evolution-go-integrator

evolution-go-integrator is an agent for coding agents from luanpdd/kit-mcp. It costs 53 tokens per session (2,465 once invoked), scanned A, original, MIT.

An integration agent for connecting WhatsApp to a multi-tenant B2B application through Evolution Go or Meta Cloud API. It creates message storage, a webhook, and an optional send queue in Supabase.

In plain words
What is it for?
Use it to set up WhatsApp configuration and message tables, receive webhooks through an Edge Function, and optionally add queued sending and conversation state management.
Why use it?
It organizes incoming and outgoing WhatsApp messages across customer organizations and can separate sending work from the immediate request.

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/evolution-go-integrator
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 evolution-go-integrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/evolution-go-integrator.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/evolution-go-integrator)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/evolution-go-integrator"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/evolution-go-integrator.svg" alt="Measured on agentmods" 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 2,465 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 $0.00053 $0.02465
Opus 5 $0.00026 $0.01233
Sonnet 5 $0.00011 $0.00493
Haiku 4.5 $0.00005 $0.00247

Measured 3d ago against content hash f557d82b8e7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolution-go-integrator 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/evolution-go-integrator.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o evolution-go-integrator. Materializa integração completa WhatsApp em B2B multi-tenant — tabelas org_whatsapp_configs + whatsapp_messages, webhook handler Edge Function, send queue + worker. Lê skills evolution-go-whatsapp-integration + whatsapp-conversation-state-machine. Delega Edge Function code para supabase-edge-fn-writer.

Inputs

  • (Opcional) provider: meta_cloud (Meta Cloud API oficial) | evolution_go (whatsmeow não-oficial)
  • (Opcional) enable_send_queue: true (default — pgmq + worker) | false (sync send, sem rate limit guard)
  • (Opcional) enable_state_machine: true (default — xstate conversation) | false (só persist messages, sem state)

Passos

Step 0 — Preflight

  • MCP detection
  • Validar Phase 106 (organizations, organization_members)
  • Validar Phase 109 (audit_logs + audit_log function)
  • Validar pgmq extension habilitada (se enable_send_queue=true)
  • ABORT se HMAC validation aplicada APÓS JSON.parse — REGRA #1 da skill (este check é pre-design, agent reforça no brief)

Step 1 — Provider via AskUserQuestion (se ausente)

- Meta Cloud API (Recomendado para production) — oficial Meta, custo por conversation, rate limit 80 msg/s, HMAC-SHA256 signature
- Evolution Go (free/self-hosted) — whatsmeow library, sem custo Meta, throttle manual 1 msg/s, API key + IP whitelist (não HMAC)
- Ambos (multi-provider) — cada org escolhe via org_whatsapp_configs.provider

Step 2 — Migration brief para supabase-migration-writer

[Migration brief — evolution-go-integrator]

Tabelas:
1. public.org_whatsapp_configs (DDL completo skill section "Tabela org_whatsapp_configs")
2. public.whatsapp_messages (DDL completo com unique(org_id, message_id) — REGRA #4 idempotency)
3. (se enable_state_machine=true) public.conversations (DDL skill conversation-state-machine)
4. (se enable_send_queue=true) pgmq queue creation: select pgmq.create('whatsapp_outbound_global');

RLS standard multi-tenant para todas (members + super_admin bypass).

(se enable_send_queue=true) pg_cron worker schedule:
select cron.schedule('whatsapp-send-worker', '* * * * *', $$ select net.http_post(...) $$);
-- worker chama Edge Function whatsapp-send-worker que processa N msgs respeitando 80 msg/s

(se enable_state_machine=true) pg_cron timeout 24h:
select cron.schedule('conversation-timeout-24h', '*/30 * * * *', $$
  update public.conversations set state = 'abandoned'
  where state = 'waiting_user_reply' and last_message_at < now() - interval '24 hours';
$$);

Read the full file on GitHub · 208 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 · 208 lines · 53 tokens per session scan A f557d82b8e7c

Subscribe to this mod's changes

evolution-go-integrator is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 2,465 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 2026-08-31.

Related

Other agents, from other repositories

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

artisan-specialist

Database specialist for Laravel, runs in the "database" extra phase after development. Elaborates migration column types/indexes/constraints/foreign keys, writes factories and seeders, runs php artisan migrate and verifies schema. Do NOT use for: application logic (laravel-architect), tests (qa-engineer), optimization…

AratKruglik/claude-sdlc · 80 tokens

go-error-reviewer

Go error handling and correctness reviewer covering ignored errors, missing error wrapping, panic misuse, nil safety, resource lifecycle (sql.Rows, resp.Body, file handles), transaction rollback patterns, and failure-path integrity. Use when Go code changes contain error returns, panic calls, sql.Rows, tx.Begin, HTTP…

johnqtcg/awesome-skills · 97 tokens

tadpole-backend-specialist

Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.

DDS-Solutions/AI-TadPole-OS · 45 tokens

go-arch-auditor

Dispatch when a Go service needs a clean-architecture audit. Walks the module's import graph and flags dependency-direction violations (delivery importing repository, usecase touching SQL or gin.Context), framework leaks into the domain, and ORM types crossing layer boundaries — with file:line citations and a refactor…

muratmirgun/gophers · 88 tokens

agentic-coding-deployment-verification-agent

Produces Go/No-Go deployment checklists with SQL verification queries, rollback procedures, and monitoring plans. Use when PRs touch production data, migrations, or risky data changes.

DolphinAI2026/dolphin-code · 45 tokens