core: Instructions file for Codex

AGENTS.md

core AGENTS.md is an instructions file for Codex, OpenCode from epicurrents/core. It costs 21,273 tokens per session, scanned C, original, Apache-2.0.

A project-specific guide for AI coding agents working on `@epicurrents/core`, the shared foundation of a family of biosignal-processing packages. Biosignals are measurements such as brain or body activity recorded over time.

In plain words
What is it for?
Use it when editing `@epicurrents/core` or answering questions about its runtime state, resources, services, workers, shared types, and related packages.
Why use it?
It explains the package's architecture and shared contracts, helping agents avoid changes that break related packages.

Instructions file for CodexOpenCode

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

This is epicurrents/core's own configuration. It tells Codex and OpenCode how to work on core 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 core configures →

Reuse

Borrowing it

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

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 core AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/epicurrents/core/agents-md"><img src="https://agentmods.dev/badge/instructions/epicurrents/core/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21,273 This file is loaded in full into every session.
When invoked 21,273 The same file — it is already loaded in full.
Security scan C 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 $0.21273 $0.21273
Opus 5.5 $0.08509 $0.08509
Sonnet 5.5 $0.04255 $0.04255
Haiku 4.5 $0.02127 $0.02127

Measured 3d ago against content hash ac7b15d9444b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

core 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf util/asymmetric-io-mutex/node_modules/scoped-event-log
AGENTS.md · 738 lines

How it starts

The opening of the file, as written. The whole thing — 738 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@epicurrents/core — architecture notes for AI coding assistants

@epicurrents/core is the dependency root of the Epicurrents package family. It defines the application entry point (Epicurrents), the runtime state manager, the asset/resource/module/service abstractions, the biosignal montage and trend machinery, the worker commission protocol, and the shared TypeScript types every sibling package imports. Every other @epicurrents/* package — readers, modality modules, services, and the viewer interface — builds on the contracts defined here, so a change in this package can break all of them at once.

This file is the in-depth technical reference for AI coding assistants: internal architecture, the contracts the package guarantees to consumers, and the gotchas that bite when editing it. It should let an agent answer most questions about the package directly, or at least point at the right place to look. README.md is the denser user-facing description (structure, usage, build workflow) and the right link to hand a human; ROADMAP.md carries design intent, not current state. Sibling packages (readers, modules, services, interface) keep their own AGENTS.md; module-side and rendering-side detail lives there, not here.

Keep this file current — update it in the same change set as the code. This document only works if it describes the code as it is; a stale section is worse than a missing one, because an agent will act on it. After any change that alters something documented here — a contract, a protocol shape, a lifecycle, a public symbol, a limitation being lifted — update the affected section (or add one for a new subsystem) before reporting the work done. The same rule applies to the siblings: README.md when the user-facing surface (usage, structure, build workflow) changes, ROADMAP.md when documented deferred work lands or new work is deliberately deferred. Pure refactors, test-only changes and bug fixes that restore documented behaviour need no update.


Read the full file on GitHub · 738 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 Changed · +224 tokens per session ac7b15d9444b
  2. 11d ago Changed · +2 lines · +392 tokens per session b3b012bc422d
  3. 1mo ago Changed · +95 lines · +4,327 tokens per session c4eaa542191b
  4. 1mo ago Changed · +72 lines · +3,222 tokens per session a954d165f92e
  5. 1mo ago Changed · +2 lines · +153 tokens per session 0f0cf4f5417c
  6. 1mo ago Changed · +10 lines · +482 tokens per session a6db34b9b30b
  7. 2mo ago Changed · +17 lines · +369 tokens per session 61133de2c234
  8. 2mo ago Changed · +1 lines · +113 tokens per session 9ec8842c59fc
  9. 2mo ago First seen · 539 lines · 11,991 tokens per session scan C 6eea7ce7a677

Subscribe to this mod's changes

core AGENTS.md is an instructions file published in the GitHub repository epicurrents/core (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 21,273 tokens to every session, about $0.0851 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

core AGENTS.md compared with instructions from other repositories

core AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
core AGENTS.mdepicurrents/coreInstructions file23d agoApache-2.0C21,273Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot