Agent skill

Cm Runtime

by kingxiaozhe in kingxiaozhe/cm-workflow

用户要查看或切换 CM 自动派发偏好、单/双 AI 声明、谁写谁审,或修改用户级运行时默认时使用。只管理运行时声明,不安装工具、不测试配额、不接管正在运行的任务。

MITAuto-check passed

Install Cm Runtime

skills CLI
$ npx skills add kingxiaozhe/cm-workflow --skill cm-runtime -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kingxiaozhe/cm-workflow cm-runtime --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kingxiaozhe/cm-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cm-runtime .claude/skills/cm-runtime && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cm-runtime
GitHub stars
104
Token cost
~931 tokens
SKILL.md length
234 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

用户要查看或切换 CM 自动派发偏好、单/双 AI 声明、谁写谁审,或修改用户级运行时默认时使用。只管理运行时声明,不安装工具、不测试配额、不接管正在运行的任务。

  • Works in 4 steps: 改哪一层?/ Which scope? [1] 当前项目 / Current… → 你手上有哪个 AI 工具?/ Which AI tools do you have? → 执行只读 preview --project "{代码项目路径}";用户范围用… → …
  • Calls node

What it does

Cm Runtime is an agent skill from kingxiaozhe/cm-workflow. 用户要查看或切换 CM 自动派发偏好、单/双 AI 声明、谁写谁审,或修改用户级运行时默认时使用。只管理运行时声明,不安装工具、不测试配额、不接管正在运行的任务。

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Codex-native, spec-driven AI Agent workflow with Claude Code compatibility, independent review, QA, fixes, and refactors. The licence is MIT.

Example prompts

  • “/cm-runtime”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 改哪一层?/ Which scope? [1] 当前项目 / Current project(显示检测到的配置路径)
  2. 你手上有哪个 AI 工具?/ Which AI tools do you have?
  3. 执行只读 preview --project "{代码项目路径}";用户范围用 preview --user,
  4. 只有用户明确同意才调用相同项目、范围、预设、语言和运行时环境的

What it can do on your machine

Read from SKILL.md and the folder at commit 971c231. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cm Runtime loads about 931 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 234 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~931

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from kingxiaozhe/cm-workflow at commit 971c231, republished under its MIT licence (© kingxiaozhe). 234 words, ~931 tokens.

Download SKILL.mdSave it as .claude/skills/cm-runtime/SKILL.md (or your agent's skills folder).
name
cm-runtime
description
用户要查看或切换 CM 自动派发偏好、单/双 AI 声明、谁写谁审,或修改用户级运行时默认时使用。只管理运行时声明,不安装工具、不测试配额、不接管正在运行的任务。

cm-runtime — 运行时声明

执行前读取 ../../runtime/project-context.md、../../runtime/workflow-config.md 与 ../../runtime/logging.md。Codex 入口 $cm-runtime;Claude Code 入口 /cm-runtime, macOS/Linux 兼容别名 /cm:runtime。这是独立配置工具,不进入 N1–N8,不创建业务任务。

从当前 Skill 目录解析 {CM_WORKFLOW_ROOT}。无参数调用时,不直接启动依赖 TTY 的脚本; 由当前会话用 AskUserQuestion 或纯文本完成下列流程。使用用户当前对话语言, 中文对话用中文、英文对话用英文,编号、含义与终端一致;文案以 ../../scripts/cm-runtime-i18n.mjs 为准,预设名与机器字段不翻译。

先执行只读 show --project "{代码项目路径}",展示有效配置、来源及模型别名,再给出: [1] 保留当前配置(推荐,默认) / Keep current configuration (recommended, default)、 [2] 修改运行时预设 / Change runtime preset、 [3] 查看高级模型配置说明 / Advanced model configuration。 选 1 结束,未声明时保留内置默认,不创建文件。选 3 只展示下述高级说明,不接着询问模型或预设。 配置无效时报告原始字段/路径错误、保留文件并结束,不能把无效配置说成默认有效或自动修复。 只有明确选 2 才进入修改:

  1. 改哪一层?/ Which scope? [1] 当前项目 / Current project(显示检测到的配置路径) [2] 用户级默认 / User default(~/.cm-workflow/runtimes.yml)。有项目配置默认 1, 无配置默认 2;无配置仍选 1 时,提示将从模板新建 .cm-workflow.yml。
  2. 你手上有哪个 AI 工具?/ Which AI tools do you have? [1] 只有 Codex / Codex only [2] 只有 Claude / Claude only [3] 两个都有 / Both。 此问无默认,必须选择;选 3 再问:谁写代码?/ Who writes code? [1] Codex(Claude 审,推荐)/ Codex (Claude reviews, recommended) [2] Claude(Codex 审)/ Claude (Codex reviews),默认 1。
  3. 执行只读 preview <preset> --project "{代码项目路径}";用户范围用 preview <preset> --user, 工作目录必须是代码项目根,以便核对该项目的覆盖关系。可加 --json 读取结构化结果。 展示目标文件/范围、字段前后值、当前项目保存前后的有效值及模型兼容性提示,保留返回的 preview_sha256,询问确认 / Confirm? [y/N],默认不保存。
  4. 只有用户明确同意才调用相同项目、范围、预设、语言和运行时环境的 set ... --expect-preview <preview_sha256>。不得用普通 set 绕过摘要校验。 配置漂移或校验失败时保留文件,重新预览并取得新的确认,不沿用旧批准。 成功后执行 show --project "{代码项目路径}" 并回显。

工具选 1/2 分别映射 codex-only/claude-only;两个都有、写代码选 1/2 分别映射 codex-codes/claude-codes。取消、拒绝确认或必选问题连续三次空输入时放弃,不写。 会话没有回复不代表回车或确认,不得因等待超时执行;选择了修改也不等于批准保存。 用户声明被项目覆盖时如实报告当前项目不会切换。摘要仅用于预览一致性,不是用户授权证据。

显式自然语言“看看配置”映射 show。带 show / set / unset 参数直接执行, 修改意图缺少预设/范围时只补问缺失项。执行示例:

bash
node "{CM_WORKFLOW_ROOT}/scripts/cm-runtime.mjs" show --project "{代码项目路径}"
node "{CM_WORKFLOW_ROOT}/scripts/cm-runtime.mjs" preview codex-codes --project "{代码项目路径}"
node "{CM_WORKFLOW_ROOT}/scripts/cm-runtime.mjs" set codex-codes --project "{代码项目路径}" --expect-preview "{preview_sha256}"
node "{CM_WORKFLOW_ROOT}/scripts/cm-runtime.mjs" set codex-codes --project "{代码项目路径}"
node "{CM_WORKFLOW_ROOT}/scripts/cm-runtime.mjs" set --user claude-codes
node "{CM_WORKFLOW_ROOT}/scripts/cm-runtime.mjs" unset --user
  • 四个预设为 codex-only、claude-only、codex-codes、claude-codes;映射以共享配置合同为准。
  • show 只读,打印有效声明、预设、coder/reviewer adapter、source、model 与 runtimes_source、声明路径;CLI 缺失只 WARN,可解析不证明配额可用。
  • preview 只读、不记日志,复用同一配置校验;摘要绑定项目、范围、预设、候选内容和相关配置快照(含继承来源及新建模板)。终端向导和安装器同样在保存前核对快照。
  • set 默认项目级;只修改 runtimes.available 与 coder/reviewer 的 adapter/source,其他原文保留;新文件从模板生成。校验失败不写。
  • set --user 写 ~/.cm-workflow/runtimes.yml(测试可用 CM_WORKFLOW_HOME 指定目录);unset --user 删除该文件,不删除项目声明。
  • 解析顺序:项目 > 用户级默认 > 未声明;项目显式角色字段保留,冲突阻断。用户默认仅在项目没有 runtimes.available 时读取。
  • 成功 set 复用统一日志 writer 写 decision/route;日志使用独立 run id,不绑定 specs、不改已有 run 指针。show 不记日志。

高级说明:建议保留当前默认,仅有明确需要时手工编辑项目配置中的模型别名,并执行 node "{CM_WORKFLOW_ROOT}/scripts/cm-workflow-config.mjs" --project "{代码项目路径}" --print-effective。 详见 ../../runtime/workflow-config.md。预设切换保留模型;更换 adapter 后,旧的非默认模型未必兼容。 校验仅证明配置合同有效,不证明 provider 支持、可调用或配额可用。这里不提供任意模型编辑器。 unset --user 只删除用户默认,项目声明仍优先;它不是恢复所有配置默认值的命令。

报告命令原始结果、写入路径、预设与来源;失败报告原因。若提示“preference saved, decision log failed”,明确配置已写、日志未成功,不伪称完全成功。

只改变新 run 的自动派发偏好;已创建 run 绑定其原配置,本命令不修改它们。 不执行安装、不改 settings、CLAUDE.md、任务状态或审查证据,不联网、不调用模型、不探测配额。

© kingxiaozhe, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/cm-runtime of kingxiaozhe/cm-workflow.

Open the folder on GitHubat commit 971c231

More from kingxiaozhe/cm-workflow

All 23 skills in this repo
  • Cm AI

    kingxiaozhe/cm-workflow

    用户明确说“规格已确认,开始实现”或要求按已审批 CM specs 开发时使用。新任务默认由 JS workflow 驱动 N1-N8,完成开发、独立审查、QA 与文档同步;模糊点子、未审规格和单独一句“继续”不能触发编码批准。

    104 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Cm Check

    kingxiaozhe/cm-workflow

    用户说“检查工作流是否安装正确”“为什么找不到 cm 命令”时使用。默认查询 npm 稳定版,有新版自动升级已管理的 CM 安装,再检查插件、核心 Skills、兼容包装与模板引用;不测试或修改业务代码。

    104 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Cm Fix

    kingxiaozhe/cm-workflow

    用户说“修复这个可复现 bug”或要求根据失败报告修代码时使用。执行红灯测试、根因定位、最小修复、独立审查和回归;尚未确认的问题先用 cm-test,新功能和架构重设计转交 cm-prd。

    104 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Cm Idea

    kingxiaozhe/cm-workflow

    用户说“我有个点子”“帮我梳理产品”或需要先聊清目标时使用。通过逐题访谈整理为可交给 cm-prd 的 PRD;已有明确需求文档时改用 cm-prd,不写代码、不拆开发任务。

    104 GitHub stars~419 tokensUpdated yesterday
    Auto-check passed
  • Cm Init

    kingxiaozhe/cm-workflow

    用户说“第一次接管这个项目”“分析仓库并生成项目规则”时使用。分析已有代码并生成 Codex AGENTS.md 与 CM/Claude 兼容规则;仅适用于非空存量项目,不创建脚手架、不承接普通代码修改。

    104 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Cm Miniprogram Engineer

    kingxiaozhe/cm-workflow

    微信小程序开发工程师 Skill,执行小程序开发任务,自动适配项目技术栈(原生小程序/Taro/uni-app 等),支持 Figma/Stitch 设计稿还原与云开发

    104 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Cm Runtime

What does Cm Runtime do?

用户要查看或切换 CM 自动派发偏好、单/双 AI 声明、谁写谁审,或修改用户级运行时默认时使用。只管理运行时声明,不安装工具、不测试配额、不接管正在运行的任务。. Cm Runtime is an agent skill from kingxiaozhe/cm-workflow.

How do I install Cm Runtime in Claude Code?

Run `npx skills add kingxiaozhe/cm-workflow --skill cm-runtime -a claude-code`. Or copy the skill folder (skills/cm-runtime in kingxiaozhe/cm-workflow) into .claude/skills/cm-runtime in your project. Claude Code loads it when a task matches its description.

How do I install Cm Runtime in Codex?

Run `npx skills add kingxiaozhe/cm-workflow --skill cm-runtime -a codex`. Or copy the skill folder (skills/cm-runtime in kingxiaozhe/cm-workflow) into .agents/skills/cm-runtime in your project. Codex loads it when a task matches its description.

Can I use Cm Runtime in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kingxiaozhe/cm-workflow --skill cm-runtime -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cm-runtime, .gemini/skills/cm-runtime, .github/skills/cm-runtime and .opencode/skills/cm-runtime in your project.

What does Cm Runtime need to run?

Going by SKILL.md and its folder, Cm Runtime needs the command-line tools its instructions call (node).

Does Cm Runtime access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cm Runtime safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cm Runtime use?

Cm Runtime is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cm Runtime use?

About 931 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

Who maintains Cm Runtime?

kingxiaozhe (a GitHub user) maintains it in kingxiaozhe/cm-workflow, which has 104 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 6, 2026.

Source: kingxiaozhe/cm-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.