What is raum AGENTS.md?

Repository instructions for raum, a desktop terminal manager that runs command-line AI coding agents in recoverable sessions. They describe its technologies, folders, and main development commands.

Finding Rust backend, Solid.js frontend, terminal, editor, and session-management code; and working with the project’s Tauri, Tokio, TypeScript, bun, and Cargo setup.

They help the coding agent understand the application’s architecture and follow its language, platform, package-manager, and code-organization rules.

raum AGENTS.md — Instructions file by andremonaco

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/andremonaco/raum/agents-md

Clone the repo

git clone --depth 1 https://github.com/andremonaco/raum

Made for: Codex, OpenCode.

Per session 2,102 This file is loaded in full into every session.

When invoked 2,102 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.

Model	Per session	Once invoked
Fable 5	$0.02102	$0.02102
Opus 5	$0.01051	$0.01051
Sonnet 5	$0.00420	$0.00420
Haiku 4.5	$0.00210	$0.00210

Measured 2d ago against content hash 74d0713345bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

raum 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.

months), `rm -rf target/<subdir>` freely — the subdirs are fully

AGENTS.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

What is raum?

raum is a lightning-fast, recoverable terminal orchestrator for AI agent harnesses (Claude Code, Codex, OpenCode). Every pseudo-terminal runs inside a tmux session (-L raum socket) so the app can crash-restart without killing agents. Built with Tauri v2 (Rust backend), Solid.js (frontend), and xterm.js (terminal renderer). Target platforms: macOS and Linux.

Tech Stack

Layer	Technology
Desktop shell	Tauri v2
Backend language	Rust (edition 2024, MSRV 1.85, stable)
Frontend framework	Solid.js + TypeScript (ES2022)
Frontend build	Vite + bun
Styling	Tailwind CSS + Kobalte UI primitives + CVA
Terminal renderer	xterm.js (100 000-line scrollback)
Code editor	CodeMirror v6
Grid layout	custom BSP split-tree grid (`frontend/src/components/terminal-grid/`)
Async runtime	Tokio (full features)
File watching	notify (macOS kqueue)
Package manager	bun (frontend), Cargo workspace resolver v2

Repository Layout

crates/
  raum-core/       # shared types, config model, AgentAdapter trait, state machine
  raum-tmux/       # tmux session lifecycle, PTY output coalescer (4 ms quiet-gap / 16 ms max-hold / 128 KB flush)
  raum-hydration/  # worktree creation, copy/symlink manifests, path-pattern grammar
  raum-hooks/      # harness hook-script writer, Unix domain IPC socket server
src-tauri/
  src/
    lib.rs         # Tauri setup + command registration
    state.rs       # AppHandleState (ConfigStore, adapters, …)
    commands/      # Tauri IPC handlers: agent, config, files, hotkeys, layouts,
                   #   notifications, project, search, terminal, worktree
frontend/
  src/
    app.tsx        # root component, rehydrates runtime layout from TOML on launch
    stores/        # Solid.js reactive stores (agent, project, terminal, worktree, layout)
    components/    # UI tree: TopRow, Sidebar, TerminalGrid, TerminalPane, OnboardingWizard, …
    lib/           # keymapContext, notificationCenter, helpers
docs/              # quickstart, config reference, harness integration, release process
.github/workflows/ # ci.yml (lint + test), release.yml (release-plz + notarization)

Read the full file on GitHub · 146 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.

2d ago First seen · 146 lines · 2,102 tokens per session scan C 74d0713345bc

Subscribe to this mod's changes

raum AGENTS.md is an instructions file published in the GitHub repository andremonaco/raum (5 stars, last pushed 20d ago), licensed MIT. It adds 2,102 tokens to every session, about $0.0105 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.

Backend and APIs Frontend Languages

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

raum AGENTS.md