cost-control

cost-control is a skill for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 76 tokens per session (937 once invoked), scanned A, original, Apache-2.0.

A cost-control workflow for paid image generators that checks whether an asset needs generation, estimates the number of calls, and tracks expected adjustments.

In plain words
What is it for?
It helps plan image-generation batches, estimate usage, and decide which campaign assets should be generated.
Why use it?
It prevents unnecessary generation costs by reusing existing photos, vectors, or simple compositions when possible.

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 It helps plan image-generation batches, estimate usage, and decide which campaign assets should be generated.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pwdev-solucoes/pwdev-claude-marketplace/cost-control
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 cost-control
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 cost-control

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/cost-control"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/cost-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 937 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 $0.00076 $0.00937
Opus 5 $0.00038 $0.00468
Sonnet 5 $0.00015 $0.00187
Haiku 4.5 $0.00008 $0.00094

Measured 7d ago against content hash 2a8ec5364595, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cost-control 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 7d 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/cost-control/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Controle de Custo

Você protege o orçamento de quem paga a conta. Cada chamada tem preço.

Princípio central

A geração mais barata é a que não acontece. Antes de estimar custo, verifique se o ativo precisa mesmo ser gerado.

Boa parte do criativo de marca é tipografia sobre cor sólida ou sobre foto que já existe. Isso é composição — Figma resolve na hora, de graça.

Antes de qualquer lote

1. Triagem

Para cada ativo da tabela do conceito:

Pergunta Se sim
É texto sobre fundo liso? não gere — Figma
Já existe foto no acervo? não gere — use
Existe vetor no design system? não gere — use
Dá para fotografar? avalie: foto real costuma sair melhor e mais barata
É fundo, textura ou abstração? gere
É cena que não existe e não dá para fotografar? gere

Reporte quantos ativos foram eliminados na triagem. É o número que mais impressiona e o mais fácil de conseguir.

2. Estimativa

Apresente em chamadas e variações, nunca em reais inventados:

Ativos a gerar:     4
Variações por ativo: 2 (primeira rodada)
Chamadas previstas:  8
Rodadas de ajuste esperadas: 1-2
Total provável:      12-16 chamadas

Vídeo:               1 clipe de 5s  ← item mais caro, por larga margem
Upscale:             0

Ferramenta: {{qual}} · Consulte o preço unitário no painel

Não invente preço em reais. Preço muda e número errado aqui vira decisão errada lá. Entregue a contagem; o preço unitário é do painel da ferramenta.

3. Confirmação

Espere aprovação explícita. Nunca gere "para mostrar como ficaria". Nunca gere lote sem autorização do lote inteiro.

Os scripts exigem --confirm como segunda barreira — mas a barreira que importa é a conversa antes.

Regra das 2 variações

Primeira rodada: 2 variações por ativo, sempre. Não 8.

Com 2 você já diagnostica se o prompt está na direção certa. Gerar 8 de um prompt errado é pagar oito vezes pelo mesmo erro.

Só gere volume depois que seed e modelo estiverem fixados.

Read the full file on GitHub · 114 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. 7d ago First seen · 114 lines · 76 tokens per session scan A 2a8ec5364595

Subscribe to this mod's changes

cost-control is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 76 tokens to every session and 937 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

kanban-video-orchestrator

Plan and run multi-agent video production pipelines.

NousResearch/hermes-agent · 16 tokens

html-ppt-knowledge-arch-blueprint

OpenDesign's incident retro: the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups. Built as a decision-grade product management deck for engineering, SRE, leadership.

nexu-io/open-design · 52 tokens

vidseeds-projects

Use for VidSeeds MCP project workflows - create a project from YouTube, list/get/snapshot, regenerate metadata (sync or async), translate metadata, apply thumbnails, and update per-platform config before publish.

hashgraph-online/awesome-codex-plugins · 47 tokens

n8n-photo-report

Automate construction photo report generation using n8n with AI-powered image analysis.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 22 tokens

manage-storyboard-projects

Create, find, inspect, update, or delete Codex Storyboard projects directly through MCP. Use when the user asks Codex to write a new video script or storyboard into the local storyboard app, add or revise shots, rename a project, change its aspect ratio, find an existing project, or delete one without browser…

Yuuhann1999/codex-storyboard · 72 tokens

client-revisions

This skill should be used when the user asks to "stop scope creep", "limit revision rounds", "write SOW revision language", "the client keeps asking for changes", "how do I say this is out of scope", "translate vague feedback", "client said make it pop", or "write a change-order email". It provides revision-cap…

2233admin/design-pipeline · 96 tokens