claude-code-agent-workflows

A production-tested system of specialized agents, workflow skills, and enforcement hooks for Claude Code. Battle-tested on a real B2B SaaS product with 18 agents and 16 workflows.

Based on Anthropic's agent-building guidance:

1. Start simple — Use /quick-fix for most things. Only escalate to agent pipelines when complexity demands it.
2. Specialized agents > one generalist — Each agent optimizes for its domain with fresh context.
3. Context documents > context agents — Rich markdown files are faster and cheaper than read-only agents.
4. Two-tier tracking — High-level stories for stakeholders, code-level tasks for Claude sessions.
5. Enforce with hooks — Workflows without enforcement are just suggestions.

.claude/
  agents/           # 10 specialized agents (architect, backend, frontend, etc.)
  skills/           # 16 workflow skills (see Workflow Ladder below)
  contexts/         # Context document pattern (README + template)
CLAUDE.md           # Template project instructions
quick-reference.md  # Cheat sheet for workflow selection

1. Copy the .claude/ directory into your project root
2. Copy CLAUDE.md to your project root and customize it
3. Adapt agent definitions to your stack (the defaults assume Python + TypeScript)
4. Create context documents for your bounded contexts / modules
5. Set up MCP servers for the tools you want to use (see MCP Servers below)

---

From lightest to heaviest:

| Workflow | Scope | Direct Edits | Agents | When to Use | |----------|-------|:------------:|:------:|-------------| | /quick-fix | 1-2 files | Yes | Optional | "Fix this bug", small refactors | | /docs | .md only | .md only | No | Documentation changes | | /explore | Read-only | No | No | Research, investigation | | /preflight-check | Read-only | No | No |