By ARCASSystems
An operating system for owners running on Claude Code. 74 skills, 35 commands, invisible version control (say "save my work", "what changed", "undo to before this morning", "back this up" and the OS wraps git for you), on-demand liveness reads (/strategic-read for a 5-section state-of-the-OS report, /log-reply for thread ingest, /since-last-session for the delta since the marker), brand voice layer (operator voice + per-brand voice for multi-brand ecosystems), campaign-from-theme with funnel gating, review-responder for incoming customer messages, execution queue with 3-item ACTIVE cap, substrate health check, persistent memory, decision tracking, six role modes, structured cadence, voice and brand profiles, knowledge notes, stable entry IDs, token-aware progressive query, opt-in observation log, weekly observation rollup, private-tag exclusion filter, graph query, audit report, readiness check, source ingest, wiki lint, wiki graph builder, approval gates, delivery ship checks, legal reference layer, runtime brain snapshot, brain-pass synthesis, today brief wrapper, and a natural-language menu of capabilities tailored to current state. Talk to Claude in plain English or run /founder-os:setup to get started.
Audit the OS. Say "audit the OS" or "give me a health report" (or run /founder-os:audit). Composite report across readiness, lint, wiki state, brain staleness, and voice completeness. Read-only unless the user approves wiki-build.
Synthesise an answer across the brain. Say "what do I know about [topic]" or "synthesise across the brain" (or run /founder-os:brain-pass "<question>"). Returns Answer / Evidence / Confidence / Gaps with stable-ID citations. Use when a question spans multiple brain files.
Set up your brand profile. Say "set up my brand profile" (or run /founder-os:brand-interview). Captures your visual identity (colors, fonts, logo) into core/brand-profile.yml. Activates branded outputs (your-deliverable-template, branded proposals, branded client updates). Takes about 10 minutes.
Capture a brand's voice and positioning. Different from voice-interview, which is for the operator's personal voice. One run per brand.
Turn one theme into a sequenced marketing campaign. Refuses to draft until five gate questions are answered (speaker, objective, audience temperature, channels, success metric). Output is a brief plus 3 to 7 content drafts.
Package this session for a fresh chat. Trigger on "summarize this for a new session", "hand this off", "session summary", "transfer this context", "continue this in a new chat", "build a handoff", "wrap this up for next time", "create a prompt for a fresh session", "context transfer", "prepare for handoff", "we've gone deep, let's start fresh", "package this up", or any reference to transferring conversation context to a new session or a different user's Claude. Also fires when Claude detects the conversation is very long and the user mentions starting fresh, continuing later, or sharing context with someone else. Do NOT trigger for simple conversation summaries, meeting prep, or document creation tasks.
Run the final ship gate before any external deliverable goes out. Say "ship this", "is this ready to ship", "final gate", or "run the ship checks" (or run /founder-os:ship-deliverable). Composes template fit, anti-AI scan, blind-spot evidence check, and pre-send-check in one report. Read-only.
Check whether data is safe to share with an external tool. Say "is this safe to paste", "can I send this to <tool>", or "classify this data". Fires before pasting, uploading, forwarding, or sending data to an external tool or AI model. Classifies the data and checks it against the user's data-handling policy.
Walk through a structured decision when the founder is stuck. Trigger phrases: "help me decide", "should I", "what would you do", "weigh these options", "pros and cons", "I'm stuck between", "I can't decide", "trade-offs", "which option", or any situation where the user is evaluating alternatives. Covers business decisions, personal decisions, and strategic choices.
Draft an email in the founder's voice. Trigger on "write an email", "draft a reply", "send a message", "follow up with", "reach out to", "respond to this email", "compose an email", or any variation. Also fires when the user pastes email content and asks for a response, or when they describe a situation that clearly needs an email. Covers client emails, partnership outreach, investor updates, team communications, cold outreach, and personal correspondence. Reads `core/voice-profile.yml`.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub arcassystems/founderos --plugin founder-osUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.