rayline AGENTS.md

rayline AGENTS.md is an instructions file for Codex, OpenCode from rayline-ai/rayline. It costs 958 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Rayline, a Rust project split into components for command-line use, background processes, proxying, routing, model support, and metrics. They define boundaries between those components and the supported command options.

In plain words
What is it for?
Use them when changing Rayline's command-line interface, routing, proxy, process injection, adapters, or model-related crates. They explain current flags such as --local, --via, and --route, along with compatibility aliases and invalid combinations.
Why use it?
They help agents put code in the correct component and avoid copying shared routing or protocol logic. They also prevent new documentation and tests from relying on deprecated command options.

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

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 rayline AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rayline-ai/rayline/agents-md.svg)](https://agentmods.dev/instructions/rayline-ai/rayline/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rayline-ai/rayline/agents-md"><img src="https://agentmods.dev/badge/instructions/rayline-ai/rayline/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 958 This file is loaded in full into every session.
When invoked 958 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.

ModelPer sessionOnce invoked
Fable 5 $0.00958 $0.00958
Opus 5 $0.00479 $0.00479
Sonnet 5 $0.00192 $0.00192
Haiku 4.5 $0.00096 $0.00096

Measured 4d ago against content hash e6380ac4ac7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rayline 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 4d 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rayline Agent Notes

CLAUDE.md is a symlink to this file. Keep rules short, current, and repo-specific.

Crate Boundaries

  • rayline-cli: user commands and CLI UX.
  • rayline-daemon: rld process orchestration.
  • rayline-proxy: proxying, TLS interception, CA handling, request routing.
  • rayline-injector: process/environment injection.
  • rayline-adapter: adapter protocol translation.
  • rayline-local-router: static routing policy and endpoint selection.
  • rayline-hf, rayline-llama, rayline-metrics: model/cache/runtime support.

Keep protocol and routing logic in shared crates. Do not duplicate it in CLI handlers. Prefer focused modules over growing the existing large CLI/proxy files.

CLI Contracts

  • Use the current routing flags in new docs, tests, and examples: --local, --via proxy|env, and --route all|subagents.
  • Treat --local-router, --no-proxy, and --routing-mode ... as deprecated compatibility aliases only.
  • --local means local static routing without hosted auth.
  • --via env is cloud-only and must not be combined with local inference or selective subagent routing.
  • Local routing defaults to --route subagents; cloud routing defaults to --route all.
  • Use --router-config-path when routes.subagents is meant to constrain the transparent proxy allowlist. Do not rely on RAYLINE_ROUTER_CONFIG alone for that allowlist.
  • rayline top should work for proxy-mode launches when metrics can bind. Metrics bind failures are best-effort and must not break proxy data flow.

Commands

cargo build --workspace --locked
cargo build --release -p rayline-cli -p rayline-daemon --locked
cargo +1.88.0 fmt --all -- --check
cargo +1.88.0 test --workspace --locked -- --test-threads=1
cargo +1.88.0 clippy --workspace --all-targets --locked -- -D warnings
cargo audit --file Cargo.lock
cargo deny --locked check advisories bans licenses sources
git diff --check

Use the pinned Rust toolchain. Run targeted checks while iterating and the relevant full gate before handoff.

Read the full file on GitHub · 91 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. 4d ago First seen · 91 lines · 958 tokens per session scan A e6380ac4ac7a

Subscribe to this mod's changes

rayline AGENTS.md is an instructions file published in the GitHub repository rayline-ai/rayline (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 958 tokens to every session, about $0.0048 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 2026-08-30.