EDDI AGENTS.md

Development instructions for the Java and Quarkus backend of EDDI, a middleware system that coordinates multiple conversational AI agents. Agent behavior is defined in JSON configuration, while the Java code runs the engine and infrastructure.

In plain words
What is it for?
Use it when working on EDDI’s backend, REST API, lifecycle pipeline, agent configurations, or related Java and Quarkus components.
Why use it?
It gives coding agents the project context and rules needed to change the backend without confusing configuration with engine code. It also points them to setup information, architecture, and coding guidance.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/labsai/eddi/agents-md
Clone the repo
git clone --depth 1 https://github.com/labsai/EDDI

Made for: Codex, OpenCode.

Per session 15,605 This file is loaded in full into every session.
When invoked 15,605 The same file — it is already loaded in full.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.15605 $0.15605
Opus 5 $0.07803 $0.07803
Sonnet 5 $0.03121 $0.03121
Haiku 4.5 $0.01561 $0.01561

Measured 3d ago against content hash 15c237edad54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

EDDI 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 3d 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

> **Warning**: `scope: "secret"` requires the vault to be active (`EDDI_VAULT_MASTER_KEY` env var set). If vault is disabled (common in dev mode), `autoVaultSecret()` fails and falls back to storing plaintext — but logs
AGENTS.md · 973 lines

How it starts

The opening of the file, as written. The whole thing — 973 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EDDI Backend — AI Agent Instructions

This file is automatically loaded by AI coding assistants. Follow ALL rules below.

New here? Read the README first — it has setup, the quick start, and a feature tour. This file is the working guide for building in the codebase: architecture, code patterns, and conventions.

Contents: 1. Project Context · 2. Workflow Protocol · 3. Roadmap · 4. Backend Java Guidelines · 5. Agent Config Authoring · 6. Session Protocol

1. Project Context

EDDI (Enhanced Dialog Driven Interface) is a multi-agent orchestration middleware for conversational AI. This repo is the Java/Quarkus backend.

EDDI is a config-driven engine, not a monolithic application. Agent behavior lives in JSON configurations; Java code builds the components and infrastructure (the "engine") that reads and executes those configurations.

Ecosystem

Repo Tech Purpose
EDDI (this repo) Java 25, Quarkus, MongoDB Backend engine, REST API, lifecycle pipeline
quarkus-eddi Java 21, Quarkus Extension Quarkus SDK — @Inject EddiClient, Dev Services, MCP bridge
EDDI-Manager React 19, Vite, Tailwind Admin dashboard (served from EDDI at /manage; / redirects to the /welcome chooser, /workforce is the group-conversation workspace)
eddi-chat-ui React, TypeScript Standalone chat widget
eddi-website Astro, Starlight Marketing site + documentation at eddi.labs.ai

Read the full file on GitHub · 973 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. 3d ago First seen · 973 lines · 15,605 tokens per session scan C 15c237edad54

Subscribe to this mod's changes

EDDI AGENTS.md is an instructions file published in the GitHub repository labsai/EDDI (372 stars, last pushed 3d ago), licensed Apache-2.0. It adds 15,605 tokens to every session, about $0.0780 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.