core AGENTS.md

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

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/epicurrents/core/agents-md
Clone the repo
git clone --depth 1 https://github.com/epicurrents/core

Made for: Codex, OpenCode.

Per session 11,991 This file is loaded in full into every session.
When invoked 11,991 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.11991 $0.11991
Opus 5 $0.05996 $0.05996
Sonnet 5 $0.02398 $0.02398
Haiku 4.5 $0.01199 $0.01199

Measured yesterday against content hash 6eea7ce7a677, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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 · 539 lines

How it starts

The opening of the file, as written. The whole thing — 539 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 · 539 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 · 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 8d ago), licensed Apache-2.0. It adds 11,991 tokens to every session, about $0.0600 per session on Opus 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

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens