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/pranav7/domux/claude-mdgit clone --depth 1 https://github.com/pranav7/domuxWrote 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/pranav7/domux/claude-md)<a href="https://agentmods.dev/instructions/pranav7/domux/claude-md"><img src="https://agentmods.dev/badge/instructions/pranav7/domux/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 5.1 | $0.01935 | $0.01935 |
| Opus 5 | $0.00967 | $0.00967 |
| Sonnet 5 | $0.00387 | $0.00387 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
domux 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 5d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build & test
go build # produces ./domux
go test ./... # run all tests
go test -run TestX # single test
go vet ./...
Single-package layout (package main) — no module subdirs. Go 1.22.
Architecture
Two surfaces, one binary. main.go dispatches: bare domux (or flags like --path/--list) goes through flag.Parse then runTUI; anything starting with a non-- arg routes through runCommand in commands.go to subcommands (start, attach, sessions, clear, install, ai-state, …).
Context resolution is the spine. Every command path funnels through resolveDomuxContext(cwd) in session.go. It tries the current tmux session first (resolveDomuxContextForSession), falling back to path-based lookup. Session state, when present, pins a session to a Root (git worktree root) so the TODO file stays attached even after cd into subdirs. The returned DomuxContext carries Session, Root, TodoPath, and State.
Storage layout (all under $HOME):
~/.local/share/domux/by-path/<sanitized-root>.md— markdown TODO file per worktree root./→%2F. Seeresolver.go.~/.local/share/domux/sessions/<session>.json—SessionState(root, todo_path, focused id, label, server, workspace, AI map). Seesession.go.~/.config/domux/domux.tmux— generated tmux integration written bydomux install tmux.
Legacy dotfile bridge. mergeLegacyState in session.go reads ~/.tmux-label-*, .tmux-server-*, .tmux-workspace-*, .tmux-claude-*, .tmux-codex-* and folds them into SessionState on load. setAIState, labelCommand, etc. also write these legacy files so old tmux configs keep working. Don't remove the legacy writes without a migration plan.
AI state model. state.AI is map[string]string keyed agent:pane (e.g. claude:1_0, codex:default). aggregateAIStatesFromSession collapses per-pane entries into AIStates{Claude, Codex} with WAITING winning over CLAUDING/CODEXING. normalizeAIState is the single source of truth for value canonicalization — go through it.
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.
- 5d ago First seen · 52 lines · 1,935 tokens per session scan A 1b808b940361
domux CLAUDE.md is an instructions file published in the GitHub repository pranav7/domux (5 stars, last pushed today), licensed MIT. It adds 1,935 tokens to every session, about $0.0097 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 2026-08-31.
Other instructions, from other repositories
libtmux-go AGENTS.md
AGENTS.md instructions for libtmux/libtmux-go, covering agents.md, what is here, which policy applies, change discipline and references.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
liney AGENTS.md
AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.
superset AGENTS.md
AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.