Borrowing it
Nothing to install: this file belongs to Aitherium/awrelay. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Aitherium/awrelay/main/AGENTS.mdgit clone --depth 1 https://github.com/Aitherium/awrelayWrote 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.
[](https://agentmods.dev/instructions/aitherium/awrelay/agents-md)<a href="https://agentmods.dev/instructions/aitherium/awrelay/agents-md"><img src="https://agentmods.dev/badge/instructions/aitherium/awrelay/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.
<a href="https://agentmods.dev/instructions/aitherium/awrelay/agents-md"><img src="https://agentmods.dev/badge/instructions/aitherium/awrelay/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00575 | $0.00575 |
| Opus 5.5 | $0.00230 | $0.00230 |
| Sonnet 5.5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
awrelay 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
awrelay for agents
Read this if you are an agent (or a human) editing this package. Short on purpose: the commands, the traps that cost a session, and where the rest lives. Nothing here is read at runtime — it is for you.
What this is
PyPI distribution awrelay (version in pyproject.toml), import package
awrelay, Python >= 3.10. A channel for agents to tell each other things — the
client side of the relay: channels, structured envelopes, A2A bridge, doors.
This repository is a synced mirror of the AitherOS monorepo (lane
.github/workflows/sync-awrelay.yml). Hand edits made here are overwritten on
the next sync — change the source and let the lane publish.
Build, test, verify
python -m pytest tests -q # the suite: 134 tests, green at v0.5.1
pip install -e . # editable install for developing against it
The suite was run from a source checkout with no prior install. The publish
lane (publish-brick.yml) additionally builds the wheel, installs it and
imports it — a tree that tests green can still ship a broken wheel.
Rules that keep this useful
- A relay change is a protocol change. The door handshake and first-party
CLI identity are pinned by name (
test_door_client.py,test_cli_first_party_identity.py,test_hookgate.py); keep new behaviour under its own named test, because two clients disagreeing about a handshake looks like the network misbehaving. - Envelopes are structured, and both ends read the same fields. The
bridge tests (
test_a2a_bridge.py) exist to keep the wire honest — a field added on one side only is a silent drop, not an error. - The registry drives the public surface. This repo's README header,
llms.txtandaither-manifest.jsonare generated from the ecosystem registry (one yaml in the AitherOS monorepo) and rewritten on every sync. Change the registry; do not hand-edit the generated blocks. - The install line is a measured claim.
check_ecosystem_install_linesasserts the advertisedpip installchannel is real and ours. A rename or a move lands with the registry entry in the same change.
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.
- 6d ago Changed af48f34542c7
- 13d ago First seen · 51 lines · 575 tokens per session scan A 335c07b18e77
awrelay AGENTS.md is an instructions file published in the GitHub repository Aitherium/awrelay (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 575 tokens to every session, about $0.0023 per session on Opus 5.5. 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 2026-10-08.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.