mule-agent

Guide mule agents through isolated task execution with git commits, draft PRs, and completion reports.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/ships/eden --skill mule-agent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mule-agent
Source: https://github.com/ships/eden/tree/main/assets/claude/skills/mule-agent
Command: npx skills add https://github.com/ships/eden --skill mule-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

It standardizes how subordinate “mule” agents execute tasks inside the ADAM multi-agent system, so outputs are consistent, correctly scoped, and ready for review.

Core Features & Use Cases

  • Execution patterns for isolated workspaces: Ensures mules operate in dedicated directories and manage git branches and artifacts predictably.
  • Strict commit and PR workflow: Enforces using the correct commit skill for every commit and creating draft PRs when PRs are requested.
  • Reliable reporting back to ADAM: Requires deliverable-complete completion reports (including SHAs, branches, tests, and modified file paths) and prevents Linear comment posting.

Example use case: When ADAM spawns a mule to implement a feature in a cloned repository, this skill guides the mule through setup, investigation, implementation, testing, commit, and draft PR creation with the required report format.

Quick Start

Tell your ADAM orchestrator to spawn a mule and operate under the workspace path /Users/eve/workspace/AGENTS/mule_<identifier>/ while following the mule-agent operational guidelines for git, PR creation, testing, and completion reporting.

Frequently Asked Questions about mule-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate autonomous coding agents to work on isolated tasks?

Autonomous coding agents are orchestrated by spawning mule workers into dedicated workspace directories, ensuring tasks remain dense, imperative, and scoped to isolated environments for reliable execution.

What is workspace isolation in multi-agent git workflows?

Workspace isolation in multi-agent git workflows confines each agent to a dedicated directory, preventing cross-contamination of branches and artifacts while ensuring predictable, scoped deliverables.

How do I create a draft pull request for autonomous agent commits?

To create a draft pull request for autonomous agent commits, use the gh pr create --draft command after ensuring all changes follow strict branch handling and testing requirements.

Does the mule-agent workflow require specific git commit handling?

Yes, the mule-agent workflow requires specific git commit handling by enforcing correct-git-commits-no-exceptions for every commit to maintain strict version control integrity across isolated workspaces.

What should be included in a multi-agent task completion report?

A multi-agent task completion report should include the commit SHA, branch name, test results, and modified file paths to ensure deliverable completeness and reliable reporting back to the orchestrator.

Can mule agents post comments directly to Linear tickets?

No, mule agents cannot post comments directly to Linear tickets; communication is strictly disciplined through ADAM-based reporting to prevent uncoordinated updates and maintain orchestration consistency.