EEP AGENTS.md

Repository instructions for coding agents working on the Entity Engagement Protocol (EEP), an open standard for sending verified updates from digital entities to subscribers. They explain the project structure, key documents, and how to add EEP to another project.

In plain words
What is it for?
Useful for navigating the EEP codebase, finding its specification and schemas, working with its TypeScript or Python packages, and adopting EEP in another project.
Why use it?
They give an agent a fast, reliable way to understand the repository and avoid confusing EEP with related systems such as MCP or agent-to-agent protocols.

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/eep-dev/eep/agents-md
Clone the repo
git clone --depth 1 https://github.com/eep-dev/EEP

Made for: Codex, OpenCode.

Per session 1,215 This file is loaded in full into every session.
When invoked 1,215 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.

ModelPer sessionOnce invoked
Fable 5 $0.01215 $0.01215
Opus 5 $0.00607 $0.00607
Sonnet 5 $0.00243 $0.00243
Haiku 4.5 $0.00121 $0.00121

Measured yesterday against content hash b3626b3cf3c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

EEP 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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — How coding agents work with this repository

Entity Engagement Protocol (EEP) — open standard for push-based, verifiable communication between digital entities and subscribers (including AI agents). This file is the fast path for autonomous tools (Claude Code, Cursor, Cline, OpenClaw, etc.). Read this first, then llms.txt or llms-full.txt for depth.

What to know in 30 seconds

  • Not a replacement for MCP (tools), A2A (agent↔agent), or ANP. EEP is entity engagement: discovery, SSE/webhooks, optional WebSockets, gates (identity, payment, agreements, …), signed deliveries. See README.md positioning table.
  • Normative truth: docs/current/SPECIFICATION.md + schemas/v0.1/.
  • Webhook signatures (outbound POST to subscribers): Standard Webhooks-style headers webhook-id, webhook-timestamp, webhook-signature (see spec §5). Do not invent a separate X-EEP-Signature for webhook bodies.

Repository map

Need Location
Full spec docs/current/SPECIFICATION.md
JSON Schemas schemas/v0.1/
TypeScript packages packages/@eep-dev/*
Python ports packages/eep-*-python/
Conformance against a live URL packages/@eep-dev/compliance-cli
Scaffold + generated artifacts packages/@eep-dev/setup-cli (eep-setup)
HTTP adapters (Express, Fastify, Hono, Koa, FastAPI, …) packages/@eep-dev/middleware, packages/eep-middleware-python
MCP ↔ EEP HTTP bridge packages/@eep-dev/mcp-bridge
One-shot adopt flow for an app repo packages/@eep-dev/agent-adopt
Agent strategy / launch notes docs/strategy/
LangGraph example examples/langgraph-eep-agent/
Docker reference stack examples/eep-reference-implementation/

Adopt EEP into another project (typical agent task)

From the target application repository (not necessarily this monorepo):

Read the full file on GitHub · 95 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. yesterday First seen · 95 lines · 1,215 tokens per session scan A b3626b3cf3c1

Subscribe to this mod's changes

EEP AGENTS.md is an instructions file published in the GitHub repository eep-dev/EEP (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,215 tokens to every session, about $0.0061 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 2026-08-30.