What is xr AGENTS.md?

A repository-specific instruction guide for coding agents working on the XR project. It explains the project's components, setup commands, enforced rules, and where the source, tests, documentation, and release files live.

Use it when modifying the XR codebase, finding the right package or test area, following setup and CI requirements, or preparing changes for release.

It gives an agent the local context needed to make changes without bypassing repository rules or overlooking the project's structure. It also points contributors to the governing documents and routine checks.

How ahmadrrrtx/xr configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ahmadrrrtx/xr. 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/ahmadrrrtx/xr/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ahmadrrrtx/xr

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ahmadrrrtx/xr/agents-md/github.svg)](https://agentmods.dev/instructions/ahmadrrrtx/xr/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ahmadrrrtx/xr/agents-md"><img src="https://agentmods.dev/badge/instructions/ahmadrrrtx/xr/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ahmadrrrtx/xr/agents-md"><img src="https://agentmods.dev/badge/instructions/ahmadrrrtx/xr/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,063 This file is loaded in full into every session.

When invoked 1,063 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.

Model	Per session	Once invoked
Fable 5.1	$0.01063	$0.01063
Opus 5.5	$0.00425	$0.00425
Sonnet 5.5	$0.00213	$0.00213
Haiku 4.5	$0.00106	$0.00106

Measured 15d ago against content hash ef77b10aa8e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

xr 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 15d 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — how to work in this repository

A briefing for coding agents (and humans in a hurry). Human onboarding lives in README.md; the full contributor guide is CONTRIBUTING.md. The law this codebase cites is docs/CONSTITUTION.md — if a rule below feels arbitrary, the Article behind it is there.

What this repo is

XR is a local-first, provider-neutral AI agent runtime: a Bun-written CLI + daemon + agent loop, governed in the execution path (policy gate, approvals, budget governor, hash-chained audit), with a Tauri v2 + React desktop shell, a mobile PWA, and a Next.js website.

src/        core runtime (cli, commands, execution, core, services, providers, tools,
            security, xr-shield, state, context, daemon, bots, mcp, plugins, voice, …)
desktop/    Tauri v2 shell (src = React UI; src-tauri = Rust shell + commands)
mobile/     mobile companion PWA · cloud/ = optional hosted control plane (independent version)
satellites/ extracted packages (@rrrtx/xr-enterprise, @rrrtx/business-os) — released separately
skills/     bundled skill manifests · test/ = suite mirroring src/ · scripts/ = gates & release machinery
docs/       product/development/release/security/historical · website/ = marketing site (Next.js)

Setup

bun install --frozen-lockfile        # bun 1.3+ (pinned in .bun-version); node >= 20 for npm-installed builds
cd desktop && bun install            # REQUIRED before any typecheck that touches desktop (preflight fails with this exact hint)

Routine commands

Task	Command
Full gate battery (must be green before a PR)	`bun run ci`
Test suite	`bun test` (segmented per directory in low-memory environments)
Typecheck	`bun run typecheck` (root) · `node_modules` in `desktop/` required for desktop tsconfig
Gates (individually)	`release:check` · `claim-lint` · `channel:check` · `placeholder-lint` · `desktop:sink-lint` · `platform:parity:check` · `changelog:check` · `baseline:inventory` · `ci-capability-gate` · `api:schema:check` · `client:check` · `api:compat` · `boundaries` · `size-gate` · `hot-path-lint` · `ownership:check` · `website:marketplace:check`
Desktop shell build/test	`cd desktop && bun run build` · `cargo check --all-targets` + `cargo test --lib` in `desktop/src-tauri` (sidecar binary must exist first: `bun run scripts/compile-sidecar.ts`)

Read the full file on GitHub · 67 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.

15d ago First seen · 67 lines · 1,063 tokens per session scan A ef77b10aa8e2

Subscribe to this mod's changes

xr AGENTS.md is an instructions file published in the GitHub repository ahmadrrrtx/xr (6 stars, last pushed 2d ago), licensed MIT. It adds 1,063 tokens to every session, about $0.0043 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 2026-10-22.

Project management ai-agent ai-agents bun byok byok-ai-tools-code-assistant llms

xr AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
xr AGENTS.mdahmadrrrtx/xr	Instructions file	6	2d ago	MIT	A	1,063	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

xr: Instructions file for Codex