octo
v9.61.1Multi-LLM orchestration with Double Diamond workflows, provider routing, safety gates, and automation. Dispatches to Codex, Gemini, Copilot, Qwen, Perplexity, OpenRouter, Ollama, and OpenCode from a single plugin.
by nyldnMIT4kupdated 5 hours ago
Source
git clone https://github.com/nyldn/claude-octopusClone the source, then follow the repository's marketplace instructions for your runtime. The repository root is the plugin root.
Layout
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/flow-define/SKILL.md├── skills/flow-deliver/SKILL.md├── skills/flow-develop/SKILL.md├── skills/flow-discover/SKILL.md├── skills/flow-parallel/SKILL.md├── skills/flow-spec/SKILL.md├── skills/octopus-architecture/SKILL.md├── skills/octopus-quick/SKILL.md├── skills/octopus-research/SKILL.md├── skills/octopus-security-audit/SKILL.md├── skills/octopus-ui-ux-design/SKILL.md├── skills/skill-agent-topology/SKILL.md├── skills/skill-audit/SKILL.md├── skills/skill-authoring/SKILL.md├── skills/skill-claw/SKILL.md├── skills/skill-code-review/SKILL.md├── skills/skill-content-pipeline/SKILL.md├── skills/skill-context-detection/SKILL.md├── skills/skill-copilot-provider/SKILL.md├── skills/skill-cost-projections/SKILL.md├── skills/skill-council/SKILL.md├── skills/skill-coverage-audit/SKILL.md├── skills/skill-debate/SKILL.md├── skills/skill-debug/SKILL.md├── skills/skill-decision-support/SKILL.md├── skills/skill-deck/SKILL.md├── skills/skill-design-lineage/SKILL.md├── skills/skill-doc-delivery/SKILL.md├── skills/skill-doc-sync/SKILL.md├── skills/skill-doctor/SKILL.md├── skills/skill-extract/SKILL.md├── skills/skill-factory/SKILL.md├── skills/skill-finish-branch/SKILL.md├── skills/skill-intake/SKILL.md├── skills/skill-intent-contract/SKILL.md├── skills/skill-issues/SKILL.md├── skills/skill-iterative-loop/SKILL.md├── skills/skill-knowledge-work/SKILL.md├── skills/skill-meta-prompt/SKILL.md├── skills/skill-native-escalation-routing/SKILL.md├── skills/skill-parallel-agents/SKILL.md├── skills/skill-prd/SKILL.md├── skills/skill-pressure-test/SKILL.md├── skills/skill-resume/SKILL.md├── skills/skill-review-response/SKILL.md├── skills/skill-rollback/SKILL.md├── skills/skill-security-framing/SKILL.md├── skills/skill-ship/SKILL.md├── skills/skill-staged-review/SKILL.md└── skills/skill-status/SKILL.md
Skills50
Multi-AI requirements scoping using available external providers (Double Diamond Define phase)
Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)
Multi-AI implementation using available external providers (Double Diamond Develop phase)
Multi-AI research using available external providers (Double Diamond Discover phase)
Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates
NLSpec authoring — use when you need a structured specification from multi-AI research and consensus
System architecture and API design with multi-AI consensus — use for design reviews and new subsystems
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
Thorough research across multiple sources — use for complex topics needing broad synthesis
OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews
Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces
Audit whether a multi-agent setup earns its coordination cost — use before adding an agent, or when a workflow feels slow or agents agree without adding signal
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
Principles for writing skills that behave the same way every run — use when adding, editing, or reviewing a skill in this plugin
OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox
Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis
Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode
Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns
Run a configurable multi-LLM council with personas, budget caps, synthesis, veto gates, and optional implementation handoff.
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs
Structured multi-provider AI debates between Claude and available advisors — use for critical decisions
Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior
Present options with trade-offs for informed decision-making — use when choosing between approaches
Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries
Persist design documents with branch tracking, revision chains, and cross-session discovery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables
Post-ship doc sync across project markdown. Use when: sync docs, update docs, document changes, release notes.
Environment diagnostics — check providers, auth, config, hooks, scheduler, and more
Reverse-engineer design systems, tokens, and components from live products or screenshots
Run a full build-and-ship pipeline from a spec — use for hands-off project generation
Wrap up a branch — run tests, create PR, merge or discard — use when implementation is done
Move incoming issues and pull requests through triage states until each is actionable or closed — use when the queue has piled up or a report arrives unsorted
Use when starting a complex or ambiguous task that risks scope drift
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage
Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence
Switch to Knowledge Work mode for research and writing — use when task is non-code focused
Craft better prompts using proven optimization techniques — use when your prompt needs refinement
Use when choosing native or multi-LLM handling for init, review, or security requests
Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work
Write an AI-optimized PRD using multi-AI orchestration — use when scoping a new feature or product
Interrogate a plan, decision, or design one question at a time until it holds — use to stress-test your own thinking before committing to it
Pick up where you left off from a previous session — use after context resets, compaction, or new conversations
Use when a reviewer, CI bot, or another AI leaves feedback to address
Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert
URL validation and content sanitization for untrusted sources — use when handling external input safely
Package and finalize completed work for delivery — use when a feature is done and ready to ship
Use when a PR or feature needs both specification and code-quality review
Show where you are in the workflow and what to do next — use for progress checks and orientation
Manifests2
{
"name": "octo",
"version": "9.61.1",
"description": "Multi-LLM orchestration with Double Diamond workflows, provider routing, safety gates, and automation. Dispatches to Codex, Gemini, Copilot, Qwen, Perplexity, OpenRouter, Ollama, and OpenCode from a single plugin.",
"author": {
"name": "nyldn"
},
"license": "MIT",
"repository": "https://github.com/nyldn/claude-octopus",
"homepage": "https://github.com/nyldn/claude-octopus",
"keywords": [
"multi-llm",
"multi-agent",
"orchestration",
"double-diamond",
"codex",
"gemini",
"copilot",
"qwen",
"ollama",
"perplexity",
"openrouter",
"multi-provider",
"provider-routing",
"adversarial-review",
"tdd",
"debugging",
"code-review",
"research"
],
"skills": "./skills/",
"interface": {
"displayName": "Claude Octopus",
"shortDescription": "Multi-LLM orchestration — dispatch to 8 providers from one plugin.",
"longDescription": "Claude Octopus orchestrates multiple AI providers (Codex, Gemini, Antigravity, Grok, Copilot, Qwen, Perplexity, OpenRouter, Ollama, OpenCode) through structured Double Diamond workflows. 32 personas, 51 commands, 63 skills covering research, implementation, review, TDD, security audits, and more. Provider dispatch includes prompt-size preflight, agent summary tables, circuit breakers, cost tracking, and model routing.",
"composerIcon": "./assets/octopus-icon.svg",
"developerName": "nyldn",
"category": "Orchestration",
"capabilities": [
"Interactive",
"Read",
"Write"
],
"defaultPrompt": [
"Research OAuth patterns across providers",
"Build a feature using multi-AI implementation",
"Review this code with adversarial multi-provider analysis",
"Run a structured debate between AI providers"
],
"brandColor": "#6366F1"
}
}{
"name": "octo",
"version": "9.61.1",
"description": "v9.61.1 — Provider routing, workflow contracts, and generated-skill reliability fixes. Run /octo:setup.",
"author": {
"name": "nyldn",
"url": "https://github.com/nyldn"
},
"license": "MIT",
"repository": "https://github.com/nyldn/claude-octopus",
"homepage": "https://github.com/nyldn/claude-octopus",
"keywords": [
"multi-llm",
"multi-agent",
"orchestration",
"claude-code-plugin",
"double-diamond",
"codex",
"gemini",
"antigravity",
"agy",
"copilot",
"code-review",
"automation"
],
"skills": [
"./skills/flow-define",
"./skills/flow-deliver",
"./skills/flow-develop",
"./skills/flow-discover",
"./skills/flow-parallel",
"./skills/flow-spec",
"./skills/octopus-architecture",
"./skills/octopus-quick",
"./skills/octopus-research",
"./skills/octopus-security-audit",
"./skills/octopus-ui-ux-design",
"./skills/skill-agent-topology",
"./skills/skill-audit",
"./skills/skill-authoring",
"./skills/skill-claw",
"./skills/skill-code-review",
"./skills/skill-content-pipeline",
"./skills/skill-context-detection",
"./skills/skill-copilot-provider",
"./skills/skill-cost-projections",
"./skills/skill-council",
"./skills/skill-coverage-audit",
"./skills/skill-debate",
"./skills/skill-debug",
"./skills/skill-decision-support",
"./skills/skill-deck",
"./skills/skill-design-lineage",
"./skills/skill-doc-delivery",
"./skills/skill-doc-sync",
"./skills/skill-doctor",
"./skills/skill-extract",
"./skills/skill-factory",
"./skills/skill-finish-branch",
"./skills/skill-intake",
"./skills/skill-intent-contract",
"./skills/skill-issues",
"./skills/skill-iterative-loop",
"./skills/skill-knowledge-work",
"./skills/skill-meta-prompt",
"./skills/skill-native-escalation-routing",
"./skills/skill-parallel-agents",
"./skills/skill-prd",
"./skills/skill-pressure-test",
"./skills/skill-resume",
"./skills/skill-review-response",
"./skills/skill-rollback",
"./skills/skill-security-framing",
"./skills/skill-ship",
"./skills/skill-staged-review",
"./skills/skill-status",
"./skills/skill-task-management",
"./skills/skill-tdd",
"./skills/skill-thought-partner",
"./skills/skill-verification-gate",
"./skills/skill-verify",
"./skills/skill-visual-feedback",
"./skills/skill-work-slicing",
"./skills/skill-writing-plans",
"./skills/sys-configure",
"./skills/octopus-starter-pack/debate-kickoff",
"./skills/octopus-starter-pack/council-verdicts",
"./skills/octopus-starter-pack/provider-health",
"./skills/octopus-starter-pack/model-cost-compare"
],
"commands": [
"./commands/auto.md",
"./commands/octo.md",
"./commands/prd.md",
"./commands/pipeline.md",
"./commands/brainstorm.md",
"./commands/meta-prompt.md",
"./commands/preflight.md",
"./commands/prd-score.md",
"./commands/setup.md",
"./commands/km.md",
"./commands/dev.md",
"./commands/review.md",
"./commands/security.md",
"./commands/debug.md",
"./commands/tdd.md",
"./commands/loop.md",
"./commands/docs.md",
"./commands/embrace.md",
"./commands/discover.md",
"./commands/define.md",
"./commands/develop.md",
"./commands/deliver.md",
"./commands/multi.md",
"./commands/plan.md",
"./commands/quick.md",
"./commands/extract.md",
"./commands/model-config.md",
"./commands/deck.md",
"./commands/scheduler.md",
"./commands/schedule.md",
"./commands/spec.md",
"./commands/parallel.md",
"./commands/sentinel.md",
"./commands/claw.md",
"./commands/factory.md",
"./commands/staged-review.md",
"./commands/design-ui-ux.md",
"./commands/debate.md",
"./commands/research.md",
"./commands/resume.md",
"./commands/careful.md",
"./commands/freeze.md",
"./commands/guard.md",
"./commands/unfreeze.md",
"./commands/costs.md",
"./commands/council.md",
"./commands/retro.md",
"./commands/history.md",
"./commands/discipline.md",
"./commands/usage.md",
"./commands/whats-new.md"
]
}