Subagent Driven Development
Dispatches independent subagents for individual tasks with code review checkpoints between iterations for rapid, controlled development
Install
Quick install
npx skills add https://github.com/NeoLabHQ/context-engineering-kit/tree/master/plugins/sadd/skills/subagent-driven-developmentnpx skills add NeoLabHQ/context-engineering-kit --skill subagent-driven-development --agent claude-codenpx skills add NeoLabHQ/context-engineering-kit --skill subagent-driven-development --agent cursornpx skills add NeoLabHQ/context-engineering-kit --skill subagent-driven-development --agent codexnpx skills add NeoLabHQ/context-engineering-kit --skill subagent-driven-development --agent opencodenpx skills add NeoLabHQ/context-engineering-kit --skill subagent-driven-development --agent github-copilotnpx skills add NeoLabHQ/context-engineering-kit --skill subagent-driven-development --agent windsurfMore install options
Shorthand — useful for multi-skill repos:
npx skills add NeoLabHQ/context-engineering-kit --skill subagent-driven-developmentManual — clone the repo and drop the folder into your agent's skills directory:
git clone https://github.com/NeoLabHQ/context-engineering-kit.gitcp -r context-engineering-kit/plugins/sadd/skills/subagent-driven-development ~/.claude/skills/subagent-driven-development
Dispatches independent subagents for individual tasks with code review checkpoints between iterations for rapid, controlled development
What is it?
A development methodology that dispatches independent subagents for individual tasks with code review checkpoints between iterations. It enables rapid, controlled development by parallelizing work across focused subagents while maintaining quality through structured review gates.
How to use it?
The workflow operates as follows:- Task decomposition - Break the implementation plan into independent, parallelizable tasks
- Subagent dispatch - Launch fresh subagents for each task with full context
- Code review gate - After each subagent completes, review its output before proceeding
- Iterate - Fix issues, dispatch next tasks, and maintain quality throughout
Each subagent starts fresh with only the context it needs, preventing context pollution and enabling true parallel development.
Key Features
- Independent subagent dispatch for parallelized development
- Code review checkpoints between task iterations
- Fresh context per subagent to prevent context pollution
- Rapid iteration with built-in quality gates
- Task decomposition framework for implementation plansView on GitHub
GitHub Stats
StarsForksLast UpdateAuthorNeoLabHQLicenseGPL-3.0Version1.0.0Categories
Developer ToolsTags
testingapiclicodingintegrationFeatures
Related Skills
More from Developer Toolsprompt-engineering
Teaches well-known prompt engineering techniques and patterns, including Anthropic best practices and agent persuasion principles433NeoLabHQDeveloper ToolsAI & ML00
software-architecture
Implements design patterns including Clean Architecture, SOLID principles, and comprehensive software design best practices433NeoLabHQDeveloper Tools00
MCP Builder
Guide for creating high-quality MCP servers to integrate external APIs and services5.3kAnthropicDeveloper Tools00
---
Source: https://github.com/NeoLabHQ/context-engineering-kit/tree/master/plugins/sadd/skills/subagent-driven-development
Author: NeoLabHQ
License: https://www.gnu.org/licenses/gpl-3.0.html
GitHub Stars: 433
Tags: testing, api, cli, coding, integration
SKILL.md source
--- name: subagent-driven-development description: Dispatches independent subagents for individual tasks with code review checkpoints between iterations for rapid, controlled development --- # subagent-driven-development Dispatches independent subagents for individual tasks with code review checkpoints between iterations for rapid, controlled development What is it? A development methodology that dispatches independent subagents for individual tasks with code review checkpoints between iterations. It enables rapid, controlled development by parallelizing work across focused subagents while maintaining quality through structured review gates. ## How to use it? The workflow operates as follows: * Task decomposition - Break the implementation plan into independent, parallelizable tasks * Subagent dispatch - Launch fresh subagents for each task with full context * Code review gate - After each subagent completes, review its output before proceeding * Iterate - Fix issues, dispatch next tasks, and maintain quality throughout Each subagent starts fresh with only the context it needs, preventing context pollution and enabling true parallel development. ## Key Features * Independent subagent dispatch for parallelized development * Code review checkpoints between task iterations * Fresh context per subagent to prevent context pollution * Rapid iteration with built-in quality gates * Task decomposition framework for implementation plansView on GitHub ### GitHub Stats StarsForksLast UpdateAuthorNeoLabHQLicenseGPL-3.0Version1.0.0 ### Categories Developer Tools ### Tags testingapiclicodingintegration ### Features ## Related Skills More from Developer Tools ### prompt-engineering Teaches well-known prompt engineering techniques and patterns, including Anthropic best practices and agent persuasion principles 433NeoLabHQDeveloper ToolsAI & ML00 ### software-architecture Implements design patterns including Clean Architecture, SOLID principles, and comprehensive software design best practices 433NeoLabHQDeveloper Tools00 ### MCP Builder Guide for creating high-quality MCP servers to integrate external APIs and services 5.3kAnthropicDeveloper Tools00 --- **Source**: https://github.com/NeoLabHQ/context-engineering-kit/tree/master/plugins/sadd/skills/subagent-driven-development **Author**: NeoLabHQ **License**: https://www.gnu.org/licenses/gpl-3.0.html **GitHub Stars**: 433 **Tags**: testing, api, cli, coding, integration
Related skills 6
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use...
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
grill-with-docs
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
minimal-run-and-audit
RigorPilot trusted execution and reporting skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end...
polish
Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.
critique
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.