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/muxgit 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)<a href="https://agentmods.dev/commands/wowoyong/agent-mux/mux"><img src="https://agentmods.dev/badge/commands/wowoyong/agent-mux/mux.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 | $0.00013 | $0.01234 |
| Opus 5 | $0.00006 | $0.00617 |
| Sonnet 5 | $0.00003 | $0.00247 |
| Haiku 4.5 | $0.00001 | $0.00123 |
Grade A, and why
mux 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mux command
Parse the user's input and execute the mux routing workflow.
Input format
/mux "task description" [--dry-run] [--verbose] [--route=claude|codex] [--auto-apply] [--confirm]
Steps
1. Parse input
Extract the task description (quoted string) and any flags from the user's input.
Available flags:
--dry-run: Analyze and show routing decision without executing--verbose: Show detailed signal analysis--route=claude|codex: Force routing to a specific CLI--auto-apply: Skip confirmation for Codex results (deny-list files still require approval)--confirm: Show diff before applying Codex results (default: ON)
2. Check budget
Call get_mux_status MCP tool to retrieve:
- Current tier (budget/standard/premium/power)
- Claude messages used and estimated total
- Codex tasks used and estimated total
- Budget recommendation (normal/conserve/codex_only/queue)
- Any running tasks
If budget recommendation is codex_only, force route to Codex unless --route=claude is explicitly set.
If budget recommendation is queue, warn the user that both CLIs are near capacity.
3. Analyze the task
Determine routing using the 2-Phase decision process:
Phase 1 -- Hard Rules (check in priority order):
- Task needs MCP tools (database queries, API calls, web fetch) -> Claude
- Task requires interactive dialogue or follow-up questions -> Claude
- Task needs previous conversation context -> Claude
- Task is a standalone security audit (single file/module) -> Codex
- Task is refactoring affecting >5 files -> Claude
- Task is scaffolding (project/module structure creation) -> Claude
Phase 2 -- Weighted Scoring (only if no hard rule matched):
- Extract keyword signals from task description using pattern matching
- Compute weighted score from all detected signals
- Apply interaction modifiers for signal combinations
- Factor in budget status (at Budget tier, ties go to Codex)
- Determine target and confidence percentage
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 · 125 lines · 13 tokens per session scan A 110425188120
mux is a command published in the GitHub repository wowoyong/agent-mux (1 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 1,234 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.
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.
review-skills
Review changed skills: automated bash checks + 9 structural dimensions (D1-D9) + 5 intent checks (M1-M5). PASS/FAIL verdict. Fix in-place.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
theme
Switch between visual theme skins — OLED Black, Matrix, Claude Anthropic, Surprise Me.