visual-consistency

visual-consistency is a skill for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 84 tokens per session (964 once invoked), scanned A, original, Apache-2.0.

A process for keeping AI-generated images in the same visual style across a campaign by fixing the model, base prompt, seed, and style references.

In plain words
What is it for?
Use it to create a consistent set of campaign images with matching visual treatment while changing the subject or scene.
Why use it?
AI image generators treat each request independently, so images made without shared settings can look like they belong to different brands.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pwdev-social-media plugin — 19 skills, 5 commands, 4 agents shipped together

Good fit Use it to create a consistent set of campaign images with matching visual treatment while changing the subject or scene.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pwdev-solucoes/pwdev-claude-marketplace/visual-consistency
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 pwdev-solucoes/pwdev-claude-marketplace --skill visual-consistency
Clone the repo
git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

Made for: Claude Code.

Or install pwdev-social-media, the plugin that ships this one along with the rest of its 19 skills, 5 commands, 4 agents.

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 visual-consistency

README.md
[![agentmods](https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/visual-consistency/github.svg)](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/visual-consistency)
Your own site
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/visual-consistency"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/visual-consistency/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 visual-consistency

Your own site · 80×15
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/visual-consistency"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/visual-consistency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 964 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 $0.00084 $0.00964
Opus 5 $0.00042 $0.00482
Sonnet 5 $0.00017 $0.00193
Haiku 4.5 $0.00008 $0.00096

Measured 6d ago against content hash 8c055522f5d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

visual-consistency 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 6d 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.

plugins/pwdev-social-media/skills/visual-consistency/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consistência Visual

Você resolve o defeito estrutural da geração por IA: cada chamada é independente, e o modelo não lembra da peça anterior.

Princípio central

O gerador não tem memória. A consistência não vem do modelo — vem do processo que você impõe a ele.

Campanha com dez imagens que parecem de dez marcas diferentes é o resultado padrão de quem gera sem sistema. É também o motivo mais comum de refação paga.

As 4 âncoras

Aplique todas. Cada uma sozinha é insuficiente.

1. Modelo fixo

Escolha um modelo e não troque no meio da campanha. Modelos diferentes têm estética diferente, por melhor que seja o prompt.

Registre na seção 6 do contexto: ferramenta, modelo, versão.

2. Prompt base

Construa um bloco fixo que entra em todas as peças:

BASE (não alterar durante a campanha):
  estilo:      fotografia documental, luz natural difusa
  paleta:      verde-azulado dessaturado, alto contraste
  enquadramento: plano médio, altura dos olhos
  tratamento:  sem filtro, sem vinheta

VARIÁVEL (muda por peça):
  sujeito:     {{o que muda}}
  ambiente:    {{o que muda}}

Só o bloco variável muda. Alterar a base no meio quebra a campanha inteira.

3. Seed

Ao acertar uma peça, registre a seed. Para gerar variação daquela imagem, reutilize a seed e mude só o sujeito.

Seed perdida significa peça irreproduzível. Grave no manifesto, sempre.

4. Referência de estilo

Quando a ferramenta suportar (Leonardo é a mais forte nisso), suba uma peça aprovada como referência e ancore as demais nela.

Teste de coerência

Antes de aprovar o conjunto, coloque todas as peças lado a lado. Não avalie uma por uma — o defeito de consistência só aparece na comparação.

Eixo Pergunta
Paleta as cores convivem, ou uma destoa?
Luz a direção e a temperatura batem?
Enquadramento a distância do sujeito é parecida?
Tratamento mesma textura, mesmo contraste, mesmo grão?
Época/estilo parecem do mesmo ensaio?

Read the full file on GitHub · 119 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. 6d ago First seen · 119 lines · 84 tokens per session scan A 8c055522f5d4

Subscribe to this mod's changes

visual-consistency is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 84 tokens to every session and 964 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

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

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 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

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens