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/flplima/tmuxy/claude-mdgit clone --depth 1 https://github.com/flplima/tmuxyWrote 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.
[](https://agentmods.dev/instructions/flplima/tmuxy/claude-md)<a href="https://agentmods.dev/instructions/flplima/tmuxy/claude-md"><img src="https://agentmods.dev/badge/instructions/flplima/tmuxy/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.04935 | $0.04935 |
| Opus 5 | $0.02468 | $0.02468 |
| Sonnet 5 | $0.00987 | $0.00987 |
| Haiku 4.5 | $0.00494 | $0.00494 |
Grade A, and why
tmuxy 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 today.
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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tmuxy
A web-based tmux interface built with React (Vite) frontend and Rust backend.
This project is under active development, not production. Breaking changes are welcome. No backwards compatibility required — delete, rename, and restructure freely.
See docs/ARCHITECTURE.md for high-level system overview and component interaction.
See docs/STATE-MANAGEMENT.md for frontend XState and backend Rust state details.
See docs/DATA-FLOW.md for SSE/HTTP protocol, Tauri IPC, and deployment scenarios.
See docs/TMUX.md for control mode routing, version-specific bugs, workarounds, and the @tmuxy-* window/pane tag schema.
See docs/COPY-MODE.md for the client-side scrollback rendering and native browser scrolling in copy mode.
See docs/SECURITY.md for security risks, mitigations, and deployment warnings.
See docs/TESTS.md for testing guidelines and principles.
See docs/NON-GOALS.md for what tmuxy intentionally does NOT do.
See docs/RICH-RENDERING.md for terminal image/OSC protocol support.
See docs/PERFORMANCE.md for speed measurement: core/render processing (Axis A) vs transport (Axis B).
See docs/TELEMETRY.md for unified cross-layer action tracing into a single local NDJSON file (design: schema, seams, redaction boundary, phased plan).
Project Structure
tmuxy/
├── packages/
│ ├── tmuxy-core/ # Rust: tmux control mode, parsing, state
│ ├── tmuxy-server/ # Rust: server (SSE, HTTP, embedded frontend, dev mode)
│ ├── tmuxy-ui/ # React/Vite frontend
│ │ └── src/tmux/demo/ # In-browser demo engine (DemoAdapter, DemoTmux, LifoShell)
│ ├── tmuxy-demo/ # Next.js demo site (static export → GitHub Pages)
│ ├── tmuxy-wasm/ # Rust: wasm-bindgen facade over tmuxy-core (browser-side parsing)
│ ├── tmuxy-connect/ # Rust: standalone "add a server" TUI form (tmuxy connect)
│ ├── tmuxy-tree/ # Rust: standalone sidebar tree TUI (tmuxy tree)
│ └── tmuxy-tauri-app/ # Tauri desktop app wrapper
├── bin/
│ ├── tmuxy-cli # Shell dispatcher (symlinked as ~/.local/bin/tmuxy)
│ └── tmuxy/ # Shell scripts for floats, groups, widgets
├── tests/ # E2E tests (Jest + Playwright)
│ ├── helpers/ # Test helpers, one module per domain
│ └── *.test.js # Test suites grouped by operation
└── docs/ # Project documentation
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.
- today Changed · +17 lines · +384 tokens per session 3d2e41833782
- 3d ago First seen · 261 lines · 4,551 tokens per session scan A 898397c423ea
tmuxy CLAUDE.md is an instructions file published in the GitHub repository flplima/tmuxy (82 stars, last pushed yesterday), licensed MIT. It adds 4,935 tokens to every session, about $0.0247 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 2026-09-01.
Other instructions, from other repositories
agent-of-empires AGENTS.md
AGENTS.md instructions for agent-of-empires/agent-of-empires, covering repository guidelines, where to look, commands, code rules and tests.
psmux AGENTS.md
AGENTS.md instructions for psmux/psmux, covering agent instructions and test isolation.
CommandMate CLAUDE.md
Claude Code instructions for Kewton/CommandMate, covering claude.md, ⚠️ 重要: モジュール詳細を claude.md に書かないこと, プロジェクト概要, 基本情報 and 技術スタック.
terminal-use CLAUDE.md
Instructions for flipbit03/terminal-use, covering terminal-use (tu), build & test, architecture, conventions and git commits.
CommandMate AGENTS.md
AGENTS.md instructions for Kewton/CommandMate, covering agents.md, scope, project context, working principles and coding rules.
remobi AGENTS.md
Instructions for connorads/remobi, covering remobi, architecture, stack, key commands and local development.