nyldn/claude-octopus

AI Debate Hub runs structured multi-provider AI debates with Claude and available advisors to help make critical decisions. Use it when you want multiple AI perspectives synthesized before choosing a technical or strategic direction.

Agent Topology Audit evaluates whether a multi-agent setup earns its coordination cost. Use it before adding an agent or when a workflow feels slow or agents agree without adding signal.

Code Review runs a multi-LLM pipeline to analyze pull requests for security vulnerabilities, code quality, performance, TDD compliance, and stubs. Use it before merging changes with security or architecture impact.

Content Pipeline extracts patterns and anatomy from up to five URLs so you can reverse-engineer content strategies. Use it to analyze articles, X threads, newsletters, YouTube descriptions, or LinkedIn posts and generate a structural blueprint, psychological playbook, and interview questions for recreating similar content.

Context Detection automatically identifies whether the current task is development or knowledge work, so agent workflows can tailor research, build, and review behavior. It checks explicit overrides, prompt indicators, and project structure before returning a confidence-scored context.

Copilot Provider integrates GitHub Copilot CLI as an optional zero-cost provider in the Claude Octopus multi-LLM ecosystem, using programmatic mode for research and exploration. Use it to supplement other providers with Copilot responses, with graceful degradation if unavailable.

Cost Projections estimates remaining workflow costs from per-phase averages and warns when projections exceed a budget ceiling. Use it when you need to track and forecast spend across multi-step AI workflows.

Council orchestrates a configurable council of multiple LLMs with personas, budget caps, synthesis, veto gates, and optional implementation handoff. Use it when you need adversarial review, decision support, or implementation planning across models.

Decision Support helps agents present options with trade-offs for informed decision-making when choosing between approaches.

Flow Define orchestrates multiple AI providers to scope requirements, capture user vision, and align stakeholders during the Double Diamond Define phase. Use it after discovery to turn research into a shared definition.

Flow Deliver coordinates multiple AI providers to validate, score, and review code or documents during the Double Diamond delivery phase. Use it to get multi-model quality, security, and completeness checks before finalizing deliverables.

Flow Develop orchestrates multiple external AI providers during the Double Diamond Develop phase, detecting whether the task is dev or knowledge work and injecting domain-specific quality guidance before implementation.

Flow Discover coordinates multi-AI research across available external providers during the Double Diamond Discover phase. Use it to gather divergent perspectives from multiple AI tools before synthesis.

Flow Parallel decomposes large changes, migrations, or multi-issue fixes into independent work packages and executes them in parallel with quality gates. Use it when a compound task can be broken into non-overlapping parts for faster completion.

Flow Spec orchestrates multi-AI research and consensus using Claude Code and external providers to generate structured natural-language specifications (NLSpec) for software projects. Use it when you need a specification grounded in multi-model synthesis, edge cases, and constraint interactions.

Octopus Architecture invokes the backend-architect persona for system design during the grasp and tangle phases. Use it for API design, microservices, distributed systems, database schemas, and scalability planning.

Octopus Research orchestrates multi-provider AI research by calling a shell orchestration script that probes external AI providers and synthesizes findings. Use it for complex research topics needing broad synthesis from multiple AI sources.

Octopus Security Audit performs OWASP compliance, vulnerability scanning, and adversarial red team testing for security reviews. Use it for quick scans or deep audits of code, git history, CI/CD, and dependencies.

Octopus UI/UX Design walks through interactive questions about product type, tech stack, deliverables, and visual adventure, then uses BM25 design intelligence to produce a complete design system with tokens, component specs, layouts, and a style guide.

OpenClaw Administration manages OpenClaw instances and hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox, including gateway lifecycle, security hardening, monitoring, and backups.

Quick Mode executes small, self-contained tasks like bug fixes, configuration changes, documentation updates, and dependency bumps through a streamlined flow with atomic commits, state tracking, and summaries. Use it for ad-hoc work that doesn't require the full Double Diamond workflow.

Skill Authoring provides principles for writing skills that behave the same way every run. Use it when adding, editing, or reviewing a skill in this plugin.

Systematic Audit examines a codebase for issues, inconsistencies, and broken patterns using a structured, checklist-driven process. Use it for pre-release reviews, tech debt assessment, or comprehensive quality verification across an application.

Systematic Debugging guides developers through a four-phase process to find root causes of errors, test failures, and unexpected behavior before applying a fix. Use it when stuck on bugs, failing tests, or unexplained behavior.

Test Coverage Audit traces codepaths in a diff, maps each path against existing tests, and generates missing coverage tests for gaps. Use it before shipping PRs to visualize coverage and reduce untested branches.