dados-distribuidos

dados-distribuidos is a command for Claude Code from luanpdd/kit-mcp. It costs 53 tokens per session (3,008 once invoked), scanned A, original, MIT.

A command that creates characterization tests for prompts and other language-model tools in production. These tests record current outputs as snapshots so later changes can be compared with the established behavior.

In plain words
What is it for?
Use it to create baseline tests for production prompts, compare outputs after edits, and detect behavior drift between model versions.
Why use it?
Prompts can change behavior without causing a normal code error. The recorded examples reveal unexpected changes during prompt refactoring or model updates.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Good fit Use it to create baseline tests for production prompts, compare outputs after edits, and detect behavior drift between model versions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/luanpdd/kit-mcp/dados-distribuidos
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.

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 dados-distribuidos

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/dados-distribuidos/github.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/dados-distribuidos)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/dados-distribuidos"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/dados-distribuidos/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 dados-distribuidos

Your own site · 80×15
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/dados-distribuidos"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/dados-distribuidos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,008 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 $0.00053 $0.03008
Opus 5 $0.00026 $0.01504
Sonnet 5 $0.00011 $0.00602
Haiku 4.5 $0.00005 $0.00301

Measured 5d ago against content hash 8a7affe0f50d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dados-distribuidos 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 5d 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/dados-distribuidos.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Suite Invocation Pattern (herdado v1.21): Agents da Suíte DDIA Foundations v1.22 delegam para agents da Suíte Supabase v1.8 + Multi-Tenant v1.21 quando precisam materializar SQL, Edge Functions, RLS policies, audit logs. Padrão canônico:

  • auditor-consistencia-isolamento → delega fix migration para supabase-migration-writer (v1.8) OU fix Edge Function para supabase-edge-fn-writer (v1.8)
  • detector-tenant-quente → delega partitioning/dedicated schema para supabase-migration-writer (v1.8) + b2b-saas-architect (v1.21)
  • validador-evolucao-schema → handoff bidirecional com supabase-migration-writer (v1.8 — invoca este validador ANTES de escrever migration arriscada)
  • Subcomando implementar-cdc → carrega skill streams-eventos-cdc (v1.22) + delega Edge Function CDC para supabase-edge-fn-writer (v1.8)

Cria/Atualiza: o que cada agent invocado cria/atualiza (skills consultadas, audits gerados, vereditos retornados).

Após: o usuário tem o output do agent (audit report, veredito GO/NO-GO, ou Edge Function CDC scaffold).

<execution_context> Skills consultadas pelos agents (Suíte DDIA Foundations v1.22): kit/skills/{evolucao-schema-compativel,consistencia-leitura-replica,tenant-quente-mitigacao,postgres-isolamento-concorrencia,armadilhas-sistemas-distribuidos,escolha-modelo-consistencia,streams-eventos-cdc}/SKILL.md + kit/skills/_shared-dados-distribuidos/glossary.md.

Agents disponíveis (Suíte DDIA Foundations v1.22): kit/agents/{auditor-consistencia-isolamento,detector-tenant-quente,validador-evolucao-schema}.md.

Agents Suíte Supabase v1.8 invocados via cross-suite delegation: supabase-migration-writer, supabase-edge-fn-writer, supabase-architect.

Agents Suíte Multi-Tenant v1.21 invocados via cross-suite delegation: b2b-saas-architect, multi-tenant-rls-writer, audit-log-implementer. </execution_context>

Subcomandos suportados (sinônimos PT-BR/EN):

Subcomando Sinônimos Agent dispatched Skill carregada
auditar-consistencia consistencia, audit-consistency, auditar-race auditor-consistencia-isolamento postgres-isolamento-concorrencia, armadilhas-sistemas-distribuidos, escolha-modelo-consistencia, streams-eventos-cdc
auditar-tenant-quente tenant-quente, hot-tenant, audit-tenant, tenant detector-tenant-quente tenant-quente-mitigacao
validar-evolucao-schema validar-schema, validate-schema, evolution-check, validar-evolucao validador-evolucao-schema evolucao-schema-compativel
implementar-cdc cdc, cdc-pipeline, streams, event-streaming (cross-suite) supabase-edge-fn-writer (v1.8) streams-eventos-cdc (skill v1.22 carregada como contexto)
help ajuda, ? exibe esta tabela inline

Aliases globais para o nome da suíte: dados-distribuidos, ddia, dados, consistencia, replicacao, streams (todos roteiam para este orquestrador via /dados-distribuidos).

Skills relacionadas (Suíte DDIA Foundations v1.22):

Skill Capítulo DDIA Quando usar
evolucao-schema-compativel Ch 4 (Encoding and Evolution) Migrations com ALTER (NOT NULL, DROP, type narrow, default)
consistencia-leitura-replica Ch 5 (Replication) Read replicas Supavisor, read-after-write, monotonic reads
tenant-quente-mitigacao Ch 6 (Partitioning) Multi-tenant skew, hot tenant, partitioning hash(org_id)
postgres-isolamento-concorrencia Ch 7 (Transactions) Lost update, write skew, isolation level Postgres
armadilhas-sistemas-distribuidos Ch 8 (Distributed Systems Trouble) Clock skew, network failure, partial failure
escolha-modelo-consistencia Ch 9 (Consistency and Consensus) Linearizabilidade, causal, eventual; uniqueness; CAP/PACELC
streams-eventos-cdc Ch 11 (Stream Processing) CDC, event sourcing, pgmq exactly-once, stream joins

Read the full file on GitHub · 189 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. 5d ago First seen · 189 lines · 53 tokens per session scan A 8a7affe0f50d

Subscribe to this mod's changes

dados-distribuidos is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 3,008 once invoked, about $0.0003 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.