agentmods.dev

MCP_Tools4Foresight: Instructions file for Codex

AGENTS.md

MCP_Tools4Foresight AGENTS.md is an instructions file for Codex, OpenCode from fridaruh/MCP_Tools4Foresight. It costs 523 tokens per session, scanned A, original, MIT.

Repository instructions for agents working on the MCP_Tools4Foresight project. They define rules such as keeping the server read-only, following the documented API, and protecting its JSON-RPC communication.

In plain words
What is it for?
Guiding code changes in this repository, including reading its architecture and API documents, keeping tools exploratory and read-only, adding tests and documentation, and following its domain vocabulary.
Why use it?
They reduce the risk of adding unsupported fields, write operations, broken protocol output, or undocumented tools.

Instructions file for CodexOpenCode

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

This is fridaruh/MCP_Tools4Foresight's own configuration. It tells Codex and OpenCode how to work on MCP_Tools4Foresight 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_Tools4Foresight configures →

not rated 0repo 2mo ago A scan 523 tokens original MIT
View source ↗ fridaruh/MCP_Tools4Foresight mcp-tools4foresight.vercel.app
Reuse

Borrowing it

Nothing to install: this file belongs to fridaruh/MCP_Tools4Foresight. 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/fridaruh/MCP_Tools4Foresight/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/fridaruh/MCP_Tools4Foresight

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_Tools4Foresight AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fridaruh/mcp_tools4foresight/agents-md/github.svg)](https://agentmods.dev/instructions/fridaruh/mcp_tools4foresight/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/fridaruh/mcp_tools4foresight/agents-md"><img src="https://agentmods.dev/badge/instructions/fridaruh/mcp_tools4foresight/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_Tools4Foresight AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/fridaruh/mcp_tools4foresight/agents-md"><img src="https://agentmods.dev/badge/instructions/fridaruh/mcp_tools4foresight/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 523 This file is loaded in full into every session.
When invoked 523 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 $0.00523 $0.00523
Opus 5.5 $0.00209 $0.00209
Sonnet 5.5 $0.00105 $0.00105
Haiku 4.5 $0.00052 $0.00052

Measured 2mo ago against content hash 34ffccae4b3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

MCP_Tools4Foresight 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 · 36 lines

What it actually says

Reglas para agentes que trabajen en este repo

Este es el servidor MCP de solo lectura de tools4foresight. Antes de tocar nada, lee docs/ARCHITECTURE.md y docs/API.md.

Invariantes

  1. Es de SOLO LECTURA y para EXPLORAR. Nunca agregues una tool, un resource o un método de cliente que escriba, modifique o borre algo. Nada de operaciones de administración (publicar, editar análisis, recalcular el grafo): eso vive en tools4foresight. Si una tarea parece pedirlo, pregunta antes. Los prompts son guiones de conversación y no dan capacidades: si agregas uno, que solo encadene tools de lectura.
  2. stdout es el canal JSON-RPC en stdio. Todo log va a stderr. Un console.log rompe el protocolo.
  3. No inventes campos. El contrato es docs/API.md. Si un campo no está ahí, la API no lo devuelve, por muy razonable que suene.
  4. Cero dependencias nuevas sin una razón explícita: solo @modelcontextprotocol/sdk y zod.
  5. Imports internos con extensión .js (moduleResolution: NodeNext).
  6. Toda tool nueva necesita test y una sección en docs/TOOLS.md.

Vocabulario del dominio (no lo traiciones)

  • Una señal es contenido curado guardado como indicio de futuro.
  • Un tema es un linaje que persiste entre corridas; puede morir y resucitar. Un tema muerto es un fósil, no un borrado: se dice "fósil", nunca "eliminado".
  • likedAt es una estimación: se muestra siempre con ~.
  • El porcentaje de similitud no se le muestra a una persona: se usa strength (fuerte/media/débil). El score es para el razonamiento del agente.
  • Los ids de macro-tema no son estables entre corridas.

El glosario completo vive en src/domain/glossary.ts y se rinde en docs/DOMAIN.md. Es la fuente única: no dupliques definiciones.

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 · 36 lines · 523 tokens per session scan A 34ffccae4b3b

Subscribe to this mod's changes

MCP_Tools4Foresight AGENTS.md is an instructions file published in the GitHub repository fridaruh/MCP_Tools4Foresight (0 stars, last pushed 2mo ago), licensed MIT. It adds 523 tokens to every session, about $0.0021 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_Tools4Foresight AGENTS.md compared with instructions from other repositories

MCP_Tools4Foresight AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
MCP_Tools4Foresight AGENTS.mdfridaruh/MCP_Tools4ForesightInstructions file02mo agoMITA523Codex, 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