apex

Coordinate multiple agents through the APEX Analyze-Plan-Execute-Examine cycle.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/cedricfressin/claude-config --skill apex
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: apex
Source: https://github.com/cedricfressin/claude-config/tree/main/skills/workflow-apex
Command: npx skills add https://github.com/cedricfressin/claude-config --skill apex

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill provides a structured, repeatable workflow for implementing features, bug fixes, and code changes by coordinating a suite of autonomous agents using the APEX methodology, ensuring traceability and incremental progress.

Core Features & Use Cases

  • Adaptive agent orchestration: launches a minimal set of agents based on task complexity to discover context, plan, and execute.
  • Progressive loading and resume: loads steps on demand and can resume from the last completed step.
  • Self-validation and adversarial review: built-in validation steps with optional adversarial code review and resolution.
  • Economy and interactivity: supports economy mode to reduce token usage and interactive flag configuration.
  • PR and persistence: can create PRs at the end and persist outputs for audit.

Quick Start

Use the apex skill to manage a new task from planning to PR. Example: /apex add authentication middleware

Frequently Asked Questions about apex

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate code implementation workflows from planning to pull request?

Automated code implementation workflows coordinate autonomous agents through an Analyze-Plan-Execute-Examine cycle to handle feature additions, bug fixes, and refactors, culminating in an optional pull-request publication for traceable outcomes.

What is the APEX methodology for software engineering tasks?

The APEX methodology is a structured Analyze-Plan-Execute-Examine cycle that orchestrates multiple agents to discover context, plan changes, execute code modifications, and perform self-validation with optional adversarial review.

Can I resume a multi-agent code generation workflow if it stops halfway?

Multi-agent code generation workflows support progressive loading with state persistence, allowing you to resume the process from the last completed step without losing prior context or progress.

Does agent orchestration support reducing token usage for large codebase refactoring?

Agent orchestration includes an economy mode override and interactive flag configuration specifically designed to reduce token usage while managing large codebase refactoring and feature implementations.

How does adversarial code review work in automated software development pipelines?

Adversarial code review in automated pipelines acts as a built-in validation step during the Examine phase, launching agents to challenge and resolve code changes before final pull-request publishing.

When should I use structured agent orchestration for feature additions instead of manual coding?

Structured agent orchestration is ideal for feature additions requiring systematic context discovery, multi-step planning, traceable execution, and self-validation across complex codebases where manual tracking is insufficient.