workflow-runner

workflow-runner is a skill for Claude Code from Leodorareluctant259/superpowers-zh. It costs 61 tokens per session (1,701 once invoked), scanned A, a copy of workflow-runner, MIT.

A workflow runner that reads agency-orchestrator YAML files and carries out their steps inside Claude Code, OpenClaw, or Cursor. A YAML workflow is a text file describing inputs, roles, tasks, and their order.

In plain words
What is it for?
It runs supplied YAML workflows and supports tasks where multiple roles collaborate, such as having a product manager and architect review a product document.
Why use it?
It lets several defined roles work through a task in one current AI session without separately configuring an API key. It also checks that required role definitions are available before starting.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; built for openclaw.

Part of the superpowers-zh plugin — 20 skills, 3 commands, 1 agent, 1 hook shipped together

Good fit It runs supplied YAML workflows and supports tasks where multiple roles collaborate, such as having a product manager and architect review a product document.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leodorareluctant259/superpowers-zh/workflow-runner
Install

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.

Any agent
npx skills add Leodorareluctant259/superpowers-zh --skill workflow-runner
Clone the repo
git clone --depth 1 https://github.com/Leodorareluctant259/superpowers-zh

Made for: Claude Code.

Or install superpowers-zh, the plugin that ships this one along with the rest of its 20 skills, 3 commands, 1 agent, 1 hook.

Wrote 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.

agentmods badge for workflow-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/leodorareluctant259/superpowers-zh/workflow-runner.svg)](https://agentmods.dev/skills/leodorareluctant259/superpowers-zh/workflow-runner)
Your own site
<a href="https://agentmods.dev/skills/leodorareluctant259/superpowers-zh/workflow-runner"><img src="https://agentmods.dev/badge/skills/leodorareluctant259/superpowers-zh/workflow-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,701 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 92% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.01701
Opus 5 $0.00030 $0.00851
Sonnet 5 $0.00012 $0.00340
Haiku 4.5 $0.00006 $0.00170

Measured 8d ago against content hash d1594cbd1f95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

workflow-runner 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 8d 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.

Origin

This is a copy

92% identical to workflow-runner — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/workflow-runner/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

工作流执行器:在 AI 工具内运行多角色编排

直接在当前会话中执行 agency-orchestrator 的 YAML 工作流,无需配置 API key。当前 LLM 就是执行引擎——依次扮演每个角色完成任务。

适用场景

  • 用户提供了一个 .yaml 工作流文件(如 运行 workflows/story-creation.yaml
  • 用户要求多个角色协作完成任务(如"用产品经理和架构师一起评审这个 PRD")
  • 用户安装了 agency-agents-zh 并希望直接在 AI 工具内编排多角色

执行流程(5 步)

按以下顺序执行,不要跳步:

第 1 步:解析工作流

用 Read 工具读取用户指定的 YAML 文件,提取以下字段:

name: "工作流名称"
agents_dir: "agency-agents-zh"    # 角色定义目录
inputs:                            # 输入变量
  - name: xxx
    required: true/false
    default: "默认值"
steps:                             # 执行步骤
  - id: step_id
    role: "category/agent-name"    # 角色路径
    task: "任务描述 {{变量}}"       # 支持模板变量
    output: variable_name          # 输出变量名
    depends_on: [other_step_id]    # 依赖关系

忽略 llmconcurrencytimeoutretry 配置——Skill 模式使用当前会话的 LLM,这些字段仅用于 CLI 模式。

定位角色目录:用 Bash test -d 按以下顺序检查,用第一个存在的:

  1. 当前工作目录下的 {agents_dir}/(如 ./agency-agents-zh/
  2. ../{agents_dir}/(上级目录)
  3. 相对于 YAML 文件所在目录的 {agents_dir}/
  4. node_modules/agency-agents-zh/

如果全部找不到,停止执行并提示用户:

找不到角色目录。请先安装:
  git clone --depth 1 https://github.com/jnMetaCode/agency-agents-zh.git
  或:npm install agency-agents-zh

第 2 步:收集输入

  • 对每个 required: true 的输入,检查用户消息中是否已提供值
  • 未提供的必填输入:立即向用户询问,不要猜测或用空值
  • default 的可选输入:使用默认值
  • 无默认值的可选输入:设为空字符串

第 3 步:构建执行顺序

根据 depends_on 进行拓扑排序,将步骤分成多个层级:

  • 无 depends_on 的步骤 → 第 1 层
  • depends_on 全部在第 N 层或之前的步骤 → 第 N+1 层
  • 同一层内的步骤互不依赖,可并行

在回复中展示执行计划:

执行计划(共 N 步):
  第 1 层: [step_id] — 角色名
  第 2 层: [step_a, step_b] — 并行
  第 3 层: [step_id] — 角色名

第 4 步:逐层执行

对每一层:

4a. 预读角色文件

用 Read 工具读取该层所有步骤的角色 .md 文件:{角色目录}/{role}.md

从文件中提取:

  • 角色名:frontmatter 中的 name 字段
  • 角色 system prompt:第二个 --- 之后的全部 markdown 内容
4b. 渲染 task 模板

将 task 中的 {{变量名}} 替换为:

  • 来自 inputs 的用户输入值
  • 来自前序步骤 output 的结果文本
4c. 执行

单步骤层:直接在主会话中扮演该角色执行。格式:

### Step N/Total: step_id(角色名)

[以该角色身份完成 task,使用角色的专业知识和沟通风格]

多步骤层(并行):使用 Agent 工具为每个步骤启动子代理。每个子代理的 prompt 必须包含:

  • 角色文件的完整文本内容(不是路径——子代理可能无法读文件)
  • 渲染后的 task 文本
  • 指令:"以上是你的角色定义,请以该角色身份完成以下任务,直接输出结果"

Read the full file on GitHub · 173 lines

Changes

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.

  1. 8d ago First seen · 173 lines · 61 tokens per session scan A d1594cbd1f95

Subscribe to this mod's changes

workflow-runner is a skill published in the GitHub repository Leodorareluctant259/superpowers-zh (5 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,701 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to workflow-runner, differing in 5 lines, and is treated as a copy.

Related

Other skills, from other repositories

ainb-fleet:daemons

Runtime-health view of the four fleet daemons — phone bridge, notifyd, ATC, and the fleet auto-continue daemon — in one table. Each row reports state (running / stopped / unknown), pid, uptime, last activity, error count, and a HEALTH reason that distinguishes a clean stop from a crash (stale heartbeat) or a…

stevengonsalvez/agents-in-a-box · 126 tokens

ainb-fleet

Fleet orchestration overview — the ainb fleet ... Rust subcommand namespace for driving every claude session on the host. Routes to the sub-skills (ainb-spawn / standup / broadcast / sequence / needs / daemon / atc). Invoke this for an at-a-glance map of what fleet can do; reach for the specific sub-skill for the verb…

stevengonsalvez/agents-in-a-box · 88 tokens

ainb-fleet:bridge

Native phone bridge — relay messages two-way between a chat channel (Telegram, Slack, and/or Discord) and your ainb sessions. Inbound chat messages route to a target session (by name: prefix, else a conductor- first default) and are delivered via tmux send-keys; the session's reply is captured from its JSONL…

stevengonsalvez/agents-in-a-box · 147 tokens

ainb-fleet:daemon

Long-running watcher that scans every claude session every 5s and auto-sends continue to any session whose recent tmux pane buffer matches a known API-error regex (ratelimited, overloadederror, internalservererror, requesttimeout, sockethangup, fetchfailed, ECONNRESET). Use this when you want unattended recovery from…

stevengonsalvez/agents-in-a-box · 89 tokens

ainb-fleet:standup

Show fleet status — every claude session running on the host, merged across ainb + claude-peers broker + background jobs. Use when you need to enumerate sessions before composing an action, check the summary of each session, or pipe the list into jq for filtering. (Writes go via tmux by default; a peerid is just an…

stevengonsalvez/agents-in-a-box · 113 tokens

ainb-fleet:cost

Show fleet spend — per-session, per-model, per-day, and per-group USD cost rollups for every claude/codex session, sourced live from ainb's burndown analytics (which already prices every provider call). Use when you need spend visibility across a multi-session fleet, want to find the most expensive session/model, or…

stevengonsalvez/agents-in-a-box · 120 tokens