run

run is a command for coding agents from mbruhler/claude-orchestration. It costs 6 tokens per session (4,738 once invoked), scanned C, original, MIT.

A deprecated command for parsing and running workflow instructions written in a compact step-by-step format. It remains supported for older workflows, while a newer workflow skill is recommended.

In plain words
What is it for?
Use it to run legacy workflow syntax such as a sequence of named tasks. It handles both direct workflow text and templates with optional settings.
Why use it?
It lets existing workflow commands continue to run, but signals that new workflows should use the newer process for better progress tracking and error handling.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claude-orchestration plugin — 9 skills, 10 commands, 3 agents shipped together

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.

agentmods
npx agentmods add commands/mbruhler/claude-orchestration/run
Clone the repo
git clone --depth 1 https://github.com/mbruhler/claude-orchestration

Or install claude-orchestration, the plugin that ships this one along with the rest of its 9 skills, 10 commands, 3 agents.

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 run

README.md
[![agentmods](https://agentmods.dev/badge/commands/mbruhler/claude-orchestration/run.svg)](https://agentmods.dev/commands/mbruhler/claude-orchestration/run)
Your own site
<a href="https://agentmods.dev/commands/mbruhler/claude-orchestration/run"><img src="https://agentmods.dev/badge/commands/mbruhler/claude-orchestration/run.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,738 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found 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 $0.00006 $0.04738
Opus 5 $0.00003 $0.02369
Sonnet 5 $0.00001 $0.00948
Haiku 4.5 $0.00001 $0.00474

Measured 4d ago against content hash 1a0f415f31a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

run scanned grade C with 1 finding 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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ./temp-scripts/*
commands/run.md · 653 lines

How it starts

The opening of the file, as written. The whole thing — 653 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ DEPRECATED: Orchestration Workflow Execution

This command is deprecated. Use the executing-workflows skill instead for better visualization, error handling, and progress tracking.

The skill automatically activates when you provide workflow syntax or ask to run a workflow.

Migration Guide

Instead of: /orchestration:run step1 -> step2 -> step3

Just provide syntax:

step1:"task" -> step2:"task" -> step3:"task"

The executing-workflows skill will automatically activate and execute with full visualization and steering support.


Legacy Usage (Still Works)

Parse and execute a workflow defined using orchestration syntax.

Arguments: {{ARGS}}

The workflow to execute. Can be provided in two formats:

  1. Raw syntax - Direct workflow operators (e.g., step1 -> step2)
  2. Template format - YAML frontmatter with workflow and optional visualization fields

Execution Phases

Phase -1: Template Detection (if applicable)

Check for YAML frontmatter:

If input starts with ---, it's a template with frontmatter:

if (input.startsWith('---')) {
  const { frontmatter, content } = parseYAMLFrontmatter(input)

  // Extract fields
  const visualization = frontmatter.visualization  // Static ASCII art
  const workflow = frontmatter.workflow            // Raw workflow syntax

  // Use workflow syntax from frontmatter, not content after ---
  syntax = workflow

  // Store visualization for Phase 2
  staticVisualization = visualization
}

If no frontmatter detected, use input as-is for raw syntax.


Phase 0: Pre-Parse (Temporary Agents)

Reference: ${CLAUDE_PLUGIN_ROOT}/docs/features/temporary-agents.md Registry: ./temp-agents/ (in current working directory)

If workflow contains temporary agent syntax ($agent-name):

  1. Extract Definitions - Find $name := {...} patterns
    const { registry, cleanedSyntax } = extractTempAgentDefinitions(syntax)
    

Read the full file on GitHub · 653 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. 4d ago First seen · 653 lines · 6 tokens per session scan C 1a0f415f31a6

Subscribe to this mod's changes

run is a command published in the GitHub repository mbruhler/claude-orchestration (218 stars, last pushed 3mo ago), licensed MIT. It adds 6 tokens to every session and 4,738 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.