agentmods.dev

project-template: Instructions file for Codex

AGENTS.md

project-template AGENTS.md is an instructions file for Codex, OpenCode from polmarza/project-template. It costs 3,297 tokens per session, scanned C, original, MIT.

A set of instructions for coding agents working in a project-template repository. It tells agents how to inspect project documents, initialise an unfinished project, follow repository skills, and handle work already in progress.

In plain words
What is it for?
Use it as the operating guide for AI coding agents working on this repository, especially during project setup, feature work, and continuation of unfinished tasks.
Why use it?
It prevents an agent from changing code before understanding the project state and its required procedures. It also points the agent to the right documentation and task-specific instructions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is polmarza/project-template's own configuration. It tells Codex and OpenCode how to work on project-template 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 project-template configures →

not rated 89repo +1 15d ago C scan 3,297 tokens original MIT
View source ↗ polmarza/project-template
Reuse

Borrowing it

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

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 project-template AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/polmarza/project-template/agents-md"><img src="https://agentmods.dev/badge/instructions/polmarza/project-template/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,297 This file is loaded in full into every session.
When invoked 3,297 The same file — it is already loaded in full.
Security scan C 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 $0.03297 $0.03297
Opus 5.5 $0.01319 $0.01319
Sonnet 5.5 $0.00659 $0.00659
Haiku 4.5 $0.00330 $0.00330

Measured 14d ago against content hash d97853db5cc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

project-template AGENTS.md scanned grade C 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 14d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Lista de antipatrones específicos de este proyecto. Ejemplo: - No modificar el esquema de Supabase directamente desde el cliente; usar migraciones. - No almacenar tokens en localStorage; usar cookies httpOnly. - No
AGENTS.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Archivo de referencia para cualquier agente de codificación que trabaje en este proyecto (Claude Code, Codex, Cursor, Copilot…). Lee este archivo completo antes de hacer cualquier cambio. Claude Code lo carga a través de CLAUDE.md, que solo añade lo específico de esa herramienta.

Los procedimientos viven como skills en .claude/skills/<nombre>/SKILL.md. Cuando este archivo dice "carga /feature", en Claude Code se lanza con /feature; con otro agente, abre .claude/skills/feature/SKILL.md y síguelo entero.

Estado del proyecto y arranque

Antes de hacer cualquier cosa, comprueba el estado del repositorio:

  1. Lee todos los archivos de docs/.
  2. Si existe .template/, o si los documentos están vacíos o solo tienen comentarios, el proyecto no está inicializado. No escribas código ni rellenes nada por tu cuenta: carga /init-proyecto y síguela. Si había contenido y .template/ sigue ahí, la inicialización quedó a medias: avisa al usuario y ofrécete a completarla.
  3. Mira docs/features/. Si hay alguna ficha en estado En construcción, ahí está el trabajo a medias: léela antes de proponer nada nuevo.

Si algo no cuadra (falta configuración, los tests no arrancan, hay fichas colgadas), /diagnostico da el parte completo del estado del proyecto y del entorno.

Documentación

docs/ tiene ocho archivos, pero no todos los proyectos necesitan los ocho; qué documentos aplican según el tamaño y en qué orden se rellenan está en /documentacion.

  • prd.md y architecture.md no se saltan nunca.
  • Un documento que no aplique se borra, no se deja vacío: un archivo con solo comentarios es indistinguible de uno que se olvidó rellenar. Si falta uno en docs/, comprueba antes en /documentacion si es deliberado.
  • Si el proyecto crece (un sitio pequeño que gana cuentas de usuario), crea los documentos que faltan en ese momento, no al final.

docs/features/ es aparte: no describe el proyecto, sino cada unidad de trabajo acordada.

Read the full file on GitHub · 277 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. 14d ago First seen · 277 lines · 3,297 tokens per session scan C d97853db5cc5

Subscribe to this mod's changes

project-template AGENTS.md is an instructions file published in the GitHub repository polmarza/project-template (89 stars, last pushed 15d ago), licensed MIT. It adds 3,297 tokens to every session, about $0.0132 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-23.

Building agentsshowcase
Related

project-template AGENTS.md compared with instructions from other repositories

project-template AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
project-template AGENTS.mdpolmarza/project-templateInstructions file8915d agoMITC3,297Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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