What is AetherEdge AGENTS.md?

Repository instructions for AetherEdge, an industry-neutral Internet of Things edge system and software development kit. They define the product direction, naming rules, architecture boundaries, and repository layout.

Guiding development across the Rust processes, shared libraries, services, SDK, protocol identifiers, and optional energy-management components.

They prevent coding agents from adding unwanted external services or mixing optional energy features into the core system. They also keep compatibility-sensitive names and structures consistent.

AetherEdge AGENTS.md — Instructions file by EvanL1

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/evanl1/aetheredge/agents-md

Clone the repo

git clone --depth 1 https://github.com/EvanL1/AetherEdge

Made for: Codex, OpenCode.

Per session 1,921 This file is loaded in full into every session.

When invoked 1,921 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.01921	$0.01921
Opus 5	$0.00960	$0.00960
Sonnet 5	$0.00384	$0.00384
Haiku 4.5	$0.00192	$0.00192

Measured yesterday against content hash 0c4790dfe613, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AetherEdge 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 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.

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 · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AetherEdge Agent Instructions

This file is the canonical instruction source for coding agents working in this repository. CLAUDE.md and GEMINI.md are symlinks to it, so every agent reads and edits the same content. Any further tool-specific file may add usage notes, but must not contradict this one.

Product Direction

AetherEdge is an AI-native, industry-neutral IoT edge kernel and SDK. Energy management is an optional domain pack, not a dependency of the core runtime. The default distribution must run on one Linux edge host without Redis, PostgreSQL, or any other external service. The default runtime is six Rust processes and requires no browser application and no LLM. The optional AetherEMS Console and Energy Pack live in EvanL1/AetherEMS.

AetherIoT is the umbrella project name. This repository is the AetherEdge product formerly named AetherIot. Preserve aether-*, aether, configuration, installer, and protocol identifiers unless a separate compatibility decision explicitly changes them.

Repository Map

crates/       domain, ports, application, SDK, Pack and testkit APIs
libs/         shared kernel implementation (SHM, local storage, config, sim)
services/     io, automation, history, api, uplink and alarm processes
tools/        aether CLI/MCP and the protocol simulator
examples/     minimal generic and compatibility composition proofs
packs/        Pack manifests
contracts/    pinned AetherContracts release
docs/         current concepts, guides and references
ai/           generated agent catalog and the safety-policy authority
skills/       the repository-owned Agent Skill
firmware/     separately targeted embedded workspace

The unified documentation site source and deployment live in EvanL1/AetherDocs.

Historical plans and scratch design material must stay outside GitHub.

Current authority is this file, the runtime manifest, OpenAPI, and the active Pack manifests.

Read the full file on GitHub · 185 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.

yesterday First seen · 185 lines · 1,921 tokens per session scan A 0c4790dfe613

Subscribe to this mod's changes

AetherEdge AGENTS.md is an instructions file published in the GitHub repository EvanL1/AetherEdge (3 stars, last pushed 17d ago), licensed Apache-2.0. It adds 1,921 tokens to every session, about $0.0096 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.

Languages Planning ai-native edge-computing embedded iot mqtt rust

AetherEdge AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AetherEdge Agent Instructions

Product Direction

Repository Map

What this file has done since we first saw it

Other instructions, from other repositories

core integrations.instructions.md

core copilot-instructions.md

kin GEMINI.md

kin AGENTS.md

serial-mcp AGENTS.md

iot-dc3 AGENTS.md