relay-action-card: Instructions file for Codex

AGENTS.md

relay-action-card AGENTS.md is an instructions file for Codex, OpenCode from neurarelay/relay-action-card. It costs 384 tokens per session, scanned A, original, MIT.

Repository instructions for developing and checking Neura's Relay Action Cards, which are documented action and result formats for bounded integrations.

In plain words
What is it for?
Use them when modifying that repository, running its required checks, reviewing dependencies, or deciding whether an example or integration is within scope.
Why use it?
They clarify what the public repository represents, which runtime and checks to use, and what private or unsafe functionality must not be added.

Instructions file for CodexOpenCode

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

This is neurarelay/relay-action-card's own configuration. It tells Codex and OpenCode how to work on relay-action-card 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 relay-action-card configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/roman/Drive/Business/Neura.

Reuse

Borrowing it

Nothing to install: this file belongs to neurarelay/relay-action-card. 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/neurarelay/relay-action-card/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/neurarelay/relay-action-card

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 relay-action-card AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/neurarelay/relay-action-card/agents-md"><img src="https://agentmods.dev/badge/instructions/neurarelay/relay-action-card/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 384 This file is loaded in full into every session.
When invoked 384 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00384 $0.00384
Opus 5 $0.00192 $0.00192
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00038 $0.00038

Measured 9d ago against content hash 4dbd2c52ac0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

relay-action-card 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 9d 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 · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Relay Action Card Repository Instructions

Role and authority

This public repository is Neura's proof, schema, example, skill, adapter, and developer-verification surface for Relay Action Cards and related receipts.

It demonstrates public contracts and bounded integrations. It is not the authoritative private Relay runtime, Registry identity source, or downstream execution engine.

Runtime and verification

  • Use Node 24 as the primary development and CI runtime.
  • Preserve package.json compatibility with Node >=22.14.0 unless a separate consumer-compatibility decision changes it.
  • Treat npm run check as the required local and CI verification entry point.
  • Run npm audit --audit-level=high for dependency changes and before remote review.

Change boundaries

  • Preserve public examples as synthetic and free of private customer or Capital Guide data.
  • Do not add public API-key issuance, public production token issuance, unprotected execution, downstream execution, raw private payloads, or secret values.
  • Do not make adoption, official-provider, certification, endorsement, or production-readiness claims without verified evidence and separate approval.
  • Package publication, release tags, public narrative changes, and repository settings require separate explicit scope.
  • Do not change shared contract versions through maintenance work.

Documentation and history

  • Update factual proof records when implementation or verification truth changes.
  • Keep dated historical evidence intact unless a dedicated archival migration is explicitly scoped and verified.
  • Use the workspace control layer at /Users/roman/Drive/Business/Neura Agent Infrastructure for portfolio strategy and cross-repository authority.
  • Do not present a local candidate as published, pushed, merged, or generally adopted.

External actions

Local inspection, edits, tests, and commits are allowed within the approved task. Pushing, opening or merging pull requests, changing repository settings, publishing packages, and creating releases require an exact consolidated external-action boundary.

Read the full file on GitHub · 34 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. 9d ago First seen · 34 lines · 384 tokens per session scan A 4dbd2c52ac0f

Subscribe to this mod's changes

relay-action-card AGENTS.md is an instructions file published in the GitHub repository neurarelay/relay-action-card (2 stars, last pushed 16d ago), licensed MIT. It adds 384 tokens to every session, about $0.0019 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 2026-08-31.

Related

Other instructions, from other repositories