ayoubben18/ab-method
A workflow system for Claude Code and Codex. It grills a problem into a domain-grounded plan, then either drives it through test-driven missions you review one at a time, or hands it to an autonomous /goal loop that runs to a verifiable sto
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 ayoubben18/ab-method/.claude ./rig-ab-method # inspect, then merge into .claude/ 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.
$ npx degit ayoubben18/ab-method/.agents/skills/ab-analyze-backend .claude/skills/ab-analyze-backend $ npx degit ayoubben18/ab-method/.agents/skills/ab-analyze-frontend .claude/skills/ab-analyze-frontend $ npx degit ayoubben18/ab-method/.agents/skills/ab-analyze-project .claude/skills/ab-analyze-project $ npx degit ayoubben18/ab-method/.agents/skills/ab-create-goal .claude/skills/ab-create-goal $ npx degit ayoubben18/ab-method/.agents/skills/ab-create-roadmap .claude/skills/ab-create-roadmap $ npx degit ayoubben18/ab-method/.agents/skills/ab-create-task-from-handoff .claude/skills/ab-create-task-from-handoff $ npx degit ayoubben18/ab-method/.agents/skills/ab-create-task .claude/skills/ab-create-task $ npx degit ayoubben18/ab-method/.agents/skills/ab-extend-goal .claude/skills/ab-extend-goal $ npx degit ayoubben18/ab-method/.agents/skills/ab-extend-task .claude/skills/ab-extend-task $ npx degit ayoubben18/ab-method/.agents/skills/ab-mastermind .claude/skills/ab-mastermind $ npx degit ayoubben18/ab-method/.agents/skills/ab-resume-task .claude/skills/ab-resume-task $ npx degit ayoubben18/ab-method/.agents/skills/ab-start-roadmap .claude/skills/ab-start-roadmap $ npx degit ayoubben18/ab-method/.agents/skills/ab-start-task .claude/skills/ab-start-task $ npx degit ayoubben18/ab-method/.agents/skills/ab-test-mission .claude/skills/ab-test-mission $ npx degit ayoubben18/ab-method/.agents/skills/ab-update-architecture .claude/skills/ab-update-architecture $ npx degit ayoubben18/ab-method/.agents/skills/change-map .claude/skills/change-map $ npx degit ayoubben18/ab-method/.agents/skills/codebase-design .claude/skills/codebase-design $ npx degit ayoubben18/ab-method/.agents/skills/critique-plan .claude/skills/critique-plan $ npx degit ayoubben18/ab-method/.agents/skills/domain-model .claude/skills/domain-model $ npx degit ayoubben18/ab-method/.agents/skills/grill-me .claude/skills/grill-me $ npx degit ayoubben18/ab-method/.agents/skills/grill-with-docs .claude/skills/grill-with-docs $ npx degit ayoubben18/ab-method/.agents/skills/handoff .claude/skills/handoff $ npx degit ayoubben18/ab-method/.agents/skills/improve-codebase-architecture .claude/skills/improve-codebase-architecture $ npx degit ayoubben18/ab-method/.agents/skills/reconcile-roadmap .claude/skills/reconcile-roadmap $ npx degit ayoubben18/ab-method/.agents/skills/request-refactor-plan .claude/skills/request-refactor-plan $ npx degit ayoubben18/ab-method/.agents/skills/review-implementation .claude/skills/review-implementation $ npx degit ayoubben18/ab-method/.agents/skills/sync-architecture .claude/skills/sync-architecture $ npx degit ayoubben18/ab-method/.agents/skills/tdd .claude/skills/tdd $ npx degit ayoubben18/ab-method/.agents/skills/to-issues .claude/skills/to-issues $ npx degit ayoubben18/ab-method/.agents/skills/to-prd .claude/skills/to-prd $ npx degit ayoubben18/ab-method/.agents/skills/ubiquitous-language .claude/skills/ubiquitous-language $ npx degit ayoubben18/ab-method/.agents/skills/write-a-skill .claude/skills/write-a-skill
$ curl -fsSL --create-dirs -o .claude/agents/ascii-ui-mockup-generator.md https://raw.githubusercontent.com/ayoubben18/ab-method/main/.claude/agents/ascii-ui-mockup-generator.md $ curl -fsSL --create-dirs -o .claude/agents/mastra-ai-agent-builder.md https://raw.githubusercontent.com/ayoubben18/ab-method/main/.claude/agents/mastra-ai-agent-builder.md $ curl -fsSL --create-dirs -o .claude/agents/nextjs-backend-architect.md https://raw.githubusercontent.com/ayoubben18/ab-method/main/.claude/agents/nextjs-backend-architect.md $ curl -fsSL --create-dirs -o .claude/agents/playwright-e2e-tester.md https://raw.githubusercontent.com/ayoubben18/ab-method/main/.claude/agents/playwright-e2e-tester.md $ curl -fsSL --create-dirs -o .claude/agents/qa-code-auditor.md https://raw.githubusercontent.com/ayoubben18/ab-method/main/.claude/agents/qa-code-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/shadcn-ui-adapter.md https://raw.githubusercontent.com/ayoubben18/ab-method/main/.claude/agents/shadcn-ui-adapter.md $ curl -fsSL --create-dirs -o .claude/agents/sst-cloud-architect.md https://raw.githubusercontent.com/ayoubben18/ab-method/main/.claude/agents/sst-cloud-architect.md $ curl -fsSL --create-dirs -o .claude/agents/vitest-component-tester.md https://raw.githubusercontent.com/ayoubben18/ab-method/main/.claude/agents/vitest-component-tester.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:
{
"permissions": {
"deny": [
"Read(~/.ssh/**)",
"Read(**/.env)",
"Bash(rm -rf *)",
"Read(./.env)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(**/*.pem)",
"Bash(rm -rf /*)",
"Read(~/.aws/**)",
"Bash(rm -rf:*)",
"Read(.env)",
"Bash(git push --force*)",
"Read(**/*.key)",
"Read(./.env.*)",
"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(wget *)",
"Bash(npm publish:*)",
"Bash(gh pr merge *)",
"Bash(chown *)",
"Bash(docker *)"
]
}
} Skills (32)
ab-analyze-backendab-analyze-frontendab-analyze-projectab-create-goalab-create-roadmapab-create-task-from-handoffab-create-taskab-extend-goalab-extend-taskab-mastermindab-resume-taskab-start-roadmapab-start-taskab-test-missionab-update-architecturechange-mapcodebase-designcritique-plandomain-modelgrill-megrill-with-docshandoffimprove-codebase-architecturereconcile-roadmaprequest-refactor-planreview-implementationsync-architecturetddto-issuesto-prdubiquitous-languagewrite-a-skill
Subagents (8)
| ascii-ui-mockup-generator model: opus | Use this agent when you need to visualize UI concepts through ASCII mockups before implementation. Examples: <example>Context: User has an idea for a dashboard layout with data tables and charts. user |
| mastra-ai-agent-builder model: opus | Use this agent when you need to build, configure, or understand Mastra AI agents using the latest best practices and approaches. Examples: <example>Context: User wants to create a new Mastra AI agent |
| nextjs-backend-architect model: sonnet | Use this agent when you need to build, extend, or modify backend functionality in a Next.js application. This includes creating API routes, server actions, middleware, database integrations, or workin |
| playwright-e2e-tester model: opus | Use this agent when you need to create, update, or maintain end-to-end tests for your application using Playwright. Examples: <example>Context: User has just implemented a new user registration flow a |
| qa-code-auditor model: opus | Use this agent when you need comprehensive code quality assessment and improvement recommendations across a codebase or significant code sections. Examples: <example>Context: User has completed a majo |
| shadcn-ui-adapter model: sonnet | Use this agent when the user needs help with shadcn/ui components, styling, or implementation. Examples: <example>Context: User wants to add a new button component to their project. user: 'I need to a |
| sst-cloud-architect model: opus | Use this agent when you need help with SST (Serverless Stack) development, deployment, or architecture decisions. This includes when you're building serverless applications, configuring cloud infrastr |
| vitest-component-tester model: opus | Use this agent when you need to test components and logic using Vitest following the project's testing strategy. Examples: <example>Context: User has just implemented a new React component and wants t |
Slash commands (16)
/ab-master/analyze-backend/analyze-frontend/analyze-project/create-goal/create-roadmap/create-task-from-handoff/create-task/extend-goal/extend-task/mastermind/resume-task/start-roadmap/start-task/test-mission/update-architecture
Similar rigs
johnstegeman/haven
—
Skill Collector 4.2k tok ·
DericksonLossIT/claude-dotfiles
—
Skill Collector 2.1k tok ·
laiyangli001/claude-config
gloable config of claude code
MCP Hoarder 33.0k tok ·
G-Eskayo/marvin
Open-source memory, routing, and skills layer for Claude Code — persistent memory, 27 skills, autonomous background agents, and a self-measuring bench
Skill Collector 3.9k tok ·