mini-swe-agent for Openclaw

An autonomous software engineering agent designed to handle complex codebase exploration, bug fixes, and feature implementations via a specialized CLI.

c1nderscript
v1.0.0
Mar 4, 2026
0
1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install mini-swe-agent

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install mini-swe-agent using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is mini-swe-agent?

The mini-swe-agent is a high-performance skill designed to act as an autonomous sub-contractor for software development projects. It is specifically built to manage the heavy lifting of end-to-end codebase editing, allowing developers to delegate intricate tasks like resolving GitHub issues or refactoring complex logic. By integrating this into your set of Openclaw Skills, you gain the ability to trigger a specialized agent that explores your files and applies changes without constant manual oversight.

mini-swe-agent Use Cases

  • Fixing multi-file bugs that require deep codebase exploration.
  • Implementing new features that interact with existing backend or frontend logic.
  • Resolving complex GitHub issues autonomously based on descriptive problem statements.
  • Refactoring legacy code sections to meet updated security or performance standards.

How mini-swe-agent Works

  1. Identify a complex coding task that requires more than a simple one-line change.
  2. Formulate a descriptive problem statement that clearly outlines the desired outcome.
  3. Trigger the mini CLI using the appropriate bash tool with the autonomous flag enabled.
  4. The agent analyzes the directory structure, reads relevant files, and determines the necessary edits.
  5. The agent applies the changes directly to the codebase and provides a status report upon completion.

mini-swe-agent Setup

To install this skill in your local environment, run the following command to create the directory and the metadata file:

mkdir -p ~/.openclaw/skills/mini-swe-agent && cat << 'EOF' > ~/.openclaw/skills/mini-swe-agent/SKILL.md
# mini-swe-agent
...
EOF

Ensure that the mini CLI is globally accessible in your system path so the Openclaw Skills runner can execute it correctly.

mini-swe-agent Data Schema & Taxonomy

The mini-swe-agent operates primarily on the source code within your current working directory. It uses the following data inputs and outputs:

Data Type Description
Problem Statement A detailed string describing the task to be performed.
CLI Flags Parameters like --yolo that dictate the agent's autonomy levels.
File Edits Direct modifications to source files within the project directory.
Execution Logs Terminal output detailing the agent's reasoning and actions.

mini-swe-agent Advanced Features

  • Autonomous execution using the --yolo flag to bypass manual confirmation prompts.
  • Recursive codebase exploration for handling dependencies across multiple files.
  • Intelligent escaping support for complex problem statements involving nested logic.
  • Seamless delegation from higher-level agents within the Openclaw Skills ecosystem.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*