ai-dev-skillset: Skill for Claude Code

.agents/skills/workflow-gerenciar-dependencias/SKILL.md

workflow-gerenciar-dependencias is a skill for Claude Code, Codex from gianverdum/ai-dev-skillset. It costs 214 tokens per session (854 once invoked), scanned A, original, MIT.

A project-workflow guide for managing dependencies, development environments, and tools in a declared, repeatable way. Dependencies are external packages or programs that a project needs to run, test, build, or check code.

In plain words
What is it for?
Use it when adding, updating, removing, or running packages and tools for testing, coverage, linting, formatting, building, runtimes, or other development tasks.
Why use it?
It reduces setup differences between developers and avoids relying on globally installed tools. It also keeps project manifests and lockfiles aligned with the chosen technology stack.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is gianverdum/ai-dev-skillset's own configuration. It tells Claude Code and Codex how to work on ai-dev-skillset itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-dev-skillset configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gianverdum/ai-dev-skillset. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gianverdum/ai-dev-skillset/main/.agents/skills/workflow-gerenciar-dependencias/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gianverdum/ai-dev-skillset

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 workflow-gerenciar-dependencias

README.md
[![agentmods](https://agentmods.dev/badge/skills/gianverdum/ai-dev-skillset/workflow-gerenciar-dependencias/github.svg)](https://agentmods.dev/skills/gianverdum/ai-dev-skillset/workflow-gerenciar-dependencias)
Your own site
<a href="https://agentmods.dev/skills/gianverdum/ai-dev-skillset/workflow-gerenciar-dependencias"><img src="https://agentmods.dev/badge/skills/gianverdum/ai-dev-skillset/workflow-gerenciar-dependencias/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 workflow-gerenciar-dependencias

Your own site · 80×15
<a href="https://agentmods.dev/skills/gianverdum/ai-dev-skillset/workflow-gerenciar-dependencias"><img src="https://agentmods.dev/badge/skills/gianverdum/ai-dev-skillset/workflow-gerenciar-dependencias.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 214 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 854 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 $0.00214 $0.00854
Opus 5 $0.00107 $0.00427
Sonnet 5 $0.00043 $0.00171
Haiku 4.5 $0.00021 $0.00085

Measured 12d ago against content hash b0f2454cfdac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

workflow-gerenciar-dependencias 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.

.agents/skills/workflow-gerenciar-dependencias/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gerenciar Dependências

Use esta skill quando uma tarefa exigir dependência, ferramenta ou ambiente que ainda não esteja configurado no projeto.

Regras

  • Declare dependências no manifesto da stack e mantenha o lockfile quando a ferramenta gerar um.
  • Prefira dependências de desenvolvimento para ferramentas de teste, cobertura, lint, formatação, build e automação local.
  • Execute comandos pelo ambiente do projeto, não por instalações globais.
  • Não trate dependência ausente como bloqueio antes de tentar configurá-la no projeto ou antes de identificar um bloqueio externo real.
  • Não misture gerenciadores de dependência na mesma stack sem padrão existente que justifique isso.
  • Quando criar ou reorganizar manifests, lockfiles, scripts ou estrutura de ambiente, siga o padrão local ou a rule da linguagem em .agents/rules.

Python

  • Use sempre uv.
  • Crie ou atualize pyproject.toml quando o projeto Python ainda não tiver manifesto.
  • Em projeto Python novo, declare metadados mínimos, requires-python, scripts de CLI quando existirem e configuração das ferramentas no pyproject.toml. Use o template mínimo definido na rule naming-structure-python em .agents/rules/naming-structure-python.md como base; ele já cobre estrutura, entrypoint, dependency-groups para dev e configuração de cobertura.
  • Adicione dependências de runtime com uv add <pacote>.
  • Adicione ferramentas de desenvolvimento com uv add --dev <pacote>.
  • Execute aplicações e validações com uv run <comando>.
  • Mantenha uv.lock quando ele for criado ou alterado.
  • Mantenha .venv/, .coverage, caches e bytecode fora do versionamento por .gitignore.
  • Não use pip install, python -m venv, virtualenv, requirements.txt novo ou instalação global, salvo quando um projeto existente já exigir esse padrão e a razão for registrada.

Fluxo

  1. Identifique a stack e o gerenciador já usado pelo projeto.
  2. Consulte a rule da linguagem quando precisar definir estrutura de manifesto, scripts ou lockfile sem padrão local.
  3. Se for Python, use uv mesmo em projetos pequenos.
  4. Adicione a dependência no grupo correto: runtime ou desenvolvimento.
  5. Atualize comandos e documentação para usar o ambiente do projeto.
  6. Execute a validação que depende da ferramenta instalada.
  7. Se a instalação exigir rede, autenticação ou permissão externa, solicite aprovação ou informe o bloqueio concreto.

Read the full file on GitHub · 50 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 · 50 lines · 0 tokens per session scan A b0f2454cfdac

Subscribe to this mod's changes

workflow-gerenciar-dependencias is a skill published in the GitHub repository gianverdum/ai-dev-skillset (5 stars, last pushed 2mo ago), licensed MIT. It adds 214 tokens to every session and 854 once invoked, about $0.0011 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens