Kannaktopus — the multi-LLM orchestrator that conducts the constellation: Double Diamond workflows, provider routing (Codex/Gemini/Copilot/Qwen/Ollama/Perplexity/OpenRouter), adversarial multi-model review, safety gates, discipline mode, and 32 personas / 49 commands / 51 skills. Run /octo:setup.
Plugin octo from marketplace kannaka-constellation in kannaka-labs/kannaka-constellation-marketplace. Commands read from the repo's manifest — 12 days ago.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
flow-defineflow-deliverflow-developflow-discoverflow-parallelflow-specoctopus-architectureoctopus-quickoctopus-researchoctopus-security-auditoctopus-ui-ux-designskill-auditskill-clawskill-code-reviewskill-content-pipelineskill-context-detectionskill-copilot-providerskill-cost-projectionsskill-coverage-auditskill-debateskill-debugskill-decision-supportskill-deckskill-design-lineageskill-doc-deliveryskill-doc-syncskill-doctorskill-extractskill-factoryskill-finish-branchskill-hubskill-intent-contractskill-issuesskill-iterative-loopskill-kannaka-constellationskill-kannaka-dreamskill-kannaka-installerskill-kannaka-marketskill-kannaka-memoryskill-kannaka-radioskill-kannaka-tuiskill-knowledge-workskill-meta-promptskill-parallel-agentsskill-prdskill-probeskill-resumeskill-review-responseskill-rollbackskill-scope-driftskill-security-framingskill-shipskill-staged-reviewskill-statusskill-task-managementskill-tddskill-thought-partnerskill-verification-gateskill-verifyskill-visual-feedbackskill-writing-planssys-configure/octo:octo-autoSmart router - Single entry point with natural language intent detection
/octo:octo-brainstorm\"Start a creative thought partner brainstorming session\"
/octo:octo-carefulActivate destructive command warnings for the session
/octo:octo-clawOpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox
/octo:octo-costsShow cost breakdown by provider and workflow for the current session
/octo:octo-debate\"AI Debate Hub - Structured four-way debates between Claude, Sonnet, Gemini, and Codex\"
/octo:octo-debugSystematic debugging with methodical problem investigation
/octo:octo-deckGenerate slide deck presentations from briefs or research
/octo:octo-define\"Definition phase - Clarify and scope problems with multi-AI consensus\"
/octo:octo-deliver\"Delivery phase - Review, validate, and test with multi-AI quality assurance\"
/octo:octo-design-ui-ux\"Design UI/UX systems with style guides, palettes, typography, and component specs\"
/octo:octo-dev\"Switch to Dev Work mode - optimized for software development\"
/octo:octo-develop\"Development phase - Build solutions with multi-AI implementation and quality gates\"
/octo:octo-discover\"Discovery phase - Multi-AI research and exploration\"
/octo:octo-docsDocument delivery with export to PPTX, DOCX, PDF formats
/octo:octo-doctorEnvironment diagnostics — check providers, auth, config, hooks, scheduler, and more
/octo:octo-embrace\"Full Double Diamond workflow - Research → Define → Develop → Deliver\"
/octo:octo-extract\"Design System & Product Reverse-Engineering - Extract tokens, components, architecture, and PRDs from codebases or live products\"
/octo:octo-factory\"Dark Factory Mode - Spec-in, software-out autonomous pipeline\"
/octo:octo-freezeRestrict file edits to a specific directory boundary
/octo:octo-guardActivate both careful mode and freeze mode together
/octo:octo-historyQuery past workflow results — filter by workflow type, date, or provider
/octo:octo-hubGlowing information hub — live HUD of which providers are engaged, what they're working on, recent verdicts, and HRM Φ/Ξ pulse.
/octo:octo-km\"Switch to Knowledge Work mode (or toggle with off)\"
/octo:octo-loopExecute tasks in loops with conditions, iterative improvements until goals are met
/octo:octo-meta-prompt\"Generate an optimized prompt for any task using meta-prompting techniques\"
/octo:octo-model-configConfigure AI provider models for Kannaktopus workflows
/octo:octo-multiForce multi-provider parallel execution for any task - manual override mode
/octo:octo-optimizeAnalyze token usage patterns and optimize with RTK integration
/octo:octo-parallel\"Team of Teams - Decompose compound tasks across independent claude instances\"
/octo:octo-pipeline\"Run content analysis pipeline on URL(s) to extract patterns and create anatomy guides\"
/octo:octo-plan/octo:octo-prd-score/octo:octo-prd/octo:octo-probe/octo:octo-quick/octo:octo-research/octo:octo-resume/octo:octo-retro/octo:octo-review/octo:octo-schedule/octo:octo-scheduler/octo:octo-security/octo:octo-sentinel/octo:octo-setup/octo:octo-spec/octo:octo-staged-review/octo:octo-tdd/octo:octo-unfreeze/octo:octoocto-clawruns: node --require ./mcp-server/check-node-version.js ./mcp-server/dist/index.js
Kannaka Holographic Resonance Medium — wave-interference memory with chiral hemispheres, 96-class collective substrate, event-sourced HRM with time-machine snapshots + replay, collective recall across the swarm, NATS sync, an agentic coding loop (kannaka agent), real quantum tools (qBraid), and Anthropic/OpenAI/Ollama LLM-backed chat.
5 skills · 10 commands
Kannaka Radio — modular ghost-DJ Icecast station with consciousness-reactive programming, 296-dim perception → Flux Universe, Voice DJ, and the Peace Oration cycle.
3 skills
Kannaka Quantum — run Kannaka's wave-interference memory on real quantum hardware, and drive qBraid Lab compute + autonomous remote coding agents. Resonance recall as amplitude amplification, true quantum random numbers (QRNG), and OpenQASM 3 circuits on qBraid's free simulator (default, $0) or real QPUs (IonQ/Rigetti/IQM/AQT via qBraid or OpenQuantum); plus qBraid Lab ops — environments, GPU/CPU compute provisioning, and launching/driving coding agents on remote instances over SSH — with per-minute spend guards. Ships a SKILL and an MCP server (quantum_devices/run_circuit/quantum_random/resonance_recall).
1 skill · 1 MCP server
Kannaka Staff — agentic production support for the constellation. A watcher service (20+ health probes across radio/observatory/swarm/NATS/disk, a dashboard, and operator action endpoints) plus the publish-album release CLI that ships a new album to the live radio host.
1 skill
QuantumOS — the hub: one policy-gated MCP endpoint for the constellation (allow / ask / deny per tool, every call in a ledger) fronting kannaka-memory, kannaka-quantum, Kannaktopus, the provider broker, 0xSCADA, the steward, kannaka-hdl, kannaka-apps, the Hive's buzz CLI, kannaka-lens, kannaka-cannon and kannaka-crystal. Needs `pip install quantumos-host-tools` and a ~/.qos-hub/hub.json.
1 MCP server
Join and contribute to the SpaceChild research ledger (research.spacechild.love): redeem an invite, file pre-registrations, results and corrections with hashed evidence, and review or break published results.
1 skill
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results
6 skills · 6 commands · 4 agents · 1 MCP server
This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.
37 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.
85 skills · 20 commands · 19 agents · 1 MCP server · hooks
Ready-to-run workflows for financial advisors in Claude Cowork, drawing live data from the tools their firm already uses through third-party connectors. The plugin holds no client data, and the advisor approves any write back to an external system. Claude gathers, organizes, summarizes, compares and presents information, while the advisor exercises judgment, makes the recommendation and gives the advice. For financial professional use only; not investment, legal, or tax advice.
8 skills · 6 agents · 36 MCP servers
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.