agentmods.dev

google-connector: Instructions file for Codex

AGENTS.md

google-connector AGENTS.md is an instructions file for Codex, OpenCode from kevinbkt10/google-connector. It costs 1,128 tokens per session, scanned A, original, MIT.

A set of instructions for deploying and operating a Google Connector, a service that links Google APIs such as YouTube and Search Console to a Cloudflare Worker.

In plain words
What is it for?
Setting up OAuth, deploying the connector to Cloudflare, connecting Google services, and preparing its API for use.
Why use it?
It lays out the required accounts, credentials, database setup, secrets, and deployment checks so the connector is configured safely.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is kevinbkt10/google-connector's own configuration. It tells Codex and OpenCode how to work on google-connector 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 google-connector configures →

not rated 5repo 3mo ago A scan 1,128 tokens original MIT
View source ↗ kevinbkt10/google-connector kevinbk.com
Reuse

Borrowing it

Nothing to install: this file belongs to kevinbkt10/google-connector. 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/kevinbkt10/google-connector/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/kevinbkt10/google-connector

Made for: Codex, OpenCode.

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 google-connector AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kevinbkt10/google-connector/agents-md/github.svg)](https://agentmods.dev/instructions/kevinbkt10/google-connector/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kevinbkt10/google-connector/agents-md"><img src="https://agentmods.dev/badge/instructions/kevinbkt10/google-connector/agents-md/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 google-connector AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kevinbkt10/google-connector/agents-md"><img src="https://agentmods.dev/badge/instructions/kevinbkt10/google-connector/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,128 This file is loaded in full into every session.
When invoked 1,128 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01128 $0.01128
Opus 5.5 $0.00451 $0.00451
Sonnet 5.5 $0.00226 $0.00226
Haiku 4.5 $0.00113 $0.00113

Measured 2mo ago against content hash fb7413adb0f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

google-connector AGENTS.md scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Exemplo de `curl` no `/runtime` com ADMIN_API_TOKEN
AGENTS.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Google Connector

Instruções para a IA instalar, publicar e operar este conector.

Objetivo do usuário

Baixou este template. Quer o Worker na Cloudflare dele, com as credenciais dele, e depois usar a API daqui (mesmo chat/projeto) para YouTube, Search Console, etc.

Regras

  1. JavaScript puro no Worker — sem React, Vue, Express ou libs de UI.
  2. Não invente Client ID, secrets ou database_id. Peça ou leia o que o usuário fornecer.
  3. Não copie credenciais de outros projetos/repos.
  4. Textos da UI em português com acentuação.
  5. Produto: Google Connector.
  6. Preferência: deploy em produção após configurar.

Fluxo em um pedido (“um clique” com a IA)

Quando o usuário pedir para publicar:

  1. Confirmar se tem conta Cloudflare e se npx wrangler login já foi feito (ou rodar).
  2. Confirmar se tem projeto Google Cloud + OAuth Web + Client ID/Secret (ou guiar a criação).
  3. npx wrangler d1 create google-services-connector → colar database_id no wrangler.jsonc.
  4. Preencher GOOGLE_CLIENT_ID e APP_BASE_URL (placeholder até o primeiro deploy, depois ajustar).
  5. Aplicar schema.sql no D1 remoto.
  6. Configurar secrets (gerar strings longas se o usuário não tiver):
    • GOOGLE_CLIENT_SECRET
    • STATE_SIGNING_SECRET
    • ACCOUNT_ENCRYPTION_SECRET
    • ADMIN_API_TOKEN
    • CONNECT_TOKEN
  7. npx wrangler deploy
  8. Atualizar APP_BASE_URL se a URL final for diferente + redeploy.
  9. Lembrar o usuário de cadastrar APP_BASE_URL/callback no Google Cloud.
  10. Entregar:
    • URL do site
    • URL do painel
    • Que ele use o CONNECT_TOKEN para entrar
    • Exemplo de curl no /runtime com ADMIN_API_TOKEN
    • Snippet .env para o projeto

Instalação (comandos)

npx wrangler login
npx wrangler d1 create google-services-connector
# editar wrangler.jsonc: database_id, GOOGLE_CLIENT_ID, APP_BASE_URL

npx wrangler d1 execute google-services-connector --remote --file=schema.sql
npx wrangler secret put GOOGLE_CLIENT_SECRET
npx wrangler secret put STATE_SIGNING_SECRET
npx wrangler secret put ACCOUNT_ENCRYPTION_SECRET
npx wrangler secret put ADMIN_API_TOKEN
npx wrangler secret put CONNECT_TOKEN
npx wrangler deploy

Read the full file on GitHub · 128 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. 2mo ago First seen · 128 lines · 1,128 tokens per session scan A fb7413adb0f7

Subscribe to this mod's changes

google-connector AGENTS.md is an instructions file published in the GitHub repository kevinbkt10/google-connector (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,128 tokens to every session, about $0.0045 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIsCloudDevOps and cloud
Related

google-connector AGENTS.md compared with instructions from other repositories

google-connector AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
google-connector AGENTS.mdkevinbkt10/google-connectorInstructions file53mo agoMITA1,128Codex, OpenCode
plan-forge dapr.instructions.mdsrnichols/plan-forgeInstructions file62d agoMITA4,975GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot