ways-of-working
CommunityRun agent teams with clear guardrails
Software Engineering#claude code#subagents#agent orchestration#cost control#workflow routing#adversarial review
Authortimgranlundmarsden
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps you coordinate Claude agent work without losing control of scope, quality, or cost, especially when a task can be completed directly or needs selective subagent support.
Core Features & Use Cases
- Routing guidance: Choose when the parent should work inline and when to involve explorer, researcher, or critic agents.
- Execution discipline: Apply rules for planning, building, reviewing, and retrying so each phase stays focused and predictable.
- Quality and cost control: Use adversarial review loops, parallelism limits, stall handling, and brevity rules to keep workflows reliable and efficient.
Quick Start
Ask the ways-of-working skill to help you plan, build, or review the current task using the safest agent routing approach.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: ways-of-working Download link: https://github.com/timgranlundmarsden/claude-agent-flow/archive/main.zip#ways-of-working Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 536,000+ vetted skills library on demand.