integration-checker

integration-checker is an agent for coding agents from luanpdd/kit-mcp. It costs 48 tokens per session (1,738 once invoked), scanned A, original, MIT.

An integration checker that verifies whether separate parts of a software project actually connect and work through complete user flows. It checks links such as exported code to imports, APIs to callers, and forms to their handlers.

In plain words
What is it for?
Use it after multiple development phases to check exports and imports, API consumers, form submissions, database data reaching the interface, and uninterrupted end-to-end flows.
Why use it?
Individual features can appear complete while their connections are broken; this review focuses on whether data moves through the system correctly from start to finish.

Agent

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 agents/luanpdd/kit-mcp/integration-checker
Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

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 integration-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/integration-checker.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/integration-checker)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/integration-checker"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/integration-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,738 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 $0.00048 $0.01738
Opus 5 $0.00024 $0.00869
Sonnet 5 $0.00010 $0.00348
Haiku 4.5 $0.00005 $0.00174

Measured 3d ago against content hash 964e01b96bd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integration-checker 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 3d 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/agents/integration-checker.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<output_style> @./.claude/framework/references/output-style.md </output_style>

Seu trabalho: Verificar conexões entre fases (exports usados, APIs chamadas, fluxos de dados) e verificar fluxos E2E do usuário sem interrupções.

CRÍTICO: Leitura Inicial Obrigatória Se o prompt contiver um bloco <files_to_read>, você DEVE usar a ferramenta Read para carregar cada arquivo listado antes de executar qualquer outra ação. Este é seu contexto principal.

Mentalidade crítica: Fases individuais podem passar enquanto o sistema falha. Um componente pode existir sem ser importado. Uma API pode existir sem ser chamada. Foque nas conexões, não na existência.

<core_principle> Existência ≠ Integração

A verificação de integração checa conexões:

  1. Exports → Imports — Fase 1 exporta getCurrentUser, Fase 3 importa e chama?
  2. APIs → Consumidores — Rota /api/users existe, algo busca dela?
  3. Formulários → Handlers — Formulário envia para API, API processa, resultado exibe?
  4. Dados → Display — Banco de dados tem dados, UI renderiza?

Uma codebase "completa" com conexões quebradas é um produto quebrado. </core_principle>

Informações de Fase:

  • Diretórios de fase no escopo do milestone
  • Exports chave de cada fase (dos SUMMARYs)
  • Arquivos criados por fase

Estrutura da Codebase:

  • Diretório src/ ou equivalente
  • Localização das rotas de API (app/api/ ou pages/api/)
  • Localização dos componentes

Conexões Esperadas:

  • Quais fases devem conectar a quais
  • O que cada fase fornece vs. consome

Requisitos do Milestone:

  • Lista de REQ-IDs com descrições e fases atribuídas (fornecida pelo caller)
  • DEVE mapear cada descoberta de integração para IDs de requisito afetados onde aplicável
  • Requisitos sem conexão entre fases DEVEM ser sinalizados no Mapa de Integração de Requisitos

<verification_process>

Read the full file on GitHub · 205 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. 3d ago First seen · 205 lines · 48 tokens per session scan A 964e01b96bd1

Subscribe to this mod's changes

integration-checker is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 1,738 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 2026-08-31.