← Back to Skills Marketplace
12675
Downloads
7
Stars
182
Active Installs
1
Versions
Install in OpenClaw
/install subagent-driven-development
Description
Use when executing implementation plans with independent tasks in the current session
Usage Guidance
Install this if you want an agent to coordinate implementation tasks, reviews, tests, and commits in a repository. Use it only on branches and codebases where you are comfortable allowing subagents to make code changes and commits, and keep the review gates enabled.
Capability Analysis
Type: OpenClaw Skill
Name: subagent-driven-development
Version: 0.1.0
This skill bundle outlines a multi-agent development workflow with strong emphasis on quality assurance and security best practices. Key indicators for benign classification include explicit instructions in `SKILL.md` to 'Never' perform risky actions (e.g., work on main branch, skip reviews) and to use isolated workspaces (`superpowers:using-git-worktrees`). Furthermore, `spec-reviewer-prompt.md` contains critical instructions for the reviewer subagent to 'DO NOT TRUST' the implementer's report and to independently verify code, actively mitigating potential prompt injection or misrepresentation from other agents. No evidence of data exfiltration, malicious execution, persistence, or obfuscation was found.
Capability Assessment
Purpose & Capability
The artifacts consistently describe executing an existing implementation plan by dispatching implementer and reviewer subagents, having them test and commit code, and then completing a development branch; this matches the stated purpose.
Instruction Scope
The scope is narrowed to current-session implementation plans with mostly independent tasks, and the body includes clear guardrails such as not skipping reviews, not advancing with open issues, not dispatching multiple implementers in parallel, and not starting on main/master without explicit consent.
Install Mechanism
The package contains markdown skill and prompt templates only; metadata and file inspection show no installer script, dependency hook, startup entry, cron job, obfuscated payload, or automatic execution mechanism.
Credentials
The skill can cause subagents to edit, test, and commit repository code, which is high-impact but expected and disclosed for a development-orchestration skill.
Persistence & Privilege
The cited TodoWrite workflow is transient task tracking for the current session, and the artifacts do not create durable background workers, auth/session access, credential handling, or unauthorized state persistence.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install subagent-driven-development - After installation, invoke the skill by name or use
/subagent-driven-development - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial release: 子代理驱动开发
Metadata
Frequently Asked Questions
What is Subagent Driven Development?
Use when executing implementation plans with independent tasks in the current session. It is an AI Agent Skill for Claude Code / OpenClaw, with 12675 downloads so far.
How do I install Subagent Driven Development?
Run "/install subagent-driven-development" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Subagent Driven Development free?
Yes, Subagent Driven Development is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Subagent Driven Development support?
Subagent Driven Development is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Subagent Driven Development?
It is built and maintained by zlc000190 (@zlc000190); the current version is v0.1.0.
More Skills