OpenAgentsControl
Teach AI agents your coding patterns for consistent, production-ready code
All Skills in This Repository (19)
Pure Emerald Level Indicatorsparallel-execution
Executes independent subtasks simultaneously via multiple subagent invocations in a single message.
task-breakdown
Breaks complex features into atomic subtasks with dependency tracking and JSON task files.
using-oac
Enforces invocation of OAC workflow skills before any AI response or action.
context-discovery
Discovers and ranks project coding standards and conventions before implementation begins.
code-review
Reviews code files for security vulnerabilities, correctness issues, and style violations with severity-ranked findings.
external-research
Fetches and caches current API documentation for external libraries before writing code.
context-setup
Installs project or global context files from a registry using bash or node installer scripts.
debugger
Diagnose bugs and test failures through a four-phase root cause investigation process.
code-execution
Implements coding subtasks from JSON specifications with mandatory self-review and acceptance criteria validation.
oac-approach
Proposes a concise implementation plan for user approval before writing any code.
test-generation
Generates unit tests following TDD principles and project testing standards.
verification-before-completion
Requires running verification commands and reading output before claiming work is complete.
Frequently Asked Questions
FAQPage SchemaHow to install OpenAgentsControl?βΌ
Run `npx skills add darrenhinde/OpenAgentsControl --all -g -y` in your terminal to install all skills in this suite globally.
How do I make AI write code that matches my project style?βΌ
OpenAgentsControl stores your coding standards and patterns in context files that agents load before generating code, so output matches your conventions without refactoring.
Does OpenAgentsControl work with Claude Code?βΌ
Yes. It ships as a Claude Code plugin with specialized subagents, workflow skills, and slash commands, and it also runs on OpenCode with any AI model.
Can AI agents break large features into smaller tasks?βΌ
Yes. The task-breakdown skill splits complex features into atomic subtasks with dependencies, acceptance criteria, and parallel execution tracking.
Do I need coding experience to use OpenAgentsControl?βΌ
Basic development knowledge helps, but agents propose plans and request your approval before executing, so you stay in control of every change.
Related Repositories in Software Engineering
View All in Software Engineeringβopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core