airy, high-taste, readable image-generated concept design with section-specific references, faithful…

fcakyon/claude-codex-settings · 71 tokens

ultralytics-branding

This skill should be used when creating Ultralytics-branded content of any kind, including PDF, PPTX, Canva, or Google Slides presentations, DOCX documents, marketing or newsletter HTML emails, social media post copy or visuals, website or landing page designs, and dataset or model result visuals. Provides official…

fcakyon/claude-codex-settings · 90 tokens

lov-maintain-partners

Maintain the Skill Publisher website's partners section AND align partner logo rows on event posters / hero strips: reuse lov-find-logo for brand logo discovery, normalize collected logos to a 240px-tall content canvas (retina-ready), rasterize SVGs via rsvg-convert before normalizing (so SVG viewBox padding gets…

lovstudio/skills · 294 tokens

lov-mobile-infographic

A mobile infographic maker that turns existing conclusions, research, or conversation content into a tall, phone-readable card. It delivers editable HTML and a PNG image.

lovstudio/skills · 111 tokens

lov-gen-logo

A logo and application-icon design workflow that creates distinct, versioned drafts and keeps brand marks separate from app icons. It also prepares selected assets for their intended uses, such as websites or device screens.

lovstudio/skills · 41 tokens

lov-professional-portrait

Turn a single-person photo into a polished professional portrait while preserving the person's identity. Use restrained skin retouching, exposure cleanup, optional hat removal and hairstyle reconstruction, background polish, and an explicit quality gate. Trigger when the user asks for a professional headshot, business…

lovstudio/skills · 139 tokens