base

base is a command for Claude Code from luanpdd/kit-mcp. It costs 41 tokens per session (1,682 once invoked), scanned A, original, MIT.

A command for maintaining a canonical register of projects, including their names, links, required fields, and local folders.

In plain words
What is it for?
Create, list, add, edit, remove, and validate project records.
Why use it?
It prevents project information from becoming incomplete, inconsistent, or out of date across connected repositories and documents.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

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.

agentmods
npx agentmods add commands/luanpdd/kit-mcp/base
Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

Made for: Claude Code.

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 base

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/base.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/base)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/base"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/base.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,682 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.01682
Opus 5 $0.00020 $0.00841
Sonnet 5 $0.00008 $0.00336
Haiku 4.5 $0.00004 $0.00168

Measured 2d ago against content hash 86f301955b3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

base 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 2d 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.

kit/commands/base.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subcomandos:

  • listar (padrão, sem argumentos): mostra o registro atual com status de completude por projeto (✅ completo / ⚠️ incompleto — qual campo falta).
  • adicionar <nome>: registra um novo projeto (o primeiro vira "Projeto principal"; os demais entram em "Projetos conectados").
  • editar <nome> [campo]: altera campos de um projeto existente.
  • remover <nome>: remove um projeto conectado do registro.
  • init: cria PROJETOS.md do template quando ausente E garante que a regra global existe em ~/.claude/CLAUDE.md (cria se faltar).

Quando usar

  • ✅ Novo projeto na máquina — /base init para criar o registro
  • ✅ Adicionar um projeto conectado (multi-repo, VPS, docs separados) — /base adicionar
  • ✅ Link de repo/docs mudou — /base editar
  • ❌ Editar campos à mão sem validação — o comando valida obrigatórios e formatos

O registro também é consumível em runtime pela MCP tool projects do kit (mcp__kit__projects): list retorna os projetos com status de completude, get busca um projeto pelo nome e doctor gera o relatório de validação (obrigatórios, existência das pastas locais, shape das URLs) — útil quando agents precisam resolver contexto de projetos conectados sem parsear o markdown.

Campo Obrigatório Validação
Pasta local do projeto Caminho absoluto; deve existir no disco
Repositório do projeto URL http(s) da página do repositório
Documentação local Caminho de pasta docs/ ou cofre Obsidian; deve existir
Repositório da documentação URL http(s) ou "—"
Infra / VPS Texto livre ou "—"
Notas Texto livre ou "—"

Read the full file on GitHub · 150 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. 2d ago First seen · 150 lines · 41 tokens per session scan A 86f301955b3c

Subscribe to this mod's changes

base is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 6d ago), licensed MIT. It adds 41 tokens to every session and 1,682 once invoked, about $0.0002 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.