relay AGENTS.md

Project instructions for Relay, a system that turns issues or written requests into planned, scheduled, verified AI coding work and watches the resulting pull requests. It includes a TypeScript orchestrator, Rust terminal and desktop interfaces, and shared local state files.

In plain words
What is it for?
Use them when working on Relay's planning pipeline, MCP server, dashboards, shared data, verification, or pull-request monitoring.
Why use it?
They explain the project's architecture and development workflow so changes fit across its command-line, terminal, and desktop parts.

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/jcast90/relay/agents-md
Clone the repo
git clone --depth 1 https://github.com/jcast90/relay

Made for: Codex, OpenCode.

Per session 3,051 This file is loaded in full into every session.
When invoked 3,051 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 $0.03051 $0.03051
Opus 5 $0.01525 $0.01525
Sonnet 5 $0.00610 $0.00610
Haiku 4.5 $0.00305 $0.00305

Measured 2d ago against content hash b921c7882fa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

relay 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Tests use per-test tmp dirs. **Never `rm -rf` outside your own tmp dir.** No test should touch a real `~/.relay/`.
AGENTS.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Conventions for coding agents (Claude Code, Codex, Cursor, and anything else) working in Relay. This is the short, agent-targeted companion to CONTRIBUTING.md — read both if you're new.

For the product pitch and user-facing features, see README.md. For the deeper walkthrough, see docs/getting-started.md. This doc is about how to work in the code, not what the product is.

Project overview

Relay turns a sentence, a GitHub issue, or a Linear ticket into a running plan of AI-coded work: classifier → planner → decomposer → scheduler → verification → PR watcher. Sessions run inside the user's normal Claude or Codex CLI; Relay wraps them with an MCP server and writes all state (channels, tickets, decisions, crosslink messages) to ~/.relay/ as JSON/JSONL.

The codebase is multi-language by design: TypeScript orchestrator (the CLI, MCP server, orchestration pipeline) + Rust TUI (tui/, ratatui) + Tauri desktop GUI (gui/, React + Vite frontend with a Rust backend) + a shared Rust crate (crates/harness-data/) that the TUI and GUI both use to read ~/.relay/. The three dashboards never talk to each other — they all read the same files on disk.

Development workflow

Most of the loop is live:

  • TS edits take effect immediately. bin/rly.mjs runs src/cli.ts through tsx, so rly … reflects your source changes on the next invocation. No rebuild.
  • After git pull touches pnpm-lock.yaml or Cargo.lock, run rly rebuild. It runs pnpm install first automatically (pass --skip-install to skip).
  • Rust TUI changes: rly rebuild --tui.
  • Tauri GUI changes: rly gui --dev for hot-reload, or rly gui --rebuild to refresh the .app bundle.

Set RELAY_USE_DIST=1 if you want to exercise the pre-built dist/ path (marginally faster startup, but stale until rly rebuild).

Verification before pushing

Run these:

pnpm test && pnpm typecheck && pnpm build

Read the full file on GitHub · 137 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. 2d ago First seen · 137 lines · 3,051 tokens per session scan C b921c7882fa9

Subscribe to this mod's changes

relay AGENTS.md is an instructions file published in the GitHub repository jcast90/relay (5 stars, last pushed 1mo ago), licensed MIT. It adds 3,051 tokens to every session, about $0.0153 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.