agentmods.dev

open-relay: Instructions file for Codex

AGENTS.md

open-relay AGENTS.md is an instructions file for Codex, OpenCode from slaveOftime/open-relay. It costs 1,188 tokens per session, scanned A, original, MIT.

A project's AGENTS.md instruction file, documenting its architecture, setup requirements, code locations, and development rules. It covers a Rust command-line and server side, plus a React and TypeScript web interface.

In plain words
What is it for?
Use it before working on the open-relay project. It helps decide which guides to read, locate backend and web code, understand release requirements, and find integration and browser tests.
Why use it?
It gives a coding agent project-specific context before it edits files. Following it helps preserve unrelated work and directs changes to the right documentation, source, and test areas.

Instructions file for CodexOpenCode

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

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

not rated 110repo +1 changed 20d ago A scan 1,188 tokens original MIT
View source ↗ slaveOftime/open-relay
Reuse

Borrowing it

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

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 open-relay AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/slaveoftime/open-relay/agents-md"><img src="https://agentmods.dev/badge/instructions/slaveoftime/open-relay/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,188 This file is loaded in full into every session.
When invoked 1,188 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 $0.01188 $0.01188
Opus 5.5 $0.00475 $0.00475
Sonnet 5.5 $0.00238 $0.00238
Haiku 4.5 $0.00119 $0.00119

Measured 20d ago against content hash 9c3ffe1b1b8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

open-relay 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 20d 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 · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent guide

Project basics

  • oly supervises interactive CLI programs in daemon-owned PTYs with recorded output.
  • Rust backend/CLI lives in src/; React + TypeScript + Vite + xterm.js UI lives in web/.
  • Release builds embed the web UI and require Rust and Node.js/npm.
  • Client disconnect preserves the child; daemon stop/crash or reboot does not.

Before starting a task

Where code lives

  • src/cli.rs, src/client/: command parsing and client operations.
  • src/daemon/, src/http/, src/node/: RPC, HTTP/WebSocket, and federation.
  • src/session/, src/terminal/: PTY lifecycle, journal, replay, logs, and terminal model.
  • web/src/: UI; tests/ and web/e2e/: integration/browser coverage.
  • skills/: agent guidance embedded by oly skill; keep it aligned with behavior.

Coding principles

  • Make small, focused changes; verify assumptions against source and tests.
  • Preserve one journal, one authoritative backend terminal model, and one attach contract.
  • Reuse existing modules and UI primitives; keep domain logic separate from rendering.
  • Add regression tests for behavior changes; update relevant docs and skills together.
  • Treat child output as untrusted data; do not weaken auth or trust boundaries for convenience.
  • Use isolated daemon state (OLY_STATE_DIR=./.dev-state); never disrupt the operator's daemon.
  • Verify observable results, not just input delivery or idle state; report skipped/untested checks.
  • Do not tag, publish, or change release channels without maintainer authorization.

Read the full file on GitHub · 60 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. 20d ago Changed · +2 lines · +18 tokens per session 9c3ffe1b1b8e
  2. 21d ago Changed · +9 lines · +348 tokens per session 3225288b6a66
  3. 23d ago First seen · 49 lines · 822 tokens per session scan A 96cbb3ab078c

Subscribe to this mod's changes

open-relay AGENTS.md is an instructions file published in the GitHub repository slaveOftime/open-relay (110 stars, last pushed 8d ago), licensed MIT. It adds 1,188 tokens to every session, about $0.0048 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 2026-10-15.

PlanningRustagentopsai-agentscliptysession-management
Related

open-relay AGENTS.md compared with instructions from other repositories

open-relay AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
open-relay AGENTS.mdslaveOftime/open-relayInstructions file1108d agoMITA1,188Codex, 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 file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode