mav-abhi/ai-eng-config
AI engineering config for Claude Code — agents, rules, commands, and workflows across a multi-repo setup
ARCHETYPE
MCP Hoarder
Six or more MCP servers wired in. Every tool, always in context.
Copy this rig
# review before running: this installs third-party code $ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -- npx -y @modelcontextprotocol/server-github $ claude mcp add atlassian -e JIRA_API_<redacted> -e JIRA_BASE_URL=YOUR_JIRA_BASE_URL -e JIRA_USER_EMAIL=YOUR_JIRA_USER_EMAIL -- npx -y @anthropic/mcp-server-atlassian $ claude mcp add slack -e SLACK_BOT_<redacted> -- npx -y @anthropic/mcp-server-slack $ claude mcp add datadog -e DD_<redacted> -e DD_APP_KEY=YOUR_DD_APP_KEY -- npx -y @anthropic/mcp-server-datadog $ claude mcp add figma -e FIGMA_ACCESS_<redacted> -- npx -y @anthropic/mcp-server-figma $ claude mcp add sentry -e SENTRY_AUTH_<redacted> -- npx -y @anthropic/mcp-server-sentry $ npx degit mav-abhi/ai-eng-config/.claude ./rig-ai-eng-config # 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.
$ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -- npx -y @modelcontextprotocol/server-github $ claude mcp add atlassian -e JIRA_API_<redacted> -e JIRA_BASE_URL=YOUR_JIRA_BASE_URL -e JIRA_USER_EMAIL=YOUR_JIRA_USER_EMAIL -- npx -y @anthropic/mcp-server-atlassian $ claude mcp add slack -e SLACK_BOT_<redacted> -- npx -y @anthropic/mcp-server-slack $ claude mcp add datadog -e DD_<redacted> -e DD_APP_KEY=YOUR_DD_APP_KEY -- npx -y @anthropic/mcp-server-datadog $ claude mcp add figma -e FIGMA_ACCESS_<redacted> -- npx -y @anthropic/mcp-server-figma $ claude mcp add sentry -e SENTRY_AUTH_<redacted> -- npx -y @anthropic/mcp-server-sentry
$ npx degit mav-abhi/ai-eng-config/.claude/skills/create-jira-ticket .claude/skills/create-jira-ticket $ npx degit mav-abhi/ai-eng-config/.claude/skills/perform-pr-review .claude/skills/perform-pr-review $ npx degit mav-abhi/ai-eng-config/.claude/skills/review-pr-feedback .claude/skills/review-pr-feedback $ npx degit mav-abhi/ai-eng-config/.claude/skills/verify-codebase .claude/skills/verify-codebase $ npx degit mav-abhi/ai-eng-config/web-platform/.claude/skills/composition-patterns .claude/skills/composition-patterns $ npx degit mav-abhi/ai-eng-config/web-platform/.claude/skills/planner .claude/skills/planner $ npx degit mav-abhi/ai-eng-config/web-platform/.claude/skills/react-best-practices .claude/skills/react-best-practices $ npx degit mav-abhi/ai-eng-config/web-platform/.claude/skills/strategic-compact .claude/skills/strategic-compact $ npx degit mav-abhi/ai-eng-config/web-platform/.claude/skills/web-design-guidelines .claude/skills/web-design-guidelines
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/mav-abhi/ai-eng-config/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/figma-interpreter.md https://raw.githubusercontent.com/mav-abhi/ai-eng-config/main/.claude/agents/figma-interpreter.md $ curl -fsSL --create-dirs -o .claude/agents/qa-engineer.md https://raw.githubusercontent.com/mav-abhi/ai-eng-config/main/.claude/agents/qa-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/staff-engineer.md https://raw.githubusercontent.com/mav-abhi/ai-eng-config/main/.claude/agents/staff-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/system-architect.md https://raw.githubusercontent.com/mav-abhi/ai-eng-config/main/.claude/agents/system-architect.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-writer.md https://raw.githubusercontent.com/mav-abhi/ai-eng-config/main/.claude/agents/tdd-writer.md $ curl -fsSL --create-dirs -o .claude/agents/workflow-orchestrator.md https://raw.githubusercontent.com/mav-abhi/ai-eng-config/main/.claude/agents/workflow-orchestrator.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 *)"
]
}
} MCP servers (6)
| server | source | est. tokens |
|---|---|---|
| GitHub MCP · "github" env: GITHUB_PERSONAL_ACCESS_TOKEN | npm | 18.0k |
| Atlassian env: JIRA_API_TOKEN, JIRA_BASE_URL, JIRA_USER_EMAIL | npm | 10.0k |
| Slack env: SLACK_BOT_TOKEN | npm | 3.5k |
| @anthropic/mcp-server-datadog · "datadog" env: DD_API_KEY, DD_APP_KEY | npm | 2.5k |
| Figma env: FIGMA_ACCESS_TOKEN | npm | 3.0k |
| Sentry env: SENTRY_AUTH_TOKEN | npm | 4.5k |
Skills (9)
create-jira-ticketperform-pr-reviewreview-pr-feedbackverify-codebasevercel-composition-patternsplannervercel-react-best-practicesstrategic-compactweb-design-guidelines
Subagents (7)
| code-reviewer model: sonnet | Use this agent for thorough code review combining CodeRabbit CLI automated analysis with senior engineering expertise. Focuses on architecture, quality, security, and platform-specific standards. Use |
| figma-interpreter model: sonnet | Use this agent to analyze Figma designs and extract technical specifications for development. This agent parses Figma files via MCP to identify components, layouts, colors, typography, spacing, and in |
| qa-engineer model: sonnet | Use this agent for ALL test writing - unit tests, integration tests, and E2E tests. This agent is the sole owner of test code in the workflow. Staff engineer writes implementation code, QA engineer wr |
| staff-engineer model: sonnet | Use this agent when you need production-ready software development with strategic system design and implementation. This agent excels at full-stack development, architectural decisions, scalability pl |
| system-architect model: sonnet | Use this agent when you need to design scalable system architectures, refactor messy codebases into clean structures, evaluate architectural decisions, or transform legacy systems into maintainable so |
| tdd-writer model: sonnet | Use this agent to create Technical Design Documents (TDD) from PRDs and Figma specifications. This agent combines product requirements with design specs to produce comprehensive technical blueprints t |
| workflow-orchestrator model: opus | Use this agent to orchestrate the complete feature development workflow from PRD and Figma to deployed code. This agent coordinates other agents (figma-interpreter, tdd-writer, system-architect, staff |
Slash commands (68)
/address-pr-comments/code-rabbit/code-review/create-release/db-operations/prepare/setup-local-dev/ship-it/ship/workflows/00-reset-and-cleanup/workflows/01-start-task/workflows/02-implement-feature/workflows/03-verify-and-commit/workflows/04-submit-pr/workflows/05-review-pr-feedback/workflows/06-perform-pr-review/workflows/07-wait-for-feedback/address-pr-comments/code-rabbit/code-review/create-release/prepare/setup-local-dev/ship-it/ship/workflows/00-reset-and-cleanup/workflows/01-start-task/workflows/02-implement-feature/workflows/03-verify-and-commit/workflows/04-submit-pr/workflows/05-review-pr-feedback/workflows/06-perform-pr-review/workflows/07-wait-for-feedback/address-pr-comments/code-rabbit/code-review/create-release/db-operations/jira-implement/prepare/setup-local-dev/ship-it/ship/workflows/00-reset-and-cleanup/workflows/01-start-task/workflows/02-implement-feature/workflows/03-verify-and-commit/workflows/04-submit-pr/workflows/05-review-pr-feedback/workflows/06-perform-pr-review/workflows/07-wait-for-feedback/address-pr-comments/code-rabbit/code-review/create-release/jira-implement/migrate-to-d1/prepare/review-better-auth/review-terraform/ship/validate-auth-schema/workflows/01-implement-feature/workflows/02-implement-quick-feature-same-branch/workflows/03-verify-and-commit/workflows/04-submit-pr/workflows/05-review-pr-feedback/workflows/06-perform-pr-review
Permissions
deny (0)
—
ask (0)
—
allow (114)
Bash(git status:*)
Bash(git diff:*)
Bash(git log:*)
Bash(git branch:*)
Bash(git fetch:*)
Bash(git ls-files:*)
Bash(git rev-parse:*)
Bash(git merge-base:*)
Bash(git worktree list:*)
Bash(git show-ref:*)
Bash(git config user:*)
Bash(git blame:*)
Bash(git remote:*)
Bash(git show:*)
Bash(ls:*)
Bash(wc:*)
Bash(diff:*)
Bash(gh pr view:*)
Bash(gh pr list:*)
Bash(gh pr status:*)
Bash(gh pr checks:*)
Bash(gh issue view:*)
Bash(gh issue list:*)
Bash(gh repo view:*)
Bash(gh run view:*)
Bash(gh api:*)
Bash(pnpm install:*)
Bash(pnpm run:*)
Bash(pnpm run --prefix app:*)
Bash(pnpm run --prefix services:*)
Bash(pnpm run --prefix admin:*)
Bash(pnpm run --prefix app-api:*)
Bash(pnpm run --prefix admin-api:*)
Bash(pnpm run --prefix packages/ui-studio:*)
Bash(pnpm exec:*)
Bash(npm install:*)
Bash(npm run:*)
Bash(npm ci:*)
Bash(npm test:*)
Bash(cd services && npm:*)
Bash(yarn install:*)
Bash(yarn add:*)
Bash(yarn dev:*)
Bash(yarn build:*)
Bash(yarn start:*)
Bash(yarn lint:*)
Bash(yarn lint-fix:*)
Bash(yarn typecheck:*)
Bash(yarn test:*)
Bash(yarn format:*)
Bash(yarn codegen:*)
Bash(yarn storybook:*)
Bash(yarn run:*)
Bash(bun install:*)
Bash(bun run:*)
Bash(bun run test:*)
Bash(bun run build:*)
Bash(bun build:*)
Bash(bun typecheck:*)
Bash(bun lint:*)
Similar rigs
KhaiTrang1995/claude-code-structure
A ready-to-use Claude Code project scaffold — rules, commands, skills, agents, and hooks in one command.
Orchestrator 24.4k tok ·
JSK9999/ai-nexus
AI coding assistant rule manager for Claude Code, Cursor, and Codex. Load only the rules you need.
Skill Collector 958 tok ·
vercel-labs/agent-skills
Vercel's official collection of agent skills
Pragmatist 34.1k tok ·
NikolaMaletic/dotfiles
Personal dotfiles - Claude Code config, skills, and settings
Pragmatist 549 tok ·