AgentsKit
AgentsKit is a one-time-purchase toolkit that turns Claude Code into a team of 89 specialist agents, 103 pre-built skills, and 181 slash commands spanning engineering and marketing. Install with a single npx command into your project's .claude/ folder, pick individual agents, and get lifetime updates. Built for solo developers who want to plan, build, test, ship, and market products without hiring.
What is AgentsKit?
AgentsKit is a one-time-purchase toolkit that upgrades Claude Code from a single generalist assistant into a team of 89 specialist agents, 103 pre-built skills, and 181 slash commands. Everything installs into your project's .claude/ folder with one npx command, so Claude Code picks it up automatically — no new tool to learn, no global install, nothing to configure. The product ships as two complementary kits. The Engineer Kit packs 58 agents covering the whole software lifecycle: a tech-lead that plans and delegates, a shipper that gates every release, backend and frontend specialists (react-specialist, typescript-pro, python-pro, golang-pro, rust-pro), data and infrastructure experts (postgres-pro, kubernetes-specialist, terraform-specialist, sre-engineer), and quality-focused agents (code-reviewer, test-automator, debugger, security-auditor). Its 61 skills cover Next.js, Tailwind, Drizzle, Docker, Stripe, MCP, TDD, and Playwright, plus 159 slash commands like /api-scaffold, /test-coverage, and /deploy-checklist. The Marketing Kit adds 31 growth agents: a growth-strategist that finds your funnel's constraint, a brand-voice agent that keeps copy on-brand and legally clean, plus seo-specialist, content-marketer, competitive-analyst, and market-researcher. Its 42 skills cover SEO audits, programmatic SEO, CRO, pricing, paid ads, marketing psychology, and analytics, with 32 commands that ship real work: /campaign-brief, /blog-post, /email-sequence, /landing-page, and /launch-plan. Agents work as a team: they chain, fan out in parallel, and delegate to each other, with an orchestrator picking the right play so you don't have to. The toolkit adapts to your stack — agents read your CLAUDE.md once and match your conventions, so output ships as if you wrote it. Installation is non-destructive: your existing CLAUDE.md and custom configs are never touched or overwritten, and you can cherry-pick individual components with commands like `agentskit add agent debugger`. Updates are included for life: run `agentskit update` any time to pull the newest agents, skills, and commands at no extra cost. The kit is curated from MIT and Apache licensed projects with full attribution and license files, and it is not affiliated with or endorsed by Anthropic. It works with any Claude Code plan — Pro, Max, Team, or API billing — and is delivered as access to a private GitHub repo with checkout handled securely via Polar. A 14-day money-back guarantee backs every purchase.
AgentsKit Core Features
89 specialist agents covering engineering and marketing that you call by name
103 pre-built skills Claude Code loads automatically exactly when they're needed
181 slash commands for instant workflow control, from /api-scaffold to /campaign-brief
One-command npx install into your project's .claude/ folder with no config
Cherry-pick components with `agentskit add agent debugger` — never all-or-nothing
Adapts to any stack via CLAUDE.md
Next.js, Django, Rails, Go, Rust, anything
Lifetime updates included — `agentskit update` pulls the newest agents for free
Open-source attribution
curated from MIT/Apache projects with full CREDITS and licenses
Who is AgentsKit for?
Solo developers and indie hackers who build products alone and want a full team behind their Claude Code workflow. AgentsKit is designed for people who ship software themselves — from first commit to launch marketing — and would rather delegate to specialist AI agents than hire engineers and marketers. Startup founders and technical founders who wear many hats benefit most: one person can plan, build, test, ship, and market a real product with 89 agents covering both engineering and growth. It suits developers already using Claude Code (Pro, Max, Team, or API billing) who want more structure: teams of agents that chain and delegate, pre-built skills that load automatically, and slash commands that standardize repeated work like scaffolding, test coverage, and deployment checklists. It also fits engineers learning to build more disciplined workflows — the tech-lead agent plans and delegates, the shipper gates releases, and the code-reviewer plus security-auditor add the second pair of eyes a solo builder never has. Technical founders launching products benefit from the Marketing Kit: positioning, launch copy, SEO, email sequences, and landing pages produced from the same context as the code. Freelancers and consultants who deliver full projects alone can use the kits to cut hours on both development and client-facing marketing work. Non-coders are not the target: while the agents do heavy lifting and respond to plain-English instructions, you still need Claude Code and a project to work in. Teams on Cursor, Copilot, or ChatGPT won't get value because the kits live in Claude Code's .claude/ format. Anyone who prefers a one-time purchase with lifetime updates over a monthly subscription will find the model attractive, and the 14-day money-back guarantee lowers the risk of trying it on a real project.
AgentsKit Use Cases
Building and shipping full-stack products solo with specialist agents handling each layer
Automated code review, debugging, test automation, and security auditing of generated code
Programmatic SEO, content marketing, and competitive analysis for product launches
Writing launch copy, email sequences, landing pages, and campaign briefs from code context
Scaffolding APIs, generating test coverage, and running deployment checklists
Planning and delegating complex builds via the tech-lead agent's orchestration
Teaching your project once in CLAUDE.md and never re-explaining stack or conventions
Standardizing a small team's output with a shared set of agents, skills, and commands
AgentsKit Pros and Cons
Pros
- One-time payment with lifetime updates — no subscription, no seats
- Covers both engineering and marketing, rare among Claude Code kits
- Non-destructive install and cherry-picking mean zero risk to existing projects
- Agents chain, fan out, and delegate, with an orchestrator choosing the right play
Cons
- Requires Claude Code — won't run inside Cursor, Copilot, or the ChatGPT app
- Unofficial community product, not affiliated with or endorsed by Anthropic
- Launch pricing is rising fast ($89 to $129 to $199), so buying early matters
FAQ About AgentsKit
AgentsKit Pricing
One-time payment with lifetime updates and no subscription. Launch pricing ladder: $89 (current, 2 spots left), rising to $129 for the next 50 users, then $199. Three options: Engineer Kit (58 agents), Marketing Kit (31 agents), or the Complete Bundle with both (89 agents total). 14-day money-back guarantee. Checkout via Polar with instant private-repo access.
Check official pricingComplete Bundle
Engineer + Marketing kits: 89 agents, 103 skills, 181 commands, both CLAUDE.md templates, private repo with lifetime updates. Launch price rising to $129, then $199.
Engineer Kit
58 engineering agents, 61 pre-built skills, 159 slash commands, CLAUDE.md template + CLI, private repo with lifetime updates.
Marketing Kit
31 marketing agents, 42 pre-built skills, 32 slash commands, brand CLAUDE.md template + CLI, private repo with lifetime updates.
AgentsKit Alternatives
Polsia
Polsia is an AI platform that runs companies on autopilot. Built on agent SDKs and MCP integrations, Polsia plans roadmaps, ships code, runs ads, replies to customers, and posts content around the clock without human intervention. Founded by Ben Cera and operated by Polsia, Inc., it is free to start with no credit card required and subscription billing via Stripe.
Otty
Otty is a native, GPU-accelerated terminal app for macOS designed for developers who use AI coding agents. It combines a fast, beautiful terminal with first-class affordances for Claude Code, Codex, and OpenCode, including agent status, live previews of agent edits, and parallel agent task monitoring. All offline usage is free with no account required, and Windows and Linux support is on the way.
Blink
Blink is an AI app builder where users describe an app in natural language and get a full-stack web or mobile application with database, authentication, APIs, and hosting included. The free plan provides 5 build credits daily with a live URL, while paid plans add custom domains, production hosting, and App Store publishing. Built by 1Flow, Inc., Blink targets founders and builders creating MVPs fast.