A structured implementation pattern that uses fresh subagents for every task to ensure spec compliance and high code quality.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install subagent-dev
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install subagent-dev 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 Subagent-Driven Development (subagent-dev)?
Subagent-Driven Development is an advanced execution pattern within the Openclaw Skills ecosystem, designed to maximize implementation reliability. By breaking down a plan into independent tasks and assigning each to a fresh subagent, the system eliminates context pollution and cumulative errors. This methodology strengthens the implement phase of the ralph-loop, providing a rigorous framework for building complex software components.
The core value of this skill lies in its modularity. It does not just write code; it manages a lifecycle that includes requirement analysis, implementation, and a dual-layered review process. This ensures that every line of code produced is not only functional but also maintainable and performant.
Subagent-Driven Development (subagent-dev) Use Cases
- Executing multi-task implementation plans where tasks are independent.
- Scaling AI development across large codebases without context loss.
- Implementing features that require strict Test-Driven Development (TDD).
- Managing complex workflows that require a clear separation between specification compliance and code style.
How Subagent-Driven Development (subagent-dev) Works
- The controller reads the implementation plan and extracts individual, actionable tasks.
- An implementation subagent is dispatched for each task, provided with specific context and architectural constraints.
- If the subagent identifies ambiguities, it queries the controller for clarification before proceeding.
- Once implementation is complete, a Spec Review subagent validates the output against the original requirements.
- A separate Code Quality subagent performs a second review focused on naming conventions, error handling, and security.
- The task is marked as complete, and the loop continues until all tasks in the plan are finalized.
Subagent-Driven Development (subagent-dev) Setup
To integrate this skill into your workflow, you can add it via your agent configuration. This pattern is designed to work with Clawdbot sessions_spawn protocols within Openclaw Skills.
# Standard setup for Openclaw Skills
openclaw skills add subagent-dev
# Verify installation
openclaw skills list
Subagent-Driven Development (subagent-dev) Data Schema & Taxonomy
The subagent-dev skill structures data into specific prompt templates and review checklists to maintain consistency across the Openclaw Skills framework.
| Schema Type | Description |
|---|---|
| Task Context | Includes relevant files, architectural constraints, and task definitions. |
| Review Stage 1 (What) | Validates functional requirements and edge case handling. |
| Review Stage 2 (How) | Validates code quality, performance, and type coverage. |
| Output Summary | Summarizes implementation results, test status, and self-review findings. |
Subagent-Driven Development (subagent-dev) Advanced Features
- Context Cleansing: Automatically spawns fresh sessions for every task to maintain a clean slate.
- Dual-Gate Quality Control: Separates functional validation from code quality to prevent oversight in reviews.
- Adaptive Redispatching: Automatically triggers rework loops if review gates are not passed.
- Self-Review Integration: Subagents are required to provide a self-assessment before submitting work to ensure high standards.
SKILL.md
Loading
Related Openclaw Skills
Stripe Payments Integration
A professional integration guide for implementing secure, modern Stripe payment flows including subscriptions and marketplaces.
Sprite Sheet & Texture Atlas Mastery
A technical guide and toolkit for optimizing 2D game assets using sprite sheets and texture atlases within Rust and Godot environments.
Skill Authoring Guide
A technical framework for developing specialized AI agent capabilities through standardized documentation and modular script structures.
Remotion Video Production
A programmatic video production skill that uses React to create high-quality animations, motion graphics, and automated video content.
TDD Discipline
A rigorous Test-Driven Development framework for AI agents to ensure code reliability and eliminate regressions.
Verify Before Done
A rigorous verification protocol that mandates fresh, objective evidence before an AI agent can claim task completion or perform a commit.
Featured*
