Mcp-Wacta: Instructions file for Codex

AGENTS.md

Mcp-Wacta AGENTS.md is an instructions file for Codex, OpenCode from Kanzando/Mcp-Wacta. It costs 1,037 tokens per session, scanned A, original, MIT.

Repository instructions for developers and agents working with Mcp-Wacta, a single-file Node.js server that operates WaCta WordPress administration endpoints.

In plain words
What is it for?
Use them when changing or using this repository to follow its development checks, keep documentation and tests aligned, and avoid unsafe WordPress administration changes.
Why use it?
They explain the project's constraints and required workflow, such as its no-dependency setup, JSON-RPC transport, testing command, and human-confirmation rules.

Instructions file for CodexOpenCode

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

This is Kanzando/Mcp-Wacta's own configuration. It tells Codex and OpenCode how to work on Mcp-Wacta 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 Mcp-Wacta configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Kanzando/Mcp-Wacta. 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/Kanzando/Mcp-Wacta/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Kanzando/Mcp-Wacta

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 Mcp-Wacta AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kanzando/mcp-wacta/agents-md/github.svg)](https://agentmods.dev/instructions/kanzando/mcp-wacta/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kanzando/mcp-wacta/agents-md"><img src="https://agentmods.dev/badge/instructions/kanzando/mcp-wacta/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 Mcp-Wacta AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kanzando/mcp-wacta/agents-md"><img src="https://agentmods.dev/badge/instructions/kanzando/mcp-wacta/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,037 This file is loaded in full into every session.
When invoked 1,037 The same file — it is already loaded in full.
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 $0.01037 $0.01037
Opus 5.5 $0.00415 $0.00415
Sonnet 5.5 $0.00207 $0.00207
Haiku 4.5 $0.00104 $0.00104

Measured 2mo ago against content hash ece135f350da, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Mcp-Wacta AGENTS.md 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 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.

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.

AGENTS.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guía para agentes (Codex y compatibles)

Este repositorio es Mcp-Wacta: un servidor MCP de un solo archivo (server.mjs, Node ≥ 18, sin dependencias) que opera la suite WaCta de WordPress vía sus endpoints REST de administración. Este archivo sigue la convención AGENTS.md: si eres un agente trabajando en este repo o usando sus herramientas, esto es lo que necesitas saber.

Si estás DESARROLLANDO en este repo

  • No hay build ni npm install. La única verificación es node test/smoke.mjs (handshake MCP + inventario de herramientas; no necesita credenciales ni sitio).
  • server.mjs es la única pieza de código. Reglas al tocarlo:
    • Cero dependencias — es un rasgo del proyecto, no una carencia.
    • El transporte es stdio con un objeto JSON-RPC por línea; jamás escribas en stdout nada que no sea un mensaje JSON-RPC (los logs irían a stderr).
    • Al cerrar stdin se drenan las peticiones en vuelo antes de salir — no lo rompas.
    • Toda herramienta nueva debe mapear a un endpoint /admin/* con manage_options de la suite; los endpoints públicos de runtime no se exponen aquí.
    • Actualiza docs/tools.md, la skill y el smoke test en el mismo cambio.

Si estás USANDO las herramientas del servidor (operar WaCta)

Flujo correcto

  1. Lee antes de escribir. Empieza con wacta_status (qué complementos hay, cuántos CTAs, tope del plan) y wacta_get_settings del plugin que vas a tocar.
  2. Cambios mínimos. wacta_update_settings es PATCH: envía SOLO las claves que cambias. Nunca reenvíes el objeto completo de settings.
  3. Verifica después. Vuelve a leer o usa la respuesta (devuelve el estado saneado final) para confirmar que el cambio aplicó como esperabas — los sanitizadores pueden acotar valores.

Pide confirmación humana antes de

  • Encender/apagar superficies públicas: activated (core), tracking_enabled/consent_enabled (analytics), frontend_enabled/portal_enabled (crm), externalMode: "managed" (studio — reescribe botones existentes del sitio).
  • Borrar CTAs (wacta_delete_cta) que muestren actividad en la analítica.
  • Cualquier cambio en un sitio de producción cuando la URL no sea claramente un entorno de desarrollo.

Read the full file on GitHub · 47 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 · 47 lines · 1,037 tokens per session scan A ece135f350da

Subscribe to this mod's changes

Mcp-Wacta AGENTS.md is an instructions file published in the GitHub repository Kanzando/Mcp-Wacta (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,037 tokens to every session, about $0.0041 per session on Opus 5.5. 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

Mcp-Wacta AGENTS.md compared with instructions from other repositories

Mcp-Wacta AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Mcp-Wacta AGENTS.mdKanzando/Mcp-WactaInstructions file03mo agoMITA1,037Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot