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 commands/wowoyong/agent-mux/mux-setupgit clone --depth 1 https://github.com/wowoyong/agent-muxWrote 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/commands/wowoyong/agent-mux/mux-setup)<a href="https://agentmods.dev/commands/wowoyong/agent-mux/mux-setup"><img src="https://agentmods.dev/badge/commands/wowoyong/agent-mux/mux-setup.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 | $0.00012 | $0.03877 |
| Opus 5 | $0.00006 | $0.01938 |
| Sonnet 5 | $0.00002 | $0.00775 |
| Haiku 4.5 | $0.00001 | $0.00388 |
Grade A, and why
mux-setup 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 — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mux-setup — agent-mux 초기 설정 마법사
이 커맨드는 사용자의 Claude + Codex 구독 조합을 파악하여 최적의 라우팅 설정을 자동 생성하는 대화형 마법사입니다.
Step 1: 환경 확인
MCP 도구 get_mux_status를 호출하여 현재 상태를 확인합니다. 호출이 실패하면 Bash로 직접 확인합니다.
command -v codex && codex --version 2>&1
확인 결과를 아래 형식으로 표시합니다:
[agent-mux] ═══ Agent Mux Setup Wizard ═══
환경 확인 중...
✓ Codex CLI: installed (v{version})
✓ Node.js: {node_version}
✓ agent-mux MCP: ready
Codex CLI가 설치되지 않은 경우:
[agent-mux] ═══ Agent Mux Setup Wizard ═══
환경 확인 중...
✗ Codex CLI: not installed
✓ Node.js: {node_version}
─────────────────────────────
Codex CLI가 필요합니다.
설치: npm install -g @openai/codex
설치 후 /mux-setup 을 다시 실행하세요.
─────────────────────────────
Codex CLI가 없으면 여기서 중단합니다. 사용자가 설치 후 다시 실행하도록 안내합니다.
Step 2: Claude 구독 선택
아래 메시지를 표시하고 사용자의 입력을 기다립니다:
[1/4] Claude Code 구독 플랜을 선택해주세요:
1) Pro $20/mo — ~45 messages / 5hr window
→ 기본 플랜. 메시지 절약이 핵심.
2) Max 5x $100/mo — ~225 messages / 5hr window
→ 중간 용량. Claude와 Codex 균형 사용 가능.
3) Max 20x $200/mo — ~900 messages / 5hr window
→ 대용량. Claude 중심 라우팅 + Codex 보조.
선택 (1/2/3):
사용자가 1, 2, 3 중 하나를 입력할 때까지 기다립니다. 유효하지 않은 입력이면 다시 물어봅니다.
Step 3: Codex 구독 선택
아래 메시지를 표시하고 사용자의 입력을 기다립니다:
[2/4] Codex CLI 구독 플랜을 선택해주세요:
1) Plus $20/mo — ~200 tasks/day, 1 concurrent, 10min timeout
→ 기본 플랜. 순차 실행.
2) Pro $200/mo — unlimited tasks, 3 concurrent, 30min timeout
→ 파워 플랜. 병렬 실행 + 무제한 태스크.
선택 (1/2):
사용자가 1 또는 2를 입력할 때까지 기다립니다.
Step 4: 티어 결정 + 요약
사용자의 구독 조합을 아래 매핑 표에 따라 티어로 변환합니다:
| Claude Plan | Codex Plan | Tier | Monthly Cost | 설명 |
|---|---|---|---|---|
| Pro $20 | Plus $20 | budget | $40/mo | 최소 비용. Codex 우선, Claude 절약 |
| Max 5x $100 | Plus $20 | standard | $120/mo | 균형 라우팅. 병렬 디스패치 |
| Max 20x $200 | Plus $20 | premium | $220/mo | Claude 중심. 태스크 분해 활성화 |
| Max 20x $200 | Pro $200 | power | $400/mo | 풀 오케스트레이션. 파이프라인 모드 |
| Pro $20 | Pro $200 | budget | $220/mo | budget 라우팅 + power Codex |
| Max 5x $100 | Pro $200 | standard | $300/mo | standard 라우팅 + power Codex |
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 · 547 lines · 12 tokens per session scan A 3740820c3410
mux-setup is a command published in the GitHub repository wowoyong/agent-mux (1 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 3,877 once invoked, about $0.0001 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 commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
whats-next
Show current project status and suggest next steps.
review
Run a Codex code review of your working tree or a branch (read-only).
explore
Fast codebase exploration with Antigravity's agy CLI (Gemini 3.7 Flash, read-only). EXPERIMENTAL.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
delegate
Delegate a coding task to the Cursor CLI agent (Composer by default).