mx-cli SKILL.md skillB

mx-cli from bluechonk/modelmux is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add bluechonk/modelmux/mx-cli@git:20261107.bc11d30

Pins git:20261107.bc11d30 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
bluechonk/modelmux
Path
.agents/skills/mx-cli/SKILL.md
Versions recorded
9
Latest version
git:20261107.bc11d30, committed Nov 7, 2026
First version recorded
Oct 20, 2026
Size
10,665 bytes
Repository stars
11
License
MIT

modelmux 的 mx CLI 使用手册。用户要运行/查询/配置 mx(启动、重启、状态、模型、登录、账号池、额度、日志、Web 控制台、path),或不确定动词与渠道参数的顺序、该用 mx model list 还是 mx model <cid>、login 与 relogin 的区别时使用。也用于排查 mx 命令报错、未知选项、参数顺序写错(如 mx <cid> <动词>)的情况。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# mx CLI 使用

`mx` 是 modelmux 的仓库级 CLI。只有 `/v1/*` 请求经过本地网关(默认 `127.0.0.1:4412`):
`status` 探测网关,`bill` 直连上游账单,`login` / `relogin` 走渠道授权,
`model` / `acct` / `path` / `log` 读写本机或本机缓存。**不要假设所有命令都必须先起网关。**

## 0. 语法铁律

```text
mx <动词> [<cid>] [参数]        # 渠道动词
mx <组名> <子命令> [参数]        # 命令组
```

- 渠道动词永远在第一位,渠道 id 在第二位:`mx login catpaw`、`mx status catpaw`。
- 不要写 `mx catpaw status`:渠道名与动词共享位置会产生二义,补全器也无法工作。
- 仓库级动词(`start` / `stop` / `restart` / `serve` / `web`)不带 cid;
  `status` / `model` / `bill` / `acct` / `path` / `login` / `relogin` 都可以带 cid ——
  `mx status <cid>` 才是「某渠道的状态」。
- 命令组是「组名在前、子命令在后」:`mx model list` / `mx model usage`。
  这与「渠道动词在前」不冲突,是两类不同形态。
- `log` 也可以带 cid,但只有配 `--kind channel` 才有区别:
  `mx log catpaw --kind channel`(`--kind channel` 必须给 cid,否则报「日志不存在」)。
- 不确定时先 `mx --help`;脚本里加 `--json`。

## 1. 命令速查

**动作命令的唯一事实源就是本表。** 规则 / 契约 / 事实**不在此表**(那些在 `docs/`);
本表只回答「要做这件事,敲什么」。别处(README / docs / AGENTS.md)只指向本技能,不复述命令。

| 要做的事 | 命令 |
| --- | --- |
| 起网关(幂等) | `mx start`(启动失败恒非零退出;`--force` 已在跑也重启,`--wait <s>` 健康等待秒数) |
| 停 / 重启网关 | `mx stop` / `mx restart` |
| 前台调试运行 | `mx serve`(无监督直跑,不落 PID) |
| 看网关与全部渠道状态 | `mx status` |
| 看某渠道状态 | `mx status <cid>` |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add bluechonk/modelmux/mx-cli@sha256:7fdc9fb9829fb3a9

The line at the top of this page pins the label git:20261107.bc11d30, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_fqwp2x7hpom7fqll.svg)](https://markdownregistry.com/a/art_fqwp2x7hpom7fqll)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 9 versions of this file, between Oct 20, 2026 and Nov 7, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261107.bc11d30 latest2026-11-07 bc11d30 10,665 BB view · diff
git:20261106.f07736d2026-11-06 f07736d 8,752 BB view · diff
git:20261105.38debea2026-11-05 38debea 8,738 BB view · diff
git:20261103.352a1fb2026-11-03 352a1fb 8,491 BB view · diff
git:20261028.9c6fe012026-10-28 9c6fe01 8,542 BB view · diff
git:20261026.7bb88c82026-10-26 7bb88c8 8,008 BB view · diff
git:20261026.55f7c702026-10-26 55f7c70 8,334 BB view · diff
git:20261024.fa572872026-10-24 fa57287 8,344 BB view · diff
git:20261020.e20c3c82026-10-20 e20c3c8 6,340 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://127.0.0.1:4412)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10665 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

bluechonk/modelmux · 11 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_fqwp2x7hpom7fqll
GET https://markdownregistry.com/api/v1/resolve?ref=bluechonk/modelmux/mx-cli
GET https://markdownregistry.com/api/v1/blob/7fdc9fb9829fb3a9b10c679dccfe9292312d4faeba4432c04a4490515d6feb06

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from bluechonk/modelmux

claude-mx-test SKILL.md skill
bluechonk/modelmux · .agents/skills/claude-mx-test/SKILL.md · 用 Claude Code 对 modelmux(mx)网关做端到端测试(Anthropic Messages 协议,/v1/messages + count_tokens)。适用于:用 claude 测 mx、claude code…
git:20261107.0bf381d · audit B · 11 stars
codex-mx-test SKILL.md skill
bluechonk/modelmux · .agents/skills/codex-mx-test/SKILL.md · 用 Codex CLI 对 modelmux(mx)网关做端到端测试(OpenAI Responses 协议,/v1/responses)。适用于:用 codex 测 mx、codex 接入 modelmux、验证…
git:20261107.0bf381d · audit B · 11 stars
dsh-mx-test SKILL.md skill
bluechonk/modelmux · .agents/skills/dsh-mx-test/SKILL.md · 用 dsh(DeepSeek Harness)ACP 协议对 modelmux(mx)网关做端到端模型测试。适用于:用 dsh 测 mx、dsh 接入 modelmux、网关端到端验收、换 harness 复测模型、dsh…
git:20261106.f07736d · audit B · 11 stars
log-triage SKILL.md skill
bluechonk/modelmux · .agents/skills/log-triage/SKILL.md · modelmux 的日志排查与故障分诊流程。只要用户问“为什么这么慢 / 为什么失败 / 超时 / 卡住 / 网关挂了 / 日志在哪 / 怎么排查 / 看下日志”,或提到 request id、慢请求、502/503、stale…
git:20261106.f07736d · audit A · 11 stars
repo-sync SKILL.md skill
bluechonk/modelmux · .agents/skills/repo-sync/SKILL.md · modelmux 仓库的收尾与同步流程:把一轮代码改动同步到 docs 文档、规划进度与 commit 历史,并在需要上线时走完分支 → PR → CI → squash merge → 删分支的闭环。用户说「收尾」「同步文档」「更新…
git:20261105.29cf971 · audit A · 11 stars
zcode-session-archaeology SKILL.md skill
bluechonk/modelmux · .agents/skills/zcode-session-archaeology/SKILL.md · 按 session id 或项目路径还原另一个 ZCode 会话做了什么(模型、轮次、工具调用、错误、最终结论、产物),用于多会话并行改同一个项目时的对齐、排查与收尾。当用户提到「另一个会话」「session_xxx /…
git:20261025.1f96581 · audit A · 11 stars
AGENTS.md AGENTS.md file
bluechonk/modelmux · AGENTS.md
git:20261107.bd0e3d9 · audit A · 11 stars
AGENTS.md@docs AGENTS.md file
bluechonk/modelmux · docs/AGENTS.md
git:20261105.36a6b70 · audit A · 11 stars
AGENTS.md@packages/core/channels/catpaw AGENTS.md file
bluechonk/modelmux · packages/core/channels/catpaw/AGENTS.md
git:20261019.f7f08e1 · audit A · 11 stars

Every file in bluechonk/modelmux

Browse by kind, by grade B, or by owner.