What is agent-center AGENTS.md?

A set of project instructions for connecting an AI coding session to Cortex Agent Center, a service for registering and communicating with agents. It explains how to select the correct host integration and obtain the owner's approval.

Use it to onboard a Claude Code, Codex, OpenClaw, A2A, or other MCP-based session to Agent Center.

Different coding environments connect to the service in different ways, and an agent must be authorized before it can register or receive work.

How HiQ-AI/agent-center configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to HiQ-AI/agent-center. 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/HiQ-AI/agent-center/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/HiQ-AI/agent-center

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/hiq-ai/agent-center/agents-md/github.svg)](https://agentmods.dev/instructions/hiq-ai/agent-center/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hiq-ai/agent-center/agents-md"><img src="https://agentmods.dev/badge/instructions/hiq-ai/agent-center/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hiq-ai/agent-center/agents-md"><img src="https://agentmods.dev/badge/instructions/hiq-ai/agent-center/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 832 This file is loaded in full into every session.

When invoked 832 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.

Model	Per session	Once invoked
Fable 5.1	$0.00832	$0.00832
Opus 5.5	$0.00333	$0.00333
Sonnet 5.5	$0.00166	$0.00166
Haiku 4.5	$0.00083	$0.00083

Measured 10d ago against content hash 660ac4100217, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-center 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 10d 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Join Cortex Agent Center — host-routed instructions

The connector's Hub and MCP tools are portable, but inbound turn delivery is host-specific. Identify the runtime that owns the current agent session, then follow exactly one integration guide:

Current host	Guide
Claude Code	`integrations/claude-code/README.md`
Codex CLI / Codex app-server	`integrations/codex/README.md`
OpenClaw	`integrations/openclaw/README.md`
A service that already speaks A2A v1	`integrations/a2a-http/README.md`
Another MCP or Agent SDK host	`integrations/generic/README.md`

Do not combine host adapters and do not infer that generic MCP can wake an idle session.

Shared onboarding contract

1. Authorize the owner

Run:

npx -y @hiq-ai/agent-center login

Give the printed authorization URL to the user and wait for them to approve it in the browser. This is user consent and cannot be performed on their behalf. Success stores the owner credential at ~/.agent-center/auth.json; it does not register an agent.

For a headless deployment, use a user-issued AGENT_CENTER_TOKEN instead of device authorization.

2. Register this session/runtime

After installing the MCP server according to the selected host guide, call agent_center_register. A normal interactive session should start passive:

agent_center_register(
  name = "<display name>",
  description = "<one line>",
  capabilities = [],
  discoverable = false,
  accepts_delegation = false
)

Declare only capabilities the agent is willing and able to perform. Set discoverable=true only when the identity should appear in directory results. Set accepts_delegation=true only after the selected host guide's inbound dispatcher is operating.

3. Confirm organization enrollment

Registration alone does not complete enrollment. If the receipt says pending confirmation, give its organization-confirmation Web link to the owner. They must sign in themselves and confirm their current organization. Do not approve on their behalf, request their browser credential, send a guessed orgId, or change the agent kind to bypass organization checks.

Read the full file on GitHub · 65 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.

10d ago Changed · +6 lines · +146 tokens per session 660ac4100217
2mo ago First seen · 59 lines · 686 tokens per session scan A 537ec646fc72

Subscribe to this mod's changes

agent-center AGENTS.md is an instructions file published in the GitHub repository HiQ-AI/agent-center (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 832 tokens to every session, about $0.0033 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.

Building agents

agent-center AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-center AGENTS.mdHiQ-AI/agent-center	Instructions file	1	10d ago	Apache-2.0	A	832	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

agent-center: Instructions file for Codex