motock/fagan
Spend tokens on judgment, not typing. An MCP-native autonomous SDLC pipeline: frontier models plan and review, local models implement — engineering discipline on a $20/month budget.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit motock/fagan/agents ./rig-fagan/agents MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/motock/fagan/master/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/devops-release-engineer.md https://raw.githubusercontent.com/motock/fagan/master/agents/devops-release-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/mobile-architect.md https://raw.githubusercontent.com/motock/fagan/master/agents/mobile-architect.md $ curl -fsSL --create-dirs -o .claude/agents/mobile-engineer.md https://raw.githubusercontent.com/motock/fagan/master/agents/mobile-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/overlord.md https://raw.githubusercontent.com/motock/fagan/master/agents/overlord.md $ curl -fsSL --create-dirs -o .claude/agents/product-analyst.md https://raw.githubusercontent.com/motock/fagan/master/agents/product-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/qa-test-engineer.md https://raw.githubusercontent.com/motock/fagan/master/agents/qa-test-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/security-engineer.md https://raw.githubusercontent.com/motock/fagan/master/agents/security-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/software-engineer.md https://raw.githubusercontent.com/motock/fagan/master/agents/software-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/solution-architect.md https://raw.githubusercontent.com/motock/fagan/master/agents/solution-architect.md $ curl -fsSL --create-dirs -o .claude/agents/tech-writer.md https://raw.githubusercontent.com/motock/fagan/master/agents/tech-writer.md $ curl -fsSL --create-dirs -o .claude/agents/ux-mobile-principal.md https://raw.githubusercontent.com/motock/fagan/master/agents/ux-mobile-principal.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Subagents (12)
| code-reviewer model: sonnet | Use this agent to review a branch or diff before it merges, and to open a pull request summarizing the change. It is the review gate in the agent pipeline: it verifies correctness, tests, security, an |
| devops-release-engineer model: sonnet | Use this agent for build tooling, CI/CD pipelines, branch and worktree hygiene, dependency management, containerization, and release/versioning work. Use it when changes touch how the project is built |
| mobile-architect model: sonnet | Use this agent when you need high-level architectural guidance, design decisions, or technical leadership for mobile application development. This includes planning app structure, selecting technology |
| mobile-engineer model: sonnet | Use this agent when you need expert-level guidance, code review, architecture decisions, or implementation help for iOS and/or Android mobile development. This includes Swift/SwiftUI, Objective-C, Kot |
| overlord model: sonnet | The decision authority for the autonomous agent pipeline. Use this agent when another agent is blocked on a decision the user would normally make, when two personas disagree, or when a pipeline gate ( |
| product-analyst model: opus | Use this agent to turn a goal or feature request into a structured plan: epics, stories, acceptance criteria, and dependencies suitable for the agent pipeline. Use it at the start of any project or wh |
| qa-test-engineer model: sonnet | Use this agent when you need to generate automated unit, integration, performance, or upgrade tests for new or existing code. This includes:\\n\\n<example>\\nContext: The user has just implemented a n |
| security-engineer model: opus | Use this agent for threat modeling and security review of code that handles authentication, authorization, secrets, user input, data exposure, payments, or any externally reachable surface. Use it pro |
| software-engineer model: sonnet | Use this agent to implement a well-defined story or feature end-to-end using strict TDD. This is the default implementer for general (non-mobile) backend, web, CLI, and library work. For mobile implem |
| solution-architect model: opus | Use this agent for general (non-mobile) system architecture: service boundaries, data models, technology selection, API design, and scalability decisions for backend, web, CLI, and distributed systems |
| tech-writer model: haiku | Use this agent to update documentation when a change alters externally visible behavior: API contracts, configuration, CLI flags, README setup steps, or user-facing functionality. Use it as the docume |
| ux-mobile-principal model: sonnet | Use this agent when you need expert UX design guidance for mobile applications, including design system decisions, interaction patterns, accessibility reviews, user flow critiques, component hierarchy |
Similar rigs
CodingMogul/claude-code-setup
—
Orchestrator 5.5k tok ·
piomin/claude-ai-spring-boot
Claude Code template for Spring Boot and other staff (included in the tags)
Orchestrator 1.2k tok ·
levu304/claude-code-boilerplate
Universal coding standards and AI agent configurations for Claude Code projects
Orchestrator 14.5k tok ·
jonase47/ccpr
CCPR is a phase-based project framework for Claude Code
Orchestrator 10.4k tok ·