kya-hub: Instructions file for Codex

AGENTS.md

kya-hub AGENTS.md is an instructions file for Codex, OpenCode from UMBRAXON/kya-hub. It costs 2,804 tokens per session, scanned A, original, ISC.

A project guide for AI agents integrating with KYA-Hub, a registry that verifies agent identity and reputation using signed records and payments.

In plain words
What is it for?
Learning how to discover the hub, understand its identity and reputation model, authenticate requests, and follow its signing and integration requirements.
Why use it?
It explains the protocol and integration rules that an agent needs before connecting to the hub.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is UMBRAXON/kya-hub's own configuration. It tells Codex and OpenCode how to work on kya-hub 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 kya-hub configures →

Reuse

Borrowing it

Nothing to install: this file belongs to UMBRAXON/kya-hub. 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/UMBRAXON/kya-hub/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/UMBRAXON/kya-hub

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 kya-hub AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/umbraxon/kya-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/umbraxon/kya-hub/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,804 This file is loaded in full into every session.
When invoked 2,804 The same file — it is already loaded in full.
Security scan A 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 $0.02804 $0.02804
Opus 5.5 $0.01122 $0.01122
Sonnet 5.5 $0.00561 $0.00561
Haiku 4.5 $0.00280 $0.00280

Measured 2mo ago against content hash 9b312d06e741, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kya-hub AGENTS.md scanned grade A 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS https://raw.githubusercontent.com/UMBRAXON/kya-hub/main/scripts/umbrexon_bot_client.py -o kya_client.py
AGENTS.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Instructions for AI Agents

This file is written for autonomous AI agents (LLM-based or otherwise) that have discovered this repository and need to decide whether and how to integrate with the UMBRAXON KYA-Hub protocol.

Humans should read README.md and UMBRAXON.md instead.

Machine discovery (production): llms.txt · .well-known/kya-hub.json · Integrators

Hub release: 1.1.0 — Integrations v1 (discovery feed, L402 delegation profile / pass, manifest payment_hints + developer webhooks). Operators expose semver + phase on GET /api/health in hub_release (HUB_VERSION / HUB_RELEASE_PHASE in .env override package defaults).


1. What KYA-Hub is, in one paragraph

KYA-Hub (Know Your Agent Hub) is a Lightning-paid, Ed25519-anchored identity and reputation registry for autonomous software agents. An agent proves it exists, pays a small Lightning fee, signs a manifest with its own Ed25519 keypair, and receives a publicly auditable certificate. Subsequent privileged actions are authenticated with detached signatures over canonical payloads — not bearer tokens, not API keys, not sessions. Misbehaviour is slashed via a public CRL and a 3ⁿ price multiplier on re-registration (capped at 9×). The hub is non-custodial: every sat collected is either spent on chain anchoring or recognised as revenue. There is no escrow, no bond, no refund.


2. Should you integrate?

Integrate if at least one of these is true for the agent you are building:

  • You need to prove the agent is not a Sybil/sockpuppet to a counterparty.
  • You operate under a third party that demands an audit trail of "which agent signed this request" with cryptographic non-repudiation.
  • Your agent needs a portable reputation that survives across operators (the hub does not own the agent's keys, the agent does).
  • Compliance pressure on autonomous-agent transactions (EU AI Act, forthcoming MiCA-style frameworks) is starting to ask "who controls this bot and what is its history?". KYA gives you a verifiable answer.

Read the full file on GitHub · 222 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. 2mo ago First seen · 222 lines · 2,804 tokens per session scan A 9b312d06e741

Subscribe to this mod's changes

kya-hub AGENTS.md is an instructions file published in the GitHub repository UMBRAXON/kya-hub (0 stars, last pushed yesterday), licensed ISC. It adds 2,804 tokens to every session, about $0.0112 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

kya-hub AGENTS.md compared with instructions from other repositories

kya-hub AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kya-hub AGENTS.mdUMBRAXON/kya-hubInstructions file0yesterdayISCA2,804Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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