What is Ultimate-Agent-Directory AGENTS.md?

A project-specific instruction file for coding agents working in the Ultimate-Agent-Directory repository. It explains the repository structure, required text format, and commands for validating data and generating documentation and the website.

Use it to guide agent work on the repository's YAML data, documentation generation, static site generation, and checks.

It gives an agent the repository rules it needs before changing files, including which files are source data and which are generated. This reduces the risk of editing generated output or skipping validation.

How moshehbenavraham/Ultimate-Agent-Directory configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to moshehbenavraham/Ultimate-Agent-Directory. 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/moshehbenavraham/Ultimate-Agent-Directory/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/moshehbenavraham/Ultimate-Agent-Directory

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/moshehbenavraham/ultimate-agent-directory/agents-md.svg)](https://agentmods.dev/instructions/moshehbenavraham/ultimate-agent-directory/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/moshehbenavraham/ultimate-agent-directory/agents-md"><img src="https://agentmods.dev/badge/instructions/moshehbenavraham/ultimate-agent-directory/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,619 This file is loaded in full into every session.

When invoked 2,619 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02619	$0.02619
Opus 5	$0.01309	$0.01309
Sonnet 5	$0.00524	$0.00524
Haiku 4.5	$0.00262	$0.00262

Measured yesterday against content hash c4f42c659e99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Ultimate-Agent-Directory 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 yesterday.

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 · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Agents when working with this repository.

IMPORTANT RULE

YOU MUST ONLY USE VALID ASCII UTF-8 LF CHARACTERS!

Repository Overview

The Ultimate AI Agent Ecosystem Directory 2025 is a data-driven documentation project that maintains a comprehensive, curated directory of AI agent frameworks, platforms, tools, and resources.

CRITICAL: This is NOT a software development project - there is no application code to build, test, or run. This is a documentation curation project using a modern data architecture:

YAML files in data/ are the single source of truth
README.md is GENERATED - never edit directly
Static website is GENERATED in _site/ from YAML data
Python scripts validate YAML and generate outputs

Essential Build Commands

All development uses the Makefile:

make install    # Install Python dependencies in venv
make validate   # Validate all YAML files against schemas (ALWAYS RUN BEFORE COMMITTING)
make generate   # Generate README.md from YAML data
make site       # Generate static website in _site/
make serve      # Build site + start local server (http://localhost:8000)
make test       # Run validation + generation (CI-friendly)
make clean      # Remove generated files and cache

Standard workflow:

Edit YAML files in data/agents/ or data/categories/
Run make validate to check schema compliance
Run make generate to update README.md
Run make site to regenerate website (optional)
Commit YAML files AND generated README.md

Data Architecture

Source of Truth: YAML Files

All content lives in structured YAML files:

Agent/Tool Entries: data/agents/{category}/{name}.yml

# REQUIRED FIELDS
name: str                          # 1-100 characters
url: HttpUrl                       # Valid HTTP/HTTPS URL
description: str                   # 20-1000 characters
category: str                      # Must match a category ID

# CLASSIFICATION
type: framework|platform|tool|course|community|research
tags: List[str]                    # Lowercase, hyphenated

# OPTIONAL METADATA
subcategory: Optional[str]         # For grouping within categories
github_repo: Optional[str]         # Format: "owner/repo"
documentation_url: Optional[HttpUrl]
demo_url: Optional[HttpUrl]
platform: Optional[List[str]]      # e.g., ["Python", "TypeScript"]
license: Optional[str]             # e.g., "MIT", "Apache-2.0"
pricing: Optional[free|freemium|paid|enterprise]

# EDITORIAL FLAGS
featured: bool                     # Highlight on homepage
verified: bool                     # Link checked, complete metadata

# TRACKING
added_date: Optional[date]
last_verified: Optional[date]

Read the full file on GitHub · 322 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.

yesterday First seen · 322 lines · 2,619 tokens per session scan A c4f42c659e99

Subscribe to this mod's changes

Ultimate-Agent-Directory AGENTS.md is an instructions file published in the GitHub repository moshehbenavraham/Ultimate-Agent-Directory (69 stars, last pushed 5d ago), licensed MIT. It adds 2,619 tokens to every session, about $0.0131 per session on Opus 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 2026-09-04.

Building agents agent agentic agentic-ai agents boilerplate boilerplate-application

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

Ultimate-Agent-Directory: Instructions file for Codex