Use AB Method when a Claude Code task is too large for one pass and needs to be broken into focused tasks and missions that are completed incrementally instead of trying to solve the whole project in one conversation.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Break large coding jobs into focused subagent missions with AB Method"
slug: "break-large-coding-jobs-into-focused-subagent-missions-with-ab-method"
description: "Use AB Method when a Claude Code task is too large for one pass and needs to be broken into focused tasks and missions that are completed incrementally instead of trying to solve the whole project in one conversation."
github_stars: 159
verification: "security_reviewed"
source: "https://github.com/ayoubben18/ab-method"
author: "ayoubben18"
publisher_type: "individual"
category: "Templates & Workflows"
framework: "Claude Code"
tool_ecosystem:
github_repo: "ayoubben18/ab-method"
github_stars: 159
npm_package: "ab-method"
npm_weekly_downloads: 472
---
# Break large coding jobs into focused subagent missions with AB Method
Use AB Method when a Claude Code task is too large for one pass and needs to be broken into focused tasks and missions that are completed incrementally instead of trying to solve the whole project in one conversation.
## Prerequisites
Claude Code, the AB Method installer or workflow files, and a repository where generated task, mission, and architecture documents can live alongside implementation work.
## Installation
Use the upstream install or setup path that matches your environment:
- npx ab-method
Basic usage or getting-started notes:
- bash
- The installer detects your environment and installs accordingly:
- | Detected | Result |
- Source: https://github.com/ayoubben18/ab-method
- Extracted from upstream docs: https://raw.githubusercontent.com/ayoubben18/ab-method/HEAD/README.md
## Documentation
- https://github.com/ayoubben18/ab-method
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/break-large-coding-jobs-into-focused-subagent-missions-with-ab-method/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.