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/epilande/ccmux/agents-mdgit clone --depth 1 https://github.com/epilande/ccmuxWrote 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/epilande/ccmux/agents-md)<a href="https://agentmods.dev/instructions/epilande/ccmux/agents-md"><img src="https://agentmods.dev/badge/instructions/epilande/ccmux/agents-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 | $0.06277 | $0.06277 |
| Opus 5 | $0.03138 | $0.03138 |
| Sonnet 5 | $0.01255 | $0.01255 |
| Haiku 4.5 | $0.00628 | $0.00628 |
Grade A, and why
ccmux 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 4d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
ccmux is a CLI tool for tracking AI coding agent sessions running in tmux panes and jumping to the one that needs you. It uses a background daemon that detects agent processes, watches log files, and scans terminal output to derive session state. An interactive TUI shows live session states at a glance.
Built-in agents: Claude Code, Codex, Cursor, OpenCode, Pi, oh-my-pi (omp), Antigravity, Copilot, Gemini CLI, plus custom agent definitions via config.
Tech Stack
- Runtime: Bun 1.x
- Language: TypeScript 5.x
- TUI Framework: @opentui/solid 0.1.97 (Solid.js-based terminal UI)
- Reactivity: Solid.js 1.9
- File Watching: native recursive
fs.watchfor the agent log trees (log-tree-watcher.ts; chokidar fallback when recursive watching is unavailable), chokidar 4.x for the small flat dirs (markers, Claude subagents); stat-polling for agents that hold their log fd open (codex), whose appendsfs.watchcannot see - CLI Framework: Commander 14.x
Development Guidelines
- Always use
buninstead ofnpmfor all package management and script execution - Avoid
as anytype casts. Use proper types, generics, oras unknown as Tonly when source types have a genuine gap - Use
ccmux showto check session status and see active tmux panes - You can run
tmuxandccmuxcommands directly to test features end to end (e.g.,ccmux screen,ccmux send,ccmux spawn,tmux list-panes,tmux send-keys)
Verifying TUI changes
Typecheck and bun test verify code correctness, not rendering correctness. After any change touching TUI components, columns, layout, theming, or the daemon→TUI data path, you MUST launch the picker and/or sidebar and capture the output before declaring the work done. Non-rendering CLI commands (ccmux show, ccmux config get/set) do not exercise the renderer.
Always test in a detached, isolated tmux session. Do not launch the picker in a window/pane inside the user's active session.
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.
- 4d ago First seen · 226 lines · 6,277 tokens per session scan A 6576ef8a2132
ccmux AGENTS.md is an instructions file published in the GitHub repository epilande/ccmux (151 stars, last pushed 4d ago), licensed MIT. It adds 6,277 tokens to every session, about $0.0314 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
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
bread CLAUDE.md
Instructions for tjakoen/bread, covering claude.md — start here, what this is, start here (reading order), this repo is the stack's control plane — run it and non-negotiables (see conventions for the full rules).
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
rosetta command-versions-vs-presence.instructions.md
Instructions for tikoci/rosetta, a project described as: MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik.
titen CLAUDE.md
Instructions for RamaAditya49/titen, covering claude.md, read agents.md first, commands, two runtimes, one core and publishing to npm.
sandy CLAUDE.md
Instructions for jamestelfer/sandy, covering claude.md, voice, what is sandy, project layout and dev commands.