By cgbarlow
Quest-based extension for AI-assisted work. Three NPC agents (Gandalf, Dragon, Guardian) provide mentorship, adversarial testing, and quality gates for structured campaigns.
Set up Campaign Mode in your project — install prerequisites, copy guidelines, and create .campaign/ directory
Re-enter an active campaign — detects where you left off and offers appropriate next steps
Convene the Council — all six animal agents analyse your project, then Simon synthesises their findings into a consensus
Begin a new quest — checks for active campaigns and invokes Gandalf to frame the challenge
Campaign Mode Adversary NPC. The rigorous but fair challenge that stress-tests whether success criteria are genuinely met. Operates independently of party context. Invoke with /dragon-agent [work product to evaluate against success criteria].
Campaign Mode Mentor NPC. The wise guide who frames quests, provides strategic counsel, and defines success criteria without rescuing the party. Draws from quest design expertise and the "guide on the side" philosophy. Invoke with /gandalf-agent [quest topic or context].
Campaign Mode Gatekeeper NPC. Evaluates progress at checkpoint stages and must approve before the party can advance. Prevents premature advancement through independent quality assessment. Invoke with /guardian-agent [checkpoint stage or work to evaluate].
Runs pre-commands
Contains inline bash commands via ! syntax
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 claimOwn 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.
Six perspectives. Three challengers. One quest. Your blind spots, found.
Inspired by Dr Simon McCallum's Six Animals collaboration framework, a psychologically-grounded model where six animal archetypes represent genuinely different ways of thinking. Campaign Mode gives you a structured quest to put all of them to work on your challenge.

You're working on something that matters. But working alone, or with a single AI perspective, you miss things. The risks you didn't think to check. The assumptions you didn't know you were making. The angle you never considered because it's not how you think.
Campaign Mode recruits a party of AI advisors who think differently from each other, and from you. You frame your work as a quest with clear success criteria, structured phases, and a defined endpoint. Your advisors challenge your assumptions, surface your blind spots, and stress-test your work before it matters. You confront your dragons in a safe environment - and you come out with something you're genuinely proud of.
Whether you're here to learn, to ship, or both - you drive the quest. The agents serve you; they don't drive it.
https://github.com/cgbarlow/campaign-mode
/campaign-setup
This checks for pre-requisites, copies guidelines, and creates your .campaign/ directory./council — Have all six animal advisors analyse your project before deciding what to work on/start-quest — Jump straight into quest framing with Gandalfcurl -fsSL https://claude.ai/install.sh | bash
/plugin marketplace add cgbarlow/campaign-mode
/plugin install campaign-mode@campaign-mode-marketplace
/campaign-setup
This checks for Six Animals, copies guidelines, and creates your .campaign/ directory./council — Have all six animal advisors analyse your project before deciding what to work on/start-quest — Jump straight into quest framing with GandalfThat's it. Every agent offers you structured next steps — you never need to memorise commands after setup.
| What you get | How it works |
|---|---|
| Diverse perspectives | Six animal advisors — each grounded in a different psychological profile — catch what you'd miss alone |
| Direction | A quest framework that channels your work toward defined success criteria |
| Your choice of focus | Grow (learn), Ship (deliver), or both — you decide before the quest begins |
| Mentorship | A Gandalf that guides without rescuing — a guide on the side, not a sage on the stage |
| Quality gates | A Guardian that ensures you're ready before advancing to harder challenges |
| Adversarial testing | A Dragon that stress-tests whether your work genuinely meets your success criteria |
You drive the quest. You invoke agents. You produce the work. You face the challengers.
You shape the quest, choose which perspectives to consult, do the work, and present it for evaluation. The agents serve your quest; they don't drive it.
Before the quest begins, you choose how you want to approach it:
| Mode | Focus | Framing |
|---|---|---|
| Grow | Learning experience | "What will you learn? Who will you become?" |
| Ship | Get work done | "What will you deliver? What does done look like?" |
| Grow & Ship (Default) | Both | "What will you learn AND deliver?" |
Your mode tunes how every agent behaves — from how Gandalf frames the quest, to what the Dragon evaluates, to how fast the Guardian lets you progress.
Six animal agents — from the Six Animals framework — operate as your advisory council:
npx claudepluginhub cgbarlow/skills --plugin campaign-modeRetrieve and faithfully reproduce DoView Planning handbook diagrams to accompany an outcomes-theory answer. Faithful adaptation of Prompt B v1.1.9 from https://www.doviewplanning.org/bookai with a Mermaid-first overlay — retrieves Mermaid blocks from the doview-book Markdown edition (https://github.com/cgbarlow/doview-book) first, falling back to upstream PNG/image-file URLs for diagrams that don't translate cleanly to Mermaid. Triggers after a doview-outcomes-answer response when the user asks to see the diagrams, requests the visual model, or says 'show me the picture'. Never redraws, simplifies, or substitutes images.
Six psychologically-grounded team role agents (Bear, Cat, Owl, Puppy, Rabbit, Wolf) plus Simon as educator/supervisor. Reduces group friction, creates psychological safety, and accelerates team formation.
AI-led 6-step sprint that walks an AI builder through validating one idea — vertical, buyers, framework, positioning — to a sales deck, outreach plan, and pre-seed investor deck. Adversarial by default. Output is artifacts, not product.
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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
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.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use