agentmods.dev

iron-mcp-framework: Instructions file for Codex

AGENTS.md

iron-mcp-framework AGENTS.md is an instructions file for Codex, OpenCode from julioalberto64/iron-mcp-framework. It costs 426 tokens per session, scanned A, original, MIT.

Repository instructions for agents working on IronMCP, a Node.js and TypeScript framework for creating MCP tools. They explain which local guides to read, where the tool contract lives, and how tools should be checked.

In plain words
What is it for?
Use them when adding or extending an MCP tool in IronMCP. They direct the agent to the relevant skill, types, registry, REST client, tests, and examples.
Why use it?
They give coding agents project-specific rules so changes follow the repository's existing structure and conventions. They also prevent unrelated tasks from loading the tool-building guide.

Instructions file for CodexOpenCode

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

This is julioalberto64/iron-mcp-framework's own configuration. It tells Codex and OpenCode how to work on iron-mcp-framework 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 iron-mcp-framework configures →

not rated 1repo 18d ago A scan 426 tokens original MIT
View source ↗ julioalberto64/iron-mcp-framework
Reuse

Borrowing it

Nothing to install: this file belongs to julioalberto64/iron-mcp-framework. 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/julioalberto64/iron-mcp-framework/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/julioalberto64/iron-mcp-framework

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 iron-mcp-framework AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/julioalberto64/iron-mcp-framework/agents-md/github.svg)](https://agentmods.dev/instructions/julioalberto64/iron-mcp-framework/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/julioalberto64/iron-mcp-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/julioalberto64/iron-mcp-framework/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 iron-mcp-framework AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/julioalberto64/iron-mcp-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/julioalberto64/iron-mcp-framework/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 426 This file is loaded in full into every session.
When invoked 426 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 $0.00426 $0.00426
Opus 5.5 $0.00170 $0.00170
Sonnet 5.5 $0.00085 $0.00085
Haiku 4.5 $0.00043 $0.00043

Measured 17d ago against content hash a5df016dd349, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

iron-mcp-framework 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 17d 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 · 22 lines

What it actually says

Instrucciones para agentes en IronMCP

Este repositorio es un framework Node.js y TypeScript para crear tools MCP. Reutiliza su registro, cliente REST, autenticación, cancelación y transportes existentes.

Skills del repositorio

Cuando el usuario solicite crear, agregar o ampliar una tool MCP en este proyecto, lee esa skill antes de implementar. No hace falta que el usuario mencione su nombre. Si pide el cambio, realiza la implementación y las verificaciones; no te limites a proponer código. Una pregunta explicativa sobre tools no requiere modificar el repositorio.

Los agentes que no descubran skills automáticamente pueden abrir el mismo SKILL.md y seguirlo como guía local. No cargues esta skill para tareas ajenas a las tools.

Contrato y verificaciones

  • El contrato vigente está en src/framework/types.ts; el registro está en src/tools/index.ts mediante createTools().
  • Las tools usan context.restClient y, para otras APIs asíncronas, context.signal. No captures un cliente compartido que eluda la cancelación de cada ejecución.
  • Usa context.logger; stdout está reservado a JSON-RPC en STDIO. Las variables de entorno se leen únicamente en src/framework/config.ts.
  • No copies credenciales ni datos reales de .env o del entorno local de Postman a código, pruebas o ejemplos. Agregar una tool no implica ampliar los permisos de los clientes existentes.
  • Después de cambios de código ejecuta npm run validate, npm run build y npm run knip. Informa cualquier comprobación que no se haya podido ejecutar.

Los commits usan Conventional Commits, por ejemplo feat: add customer lookup tool, sin punto final.

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. 17d ago First seen · 22 lines · 426 tokens per session scan A a5df016dd349

Subscribe to this mod's changes

iron-mcp-framework AGENTS.md is an instructions file published in the GitHub repository julioalberto64/iron-mcp-framework (1 stars, last pushed 18d ago), licensed MIT. It adds 426 tokens to every session, about $0.0017 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 2026-10-20.

Building agents
Related

iron-mcp-framework AGENTS.md compared with instructions from other repositories

iron-mcp-framework AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
iron-mcp-framework AGENTS.mdjulioalberto64/iron-mcp-frameworkInstructions file118d agoMITA426Codex, OpenCode
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
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode