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.
git 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-config)<a href="https://agentmods.dev/commands/wowoyong/agent-mux/mux-config"><img src="https://agentmods.dev/badge/commands/wowoyong/agent-mux/mux-config/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/wowoyong/agent-mux/mux-config"><img src="https://agentmods.dev/badge/commands/wowoyong/agent-mux/mux-config.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00011 | $0.02479 |
| Opus 5 | $0.00005 | $0.01239 |
| Sonnet 5 | $0.00002 | $0.00496 |
| Haiku 4.5 | $0.00001 | $0.00248 |
Grade A, and why
mux-config scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mux-config command
View or modify the routing configuration stored in .agent-mux/config.yaml.
Usage
/mux-config-- show current configuration/mux-config set <key> <value>-- update a specific setting/mux-config reset-- reset configuration to tier defaults
Implementation Steps
Step 1: Parse the subcommand
Look at the user's input after /mux-config:
- No arguments → show config
set <key> <value>→ update settingreset→ reset to defaults
Step 2: Locate the config file
The config file is at .agent-mux/config.yaml relative to the project root.
# Find the project root (where .agent-mux/ lives or should live)
PROJECT_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
CONFIG_DIR="$PROJECT_ROOT/.agent-mux"
CONFIG_FILE="$CONFIG_DIR/config.yaml"
Show current config (/mux-config)
- Read
.agent-mux/config.yamlfrom the project root using the Read tool. - If the file does not exist, inform the user and show default configuration for the Budget tier.
- Parse the YAML content and display it in this exact format:
[agent-mux] ═══ Configuration ═══
Config file: .agent-mux/config.yaml
Tier: {tier}
Routing:
engine: {local|hybrid}
bias: {codex|balanced|claude|adaptive}
split: Claude {claude_pct}% / Codex {codex_pct}%
Escalation:
enabled: {true|false}
strategy: {fix|fix_then_redo|full}
max_retries: {n}
Features:
batch_mode: {on|off}
conservation_mode: {on|off}
parallel_dispatch: {on|off}
task_decomposition: {on|off}
Budget Warnings: {thresholds}
Deny List:
{deny_list_entries, one per line}
═══════════════════════════════
For features, check these YAML keys:
batch_mode.enabled→ batch_modeconservation.enabled→ conservation_modeparallel_dispatch.enabled→ parallel_dispatch (default: off unless Standard+ tier)task_decomposition.enabled→ task_decomposition (default: off unless Premium+ tier)
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.
- 9d ago First seen · 357 lines · 11 tokens per session scan A 2dfd49fb11be
mux-config is a command published in the GitHub repository wowoyong/agent-mux (1 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 2,479 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.
ccc-orchestrate
Sequential and tmux/worktree orchestration guidance for multi-agent workflows.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.