What is visual-builder?

A tool for turning a supplied image or design document into a reusable visual style without keeping the original brand or subject.

Use it to create style candidates and visual templates from screenshots, posters, knowledge cards, illustrations, or designed interfaces.

It helps separate reusable design patterns from a specific poster, interface, infographic, or illustration.

visual-builder — Skill for Codex by tranfu-labs

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 tranfu-labs/tranfu-skills --skill visual-builder

Clone the repo

git clone --depth 1 https://github.com/tranfu-labs/tranfu-skills

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/visual-builder/github.svg)](https://agentmods.dev/skills/tranfu-labs/tranfu-skills/visual-builder)

Your own site

<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/visual-builder"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/visual-builder/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/visual-builder"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/visual-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,189 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.

Model	Per session	Once invoked
Fable 5.1	$0.00127	$0.04189
Opus 5	$0.00063	$0.02094
Sonnet 5	$0.00025	$0.00838
Haiku 4.5	$0.00013	$0.00419

Measured 9d ago against content hash 2909e133738b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

visual-builder 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 4 executable files (scripts/build-contact-sheet.mjs, scripts/mark-approved.mjs, scripts/validate-candidate.mjs, …), 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.

own-skills/visual-builder/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Builder

Build a reusable style candidate from visual evidence without carrying over its identity or subject. Treat the reference as evidence for visual grammar, never as a generation reference or a source to imitate literally.

Companion Preflight

Run this preflight once at the start of each task, before validating inputs. Set a task-local CompanionContext and never write it into the candidate bundle.

Mark visual-dna-system or post-illustration-images available when the current runtime lists that skill.
For any unresolved skill, check for a readable SKILL.md at ${CODEX_HOME:-$HOME/.codex}/skills/<skill-name>/SKILL.md. Do not search unrelated directories.
When both skills are available, continue silently.
When one or both skills are missing, issue one concise, non-blocking recommendation that lists all and only the missing skills, calls them optional, explains the applicable fallbacks below, and states that the current task will continue. Do not ask the user to choose, do not install automatically, and do not repeat the recommendation in the same task.

Treat this as installation onboarding, independent of the current input_mode or installation intent. Preflight availability means only that a skill was discovered; validate the downstream scripts separately if installation is later requested. A later target-skill-unavailable result is an installation blocker, not a repeated onboarding recommendation.

Use the companions only for these boundaries:

visual-dna-system: preferred upstream extractor for image input. When missing, use the built-in extraction path in Section 1.
post-illustration-images: optional downstream registry and production skill. When missing, complete and approve a portable candidate bundle but do not describe it as installed or production-ready.

Inputs

Require all named inputs before compiling:

input_mode: image or visual-dna.
source: readable image path for image, or JSON/Markdown containing a visual_dna_system object for visual-dna.
target_platform: exactly wechat, xhs, zhihu, weibo, or toutiao; never infer it from the source ratio.
output_root: directory in which to create visual-builder-output/<style_id>/.
Optional overrides before review: style_id, display_name, purpose, aliases, default_use, brand_default_enabled, and make_default. Map purpose only to style.md ## Purpose; map default_use to candidate.style.defaultUse and the registry's defaultUse. Map make_default to optional candidate.style.makeDefault; omit it or use false unless the user explicitly requests this style as the platform default.

Read the full file on GitHub · 262 lines

Files

What ships with it

13 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.

9d ago First seen · 262 lines · 127 tokens per session scan A 2909e133738b

Subscribe to this mod's changes

visual-builder is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 127 tokens to every session and 4,189 once invoked, about $0.0006 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 2026-09-03.

Creative and media Design and UX

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 52 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

make-resume

A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.

Hisn00w/ASu-skills · 86 tokens