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.
npx agentmods add instructions/talayash/agentrium/claude-mdgit clone --depth 1 https://github.com/talayash/agentriumWhat 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 | $0.02449 | $0.02449 |
| Opus 5 | $0.01224 | $0.01224 |
| Sonnet 5 | $0.00490 | $0.00490 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
agentrium CLAUDE.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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Agentrium (Agent Desktop Environment) is a cross-platform desktop application (Windows and macOS) for managing multiple Claude Code CLI terminal instances from a unified interface. Built with Tauri 2.x (Rust backend) and React 18 (TypeScript frontend), it provides tabbed and grid views of parallel Claude Code sessions with PTY-based terminal emulation. The release workflow produces NSIS/MSI installers for Windows and .dmg/.app bundles for both Apple Silicon and Intel Macs.
Current version: 1.33.0
Tech Stack
- Desktop framework: Tauri 2.x
- Backend: Rust (edition 2021)
- Frontend: React 18 + TypeScript + Vite
- Terminal emulation: xterm.js (
@xterm/xterm) with fit, search, and web-links addons - Styling: Tailwind CSS + Framer Motion. Flat IntelliJ IDEA 2026.1 "New UI"–style design: a 5-step elevation ramp (
--elevation-0..4CSS vars),#3574F0accent, Inter (UI) + JetBrains Mono (code). Supports dark/light/auto theme, user-set accent color, compact/comfortable/spacious density, UI font scale, and a "reduce motion" toggle that follows the OSprefers-reduced-motionsetting until explicitly overridden. Text tokens target WCAG AA contrast. (Not glassmorphic - translucency is limited to overlay scrims.) - State management: Zustand (persisted via
zustand/middleware/persist) - Database: SQLite via
rusqlite(bundled) - stores profiles, workspaces, session history - PTY:
portable-ptycrate for spawning Claude Code processes - Notifications:
notify-rustcrate for native desktop notifications (Windows Toast and macOS NSUserNotification) - Auto-updates:
tauri-plugin-updaterwith signed releases from GitHub
Project Structure
src/ # React frontend
App.tsx # Root component - layout, event listeners, setup wizard gate
main.tsx # React entry point
index.css # Tailwind base styles
components/
TitleBar.tsx # Custom frameless window titlebar
Sidebar.tsx # Terminal list sidebar with search
TerminalTabs.tsx # Tab bar for switching terminals
TerminalView.tsx # xterm.js terminal renderer
TerminalGrid.tsx # Multi-terminal grid view (up to 8)
TerminalSearch.tsx # Search within terminal output
NewTerminalModal.tsx # Create terminal dialog
ProfileModal.tsx # Create/edit configuration profiles
SettingsModal.tsx # App settings (args, updates, shortcuts)
HintsPanel.tsx # Claude Code command hints reference
SetupWizard.tsx # First-run setup (Node.js/Claude Code detection)
AutoUpdater.tsx # In-app update UI
WhatsNewModal.tsx # Post-update release notes popup
changelog.json # Structured release notes data for What's New modal
store/
terminalStore.ts # Terminal instances state (Map<id, {config, xterm}>)
appStore.ts # UI state (sidebar, grid, modals, settings)
updaterStore.ts # Auto-updater state
hooks/
useKeyboardShortcuts.ts # Global keyboard shortcut handler
useNotification.ts # Desktop notification hook
src-tauri/ # Rust backend
src/
main.rs # Tauri app setup, plugin registration, state init
terminal.rs # TerminalManager - PTY lifecycle (create, write, resize, close)
commands.rs # Tauri IPC commands (all #[command] handlers)
config.rs # ConfigProfile struct, HintCategory/Hint structs, default hints
database.rs # SQLite database (profiles, workspaces, session_history tables)
tauri.conf.json # Tauri config (window, bundling, updater, plugins)
Cargo.toml # Rust dependencies
capabilities/default.json # Tauri security capabilities
.claude/commands/
publish.md # /publish slash command - full release workflow
.github/workflows/release.yml # CI: build + publish GitHub releases (tag-triggered)
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 · 157 lines · 2,449 tokens per session scan A a1296e507dc8
agentrium CLAUDE.md is an instructions file published in the GitHub repository talayash/agentrium (39 stars, last pushed 2d ago), licensed MIT. It adds 2,449 tokens to every session, about $0.0122 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.
Other instructions, from other repositories
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
cherry-studio AGENTS.md
AGENTS.md instructions for CherryHQ/cherry-studio, a project described as: AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs.
easy-vibe AGENTS.md
AGENTS.md instructions for datawhalechina/easy-vibe, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
tree-sitter-analyzer CLAUDE.md
Instructions for aimasteracc/tree-sitter-analyzer, covering ruflo — claude code configuration, rules, test quality rules — locked (2026-06-28), t-1: no new test files for existing plugins (blocker) and t-2: no weak assertions — ratchet-enforced (blocker).
nezha AGENTS.md
AGENTS.md instructions for hanshuaikang/nezha, covering nezha — agents.md, 项目概述, 开发命令, 架构设计 and 前端(src/).