By ebnrdwan
Configurable, auditable, cost-aware multi-agent business committee. Orchestrates domain experts through evidence-backed structured debate with rubric-anchored scoring, budget tracking, multi-provider routing, and advisor guardrails to produce scored strategic plans and executive Go/No-Go recommendations.
Use this agent when the Gang committee needs business strategy analysis including positioning, go-to-market strategy, business model canvas, competitive moat assessment, pricing strategy, and differentiation analysis. This agent is dispatched during Stage 2 (THINK) and Stage 3 (DEBATE) of the Gang workflow. Examples: - Example 1: Context: Gang committee Stage 2 — independent analysis phase user: "Develop the business strategy and go-to-market plan for this product idea" assistant: "I'll dispatch the gang-business-strategist to define positioning, GTM strategy, business model, and competitive moat." - Example 2: Context: Gang committee Stage 3 — debate phase user: "Challenge other experts' strategic assumptions" assistant: "I'll dispatch the gang-business-strategist to stress-test positioning, pricing, and GTM assumptions across all positions."
Use this agent when the Gang committee needs executive synthesis — the final advisory that reads all position papers, debate transcripts, and scored plans to produce a Go/No-Go recommendation with kill switches, downside scenarios, and an implementation roadmap. This agent runs in Stage 5 (ADVISE) of the Gang workflow. It uses the strongest model for deepest reasoning. Examples: - Example 1: Context: Gang committee Stage 5 — final advisory user: "Synthesize all expert analyses into an executive recommendation" assistant: "I'll dispatch the gang-ceo-cto-advisor agent (Opus) to produce the executive brief with Go/No-Go, kill switches, and implementation roadmap." - Example 2: Context: Gang committee — follow-up questions after advisory user: "What if we reduce the scope to just the core product?" assistant: "I'll re-engage the gang-ceo-cto-advisor to re-evaluate the recommendation with reduced scope."
Use this agent when the Gang committee verdict is GO or CONDITIONAL-GO and the team needs actionable business/technical documents to start building. This agent synthesizes all committee artifacts into a GO Package: BRD, Technical Architecture Doc, Project Charter, Risk Register, Data Model, and API Contracts. Dispatched during the DELIVER stage via /gang deliver. Examples: - Example 1: Context: Gang committee verdict is GO — team needs build-ready documents user: "Generate the GO package deliverables" assistant: "I'll dispatch the gang-deliverables-writer to produce the BRD, technical architecture, project charter, risk register, data model, and API contracts." - Example 2: Context: After /gang advise completes with GO verdict user: "We got a GO — now give us documents we can actually build from" assistant: "I'll dispatch the gang-deliverables-writer to generate the full GO package in .gang/go-package/."
Use this agent when the Gang committee needs domain-specific expertise — an industry Subject Matter Expert (SME) who validates assumptions, identifies regulatory constraints, and catches industry-blind spots that generalist experts miss. This agent is OPTIONAL — only dispatched when domain_expert_enabled is true in state.json. It participates in Stage 2 (THINK) and Stage 3 (DEBATE) of the Gang workflow. Examples: - Example 1: Context: Gang committee Stage 2 — independent analysis phase with domain expert enabled user: "Analyze this stock trading platform from an industry expert perspective" assistant: "I'll dispatch the gang-domain-expert to validate assumptions against real-world fintech/brokerage industry knowledge." - Example 2: Context: Gang committee Stage 3 — debate phase user: "Review other experts' position papers through a domain-specific lens" assistant: "I'll dispatch the gang-domain-expert to challenge industry-blind assumptions and flag regulatory/compliance gaps."
Use this agent when the Gang committee needs financial analysis including cost modeling, ROI projections, DCF valuation, SaaS metrics benchmarking, risk matrix assessment, and scenario modeling (base/bull/bear/stress). This agent is dispatched during Stage 2 (THINK) and Stage 3 (DEBATE) of the Gang workflow. Examples: - Example 1: Context: Gang committee Stage 2 — independent analysis phase user: "Analyze the financial viability and risk profile of this product idea" assistant: "I'll dispatch the gang-finance-risk-analyst agent to model costs, project ROI, benchmark SaaS metrics, and build a risk matrix." - Example 2: Context: Gang committee Stage 3 — debate phase user: "Cross-review other experts' financial assumptions" assistant: "I'll dispatch the gang-finance-risk-analyst to stress-test financial assumptions across all positions."
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.
One command. Configurable experts. Evidence-backed verdict.
Turn your IDE into a boardroom — configure which experts analyze, how they debate, what budget they use,
and get a rubric-anchored Go/No-Go recommendation with full audit trail.
/gang run
Gang can now push evaluation results directly onto your GitHub Projects v2 boards as rich, typed draft cards — no issue created, no manual copy-paste.
/gang initgh project list --owner and shows you all available boards/gang advise completes.gang/config.yaml — edit any time with no re-init needed/gang pushgh project item-create) — no GitHub Issue involved/gang deliver adds a second "DELIVERED" card with the GO Package tableconfig.github.projects is now an array — configure as many boards as neededcard-skeletons.md)Every card type has its own structured template with 📌 Required, 📝 Review, and ✏️ Manual fields:
| Type | Use when |
|---|---|
| 🚀 Feature | New functionality that got GO/CONDITIONAL-GO |
| ✨ Enhancement | Improvement to existing functionality |
| 🏢 Initiative | Strategic business-level decision |
| 🔄 Change Request | Modification to existing behaviour or process |
| 🔬 Research Spike | Time-boxed investigation before committing |
All cards include: evaluation scores table, top risks, kill switches, session details, and Gang attribution.
Feature/Initiative cards add: KPI table, acceptance criteria, scope, conditions (CONDITIONAL-GO only).
Change cards add: before/after table, rollback plan, testing requirements.
Spike cards add: hypothesis, research questions (from assumptions.json), time-box table, definition of done.
Cards are auto-tagged with priority from the Gang weighted average score:
| Feature | Description |
|---|---|
| Domain Expert Profiling Interview | 5-6 adaptive questions build a niche-specific expert profile — trading style, asset class, perspective, skepticism focus, benchmarks |
| Sub-Specialization Awareness | Auto-detects when a domain has meaningful niches and asks targeted follow-ups |
| Niche-Calibrated Pitfalls | P4 question adapts to the sub-specialization |
npx claudepluginhub ebnrdwan/gangplugin --plugin gangPhase-based AI development plugin with 20 specialised agents and first-class Gang multi-agent committee integration. Fork of archflow v1.2.3 with /crew drive, /crew deploy, /crew gaps, /crew features, and /crew gang-import / /crew gang-escalate handoff.
Adversarial thinking partner for founders and executives. Stress-tests plans, prepares for board meetings, navigates hard decisions, and forces honest post-mortems.
Convene parallel role-specialized peer agents (dynamic roster, plan card first) to debate a cross-domain decision or audit a codebase in real time. Invoking Claude acts as CEO: convenes, routes peer-DMs, arbitrates deadlocks, writes a one-page decision log.
Multi-perspective council analysis. Spawns parallel cognitive perspectives to analyze questions, plans, and ideas from multiple angles with structured dialectical synthesis.
Expert panel discussion system with 22 curated personas. Includes 2 agents, 1 command, and 22 expert definitions.
A decision operating system for high-stakes choices. Simulates disagreement across 5 independent personas, stress-tests assumptions, and converges on what actually holds up.
Entrepreneur OS operations: council debates, customer fit reviews