Inspired by gstack: I stopped prompting Claude and gave it job titles instead

One session. Two commands. Full team. Zero meetings. 23 specialists just showed up. Engineering executes. Product decides. 125 skills across every discipline. MIT licensed, two commands to install. Right now, everyone gets a generalized AI assistant. Engineers, product managers, designers, strategists — all prompting separately, getting separate outputs, then copying results into Slack threads for the next person to feed back into AI. It's a relay race where every handoff loses context. The team is the unit. Not the assistant. Instead of giving each person an AI assistant, give the whole company an AI team. Specialists that talk to each other, share context, and run the show end to end — from user research to infrastructure to deployment — without the copy-paste relay. That's Tonone. Not twenty-three copies of the same generalist. Twenty-three specialists, each owning one domain, coordinated by leads who know when to call who and at what depth. Production-ready output. No tutorials. No boilerplate. | Agent | Hat | What They Do | |---|---|---| | Apex | Engineering Lead | Orchestrates the team, scopes work, controls depth and budget | | Forge | Infrastructure | Cloud services, networking, IaC, cost optimization | | Relay | DevOps | CI/CD, deployments, GitOps, developer experience | | Spine | Backend | APIs, system design, performance, distributed systems | | Flux | Data | Databases, migrations, pipelines, data modeling | | Warden | Security | IAM, secrets, compliance, threat modeling | | Vigil | Observability + Reliability | Monitoring, alerting, SRE, incident response, SLOs | | Prism | Frontend/DX | UI, internal tools, developer portals | | Cortex | ML/AI | Model training, MLOps, feature engineering, LLM integration | | Touch | Mobile | Native iOS/Android, cross-platform, app stores | | Volt | Embedded/IoT | Firmware, microcontrollers, edge computing, protocols | | Atlas | Knowledge Engineering | Architecture docs, ADRs, API specs, system diagrams | | Lens | Data Analytics & BI | Dashboards, metrics design, reporting, data storytelling | | Proof | QA & Testing | Test strategy, E2E suites, integration testing, flaky triage | | Pave | Platform Engineering | Developer experience, golden paths, service catalogs | | Agent | Hat | What They Do | |---|---|---| | Helm | Head of Product | Orchestrates the product team, writes briefs, hands off to Apex | | Echo | User Research | User interviews, personas, Jobs-to-Be-Done, feedback synthesis | | Lumen | Product Analytics | Metrics frameworks, funnel analysis, OKRs, A/B test design | | Draft | UX Design | User flows, information architecture, wireframes | | Form | Visual Design | Brand identity, color systems, typography, design system | | Crest | Product Strategy | Roadmap planning, prioritization, competitive analysis | | Pitch | Product Marketing | Positioning, messaging, value prop, GTM, launch copy | | Surge | Growth | Acquisition channels, activation funnels, retention playbooks | Prerequisites: Claude Code v1.0+ From your terminal: claude plugin marketplace add tonone-ai/tonone claude plugin install tonone@tonone-ai Or inside an active Claude Code session: /plugin marketplace add tonone-ai/tonone /plugin install tonone@tonone-ai Your team is ready: > /apex-plan Build a real-time analytics platform for our IoT fleet > /helm-brief Define the next product sprint > /forge-infra Set up cloud infrastructure for a new SaaS product > /spine-api Design a REST API for user management > /warden-audit Run a full security audit on this codebase > /echo-interview Run a user research session > /crest-roadmap Build a product roadmap Prerequisites: Codex CLI installed git clone https://github.com/tonone-ai/tonone cd tonone codex Codex reads AGENTS.md automatically. Invoke agents and skills by describing what you want: > Read agents/forge.md and act as Forge — audit this infrastructure > Read agents/apex.md — plan this project with S/M/L options > Follow the workflow in skills/warden-audit/SKILL.md Skills are markdown workflow documents in skills//SKILL.md . Read them and follow the steps — no slash commands needed. Every specialist ships in three modes: | Mode | What It Means | Example Skills | |---|---|---| | Build | Create from scratch — production-ready, not tutorials | /forge-infra , /spine-api , /prism-ui , /touch-app | | Review | Audit and fix existing systems | /warden-audit , /relay-audit , /prism-audit , /vigil-check | | Recon | Survey a domain for system takeover | /forge-recon , /spine-recon , /flux-recon , /apex-takeover | Every engineering agent adapts to what you're already using: - Cloud: GCP, AWS, Azure, Cloudflare, Vercel, Fly.io, Hetzner, DigitalOcean - CI/CD: GitHub Actions, GitLab CI, Cloud Build, CircleCI, Bitbucket Pipelines - Backend: Node.js, Python, Go, Rust, Java/Kotlin, Ruby - Databases: PostgreSQL, MySQL, MongoDB, Redis, BigQuery, Snowflake, Supabase, Planetscale - Frontend: React/Next.js, Vue/Nuxt, Svelte/SvelteKit, Astro - Mobile: Swift/SwiftUI, Kotl