The Vivreal bug/feature workflow — coordinator plus research, architect, coder, tester, reviewer, documenter, and vuln role agents, their slash commands (/orchestrate, /coordinator, /research, /design, /implement, /test, /reviewer, /vuln-fix, and more), and the shared-standards skill.
Adversarial 12-point review of a bug fix. Reviews the diff for the given slug against research.md and plan.md. Can also review the current unstaged diff with no arguments. Records metrics.
Orchestrate the full bug fix workflow — research, plan, user approval, implement, strict review (max 3 passes), document, PR.
Principal-level system architecture and design. Evaluates tradeoffs, generates options, and recommends the best approach. Use for "how should we build X?", migration planning, or architecture decisions.
Generate RESOLUTION.md and PR description for a completed bug fix. Reads all artifacts for the given slug. Records metrics.
Principal-level implementation of a feature or change. Writes production-grade code with proper error handling, performance, and security. Use for complex implementations that need senior-level judgment.
Use after research is complete and an implementation plan or design is needed. Designs implementation plans with 2-3 options and tradeoffs. Bug mode produces docs/bugs/<slug>/plan.md. Feature mode produces design.md. Stops at judgment calls.
Use to implement an approved plan.md or design.md. Implements approved plans. Zero scope creep. Follows existing patterns. Reads plan.md/design.md as the spec, runs lint and type-check before reporting done.
Use for end-to-end bug fixes and small tasks that need the full research→implement→review cycle. Multi-mode orchestrator (bug|feature|audit|migration). Dispatches role agents through research → plan → approve → implement → test → review → document.
Use after a fix is implemented and approved, to produce RESOLUTION.md and the PR description. Generates RESOLUTION.md and PR descriptions from completed bug-fix or feature artifacts. Templated transform of research.md + plan.md + final review. Reports metrics.
Investigates issues end-to-end across the Vivreal stack. Cites file:line for every claim. Read-only — never edits source. Dispatches @<system-expert> for system-specific gotchas.
Uses power tools
Uses Bash, Write, or Edit tools
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.
Claude Code agents, workflows, skills, and tooling for Vivreal — a multi-tenant CMS + distribution platform — packaged as a portable plugin marketplace so they're available from any repository on your machine, and authored so Claude dispatches them proactively without you naming them.
This repo is a Claude Code plugin marketplace. It contains thirteen plugins.
| Plugin | What it is | Use everywhere? |
|---|---|---|
vivreal-principal | 7 repo-agnostic principal-level agents: principal-coordinator, principal-coder, principal-architect, principal-researcher, principal-reviewer, principal-designer, principal-growth-auditor. | ✅ Yes — generalist. Safe and useful in any repo. |
vivreal-workflow | The Vivreal bug/feature workflow: coordinator + researcher/architect/coder/tester/reviewer/documenter/vuln role agents, their slash commands (/orchestrate, /coordinator, /research, /design, /implement, /test, /reviewer, /vuln-fix, …), and the shared-standards skill. | ✅ The repo-agnostic workflow generalists (coordinator/researcher/coder/reviewer/tester) work anywhere; the docs/bugs flow is most useful in Vivreal repos. |
vivreal-experts | 7 read-only system-expert consultants for the Vivreal ecosystem: portal, cms-api, secure-api, main-api, client-stack, event-handler, outreach-api. | ⚠️ Enable when you work across the Vivreal backend/portal repos. |
vivreal-knowledge | Auto-invoked knowledge skills: vivreal-db (safe multi-tenant Mongo query rules), sentry-tracer (cross-stack tracing), vivreal-sites (the site product/data/authoring model), vivreal-design-system (the portal UI/UX system — real component patterns + tokens + WCAG 2.2 + UX-psychology references), vivreal-unit-economics (the cost/margin/pricing model), vivreal-brand-voice (the Vivreal voice + marketing best-practices), and a per-repo digest for each Vivreal repo (portal, CMS/Secure/Main APIs, the public Client stack [vivreal-client-stack-knowledge], EventHandler, Templates, site-renderer, MCP server, and the Outreach API [vivreal-outreach-api-knowledge]). | ✅ Skills load passively from your intent and are cheap when idle. Enable everywhere you touch Vivreal code or data. |
vivreal-infra | Auto-invoked cross-cutting infrastructure skills that span repos: vivreal-lambda (deploy + scaling, with references), vivreal-auth-architecture, vivreal-site-deploy-pipeline, vivreal-iam-secrets, vivreal-atlas-topology, vivreal-media-cdn, vivreal-websocket-realtime. The AWS/Mongo/Amplify plumbing you touch regardless of which repo you're in. | ✅ Skills load passively from your intent and are cheap when idle. Enable everywhere you do AWS/deploy/scaling/ops work. |
vivreal-sentry | Active Sentry investigation tooling: the sentry agent (wired to the Sentry MCP) + the /sentry-trace command. Reconstructs the cross-stack timeline (browser → edge proxy → backend Lambda → MongoDB → WebSocket) for "what happened when I did X", error deep-dives, deploy validation, and tenant-scoped triage. The active companion to the passive sentry-tracer knowledge skill. | ✅ Enable anywhere you investigate Vivreal errors/deploys (requires the Sentry MCP connected). |
vivreal-ops | The vivreal-ops agent — a read-only investigator of running infrastructure: live AWS Lambda config/concurrency, Step Functions execution history, API Gateway, IAM, Secrets Manager, and MongoDB Atlas state. Investigates the deployed reality and recommends; fixes route to principal-coder/coder. | ⚠️ Enable when you do live AWS/Atlas ops investigation (best with the AWS Lambda + AWS docs + mongodb MCPs connected). |
vivreal-product | Three read-only product/business audit agents: finance-auditor (unit economics, gross margin, the AWS/Atlas/Anthropic cost stack, scale economics, the ~80% margin-floor guard), marketing-auditor (brand-voice + marketing best-practices critique of customer-facing copy), and ux-critic (dual-lens naive-user + UX-designer usability critique of portal/customer-site screens, with a Playwright walkthrough). All advisory — they evaluate and recommend; fixes route to principal-coder/coder, content-creator/content-planner, or designer/principal-designer. Grounded in the vivreal-unit-economics, vivreal-brand-voice, and vivreal-design-system skills. | ✅ Enable for product/business reviews (the ux-critic browser walkthrough needs the Playwright MCP). |
vivreal-fullstack | The fullstack-tracer agent (static cross-repo request-path tracing), the fullstack-context auto-loader skill, and the /fullstack end-to-end feature-scaffold command. | ⚠️ Most useful with the Vivreal repos as siblings under C:\repos\. |
npx claudepluginhub hillbombcreations/vivreal-skills --plugin vivreal-workflowRead-only system-expert consultants for the Vivreal ecosystem — cms-api, secure-api, main-api, client-stack, event-handler, outreach-api, and the portal. Proactively dispatched when working inside a Vivreal repo and you need that system's architecture and gotchas.
Auto-invoked knowledge skills for the Vivreal ecosystem — safe multi-tenant MongoDB query rules (vivreal-db), cross-stack Sentry tracing (sentry-tracer), the site product/authoring model (vivreal-sites), the portal design system (vivreal-design-system), the cost/margin/pricing model (vivreal-unit-economics), the brand voice (vivreal-brand-voice), and a per-repo knowledge digest for each Vivreal repo (portal, CMS/Secure/Main APIs, the public Client stack, EventHandler, Templates, site-renderer, MCP server, and the Outreach API). Skills load passively based on intent; install everywhere you touch Vivreal code or data.
Auto-invoked CROSS-CUTTING infrastructure & architecture knowledge skills for the Vivreal AWS stack — Lambda packaging/deploy + reserved-concurrency scaling (vivreal-lambda), API Gateway + Cognito + the Client API key authorizer, the Step Functions + Amplify site-deploy pipeline, IAM + Secrets Manager, MongoDB Atlas topology/ops, the media CDN + S3 + CloudFront signing, and the WebSocket real-time API. Spans repos (unlike the per-repo digests in vivreal-knowledge). Skills load passively from intent; install everywhere you do AWS/deploy/scaling/ops work.
Active Sentry investigation tooling for the Vivreal stack — the `sentry` agent (wired to the Sentry MCP) and the /sentry-trace command. Reconstructs cross-stack timelines (browser → edge proxy → backend Lambda → MongoDB → WebSocket) from Sentry telemetry to answer "what happened when I did X", investigate errors, validate deploys, and run tenant-scoped triage. The active companion to the passive sentry-tracer knowledge skill in vivreal-knowledge.
Repo-agnostic principal-level agents — single-dispatch coordinator, coder, architect, researcher, reviewer, designer, and growth auditor. Proactively dispatched for design-then-build, audits, refactors, code review, and GTM analysis in any repository.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
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.