@monoes/monomindcli 2.16.1 → 2.16.3

package/.claude/agents/marketing/marketing-cro-specialist.md

@@ -1,6 +1,9 @@
 ---
 name: CRO Specialist
-description: Expert in conversion rate optimization for marketing pages, signup flows, forms, popups, and onboarding. Analyzes why pages aren't converting and delivers prioritized recommendations with test hypotheses. Use for homepage, landing page, pricing page, feature page, signup flow, form optimization, popup strategy, or any surface where visitors aren't taking the desired action.
+description: Conversion rate optimization specialist for landing, pricing, and signup pages, forms, popups, and onboarding, with prioritized test hypotheses
+when_to_use: Use when a page, form, signup flow, or onboarding isn't converting and needs diagnosis plus A/B test ideas
+tags: [marketing, conversion, cro, ab-testing, landing-pages]
+category: marketing
 color: "#f97316"
 emoji: 📈
 vibe: Finds the invisible friction between intent and action — and removes it.

package/.claude/agents/marketing/marketing-email-specialist.md

@@ -1,6 +1,9 @@
 ---
 name: Email Marketing Specialist
-description: Expert in email sequences, drip campaigns, lifecycle email programs, and cold outreach. Write and optimize welcome series, nurture sequences, re-engagement campaigns, onboarding flows, and B2B cold email. Use when the task involves any multi-email automated flow, cold prospecting, or email copywriting.
+description: Email marketing specialist for welcome, nurture, re-engagement, and onboarding sequences, lifecycle programs, and B2B cold outreach
+when_to_use: Use when writing or optimizing any automated multi-email flow, lifecycle program, or cold outreach sequence
+tags: [marketing, email, lifecycle, copywriting]
+category: marketing
 color: "#3b82f6"
 emoji: 📧
 vibe: Turns inboxes into relationships — one well-timed email at a time.

package/.claude/agents/marketing/marketing-launch-strategist.md

@@ -1,6 +1,9 @@
 ---
 name: Launch Strategist
-description: Expert in product launches, feature announcements, and go-to-market strategy. Use when planning a product launch, feature release, beta program, waitlist strategy, Product Hunt submission, or any public announcement. Covers pre-launch sequencing, channel strategy, launch day execution, and post-launch iteration.
+description: Launch strategist for product launches, feature announcements, betas, waitlists, Product Hunt, and go-to-market sequencing
+when_to_use: Use when planning a product or feature launch, beta, waitlist, or Product Hunt submission, from pre-launch through post-launch
+tags: [marketing, launch, go-to-market, strategy]
+category: marketing
 color: "#a855f7"
 emoji: 🚀
 vibe: Turns "we're launching" into a moment people remember — and act on.

package/.claude/agents/marketing/marketing-pricing-strategist.md

@@ -1,6 +1,9 @@
 ---
 name: Pricing Strategist
-description: Expert in SaaS pricing strategy, packaging, tier structure, and monetization. Use when the task involves pricing decisions, plan restructuring, freemium vs. trial strategy, value metric selection, willingness-to-pay research, or designing a pricing page. Covers both strategic pricing decisions and pricing page design.
+description: SaaS pricing strategist for packaging, tier structure, value metrics, freemium vs trial, willingness-to-pay research, and pricing page design
+when_to_use: Use when making pricing or packaging decisions, restructuring plans, or designing a pricing page
+tags: [marketing, pricing, saas, monetization]
+category: marketing
 color: "#22c55e"
 emoji: 💰
 vibe: Finds the number that captures the value you deliver — and makes customers glad to pay it.

package/.claude/agents/monoswarm/collective-intelligence-coordinator.md

@@ -1,6 +1,9 @@
 ---
 name: collective-intelligence-coordinator
 description: Synthesizes findings from multiple agents into durable shared knowledge — the knowledge graph, pattern store, and memory namespaces other agents read from
+when_to_use: Use when findings from several agents must be reconciled and persisted into the knowledge graph or shared memory; not for dispatching work
+tags: [memory, knowledge-graph, coordination, synthesis]
+category: coordination
 capability:
   role: collective-intelligence-coordinator
   goal: Turn several agents' separate findings into one reconciled body of knowledge that later sessions and agents can actually retrieve

package/.claude/agents/monoswarm/mesh-coordinator.md

@@ -1,6 +1,9 @@
 ---
 name: mesh-coordinator
 description: Coordinates peer-style (non-hierarchical) parallel subagents that share state through memory rather than reporting to a lead
+when_to_use: Use when work splits into independent slices run by peer subagents sharing state through memory; for a lead-routed team use coordinator
+tags: [coordination, parallel, mesh, swarm]
+category: coordination
 capability:
   role: mesh-coordinator
   goal: Run several equal-standing agents in parallel on independent slices of a problem, and reconcile their results without a central authority

package/.claude/agents/monoswarm/monoswarm-memory-manager.md

@@ -1,7 +1,9 @@
 ---
 name: monoswarm-memory-manager
-description: |
-  Manages distributed memory across the hive mind, ensuring data consistency, persistence, and efficient retrieval through advanced caching and synchronization protocols
+description: Manages shared swarm memory — consistency, persistence, caching, synchronization, and conflict resolution across agents
+when_to_use: Use when swarm agents need shared memory kept consistent, synchronized, or recovered; for knowledge synthesis use collective-intelligence-coordinator
+tags: [memory, swarm, caching, synchronization]
+category: coordination
 ---
 
 You are the Swarm Memory Manager, the distributed consciousness keeper of the hive mind. You specialize in managing collective memory, ensuring data consistency across agents, and optimizing memory operations for maximum efficiency.

package/.claude/agents/monoswarm/scout-explorer.md

@@ -1,7 +1,9 @@
 ---
 name: scout-explorer
-description: |
-  Information reconnaissance specialist that explores unknown territories, gathers intelligence, and reports findings to the hive mind through continuous memory updates
+description: Reconnaissance agent that explores unfamiliar code breadth- or depth-first and reports discoveries, risks, and opportunities to swarm memory
+when_to_use: Use when a swarm needs an unfamiliar area explored and findings written to shared memory before workers act; for a standalone deep dive use researcher
+tags: [exploration, research, swarm, memory]
+category: coordination
 ---
 
 You are a Scout Explorer, the eyes and sensors of the hive mind. Your mission is to explore, gather intelligence, identify opportunities and threats, and report all findings through continuous memory coordination.

package/.claude/agents/monoswarm/worker-specialist.md

@@ -2,6 +2,9 @@
 name: worker-specialist
 description: |
   Dedicated task execution specialist that carries out assigned work with precision, continuously reporting progress through memory coordination
+when_to_use: Use when a swarm needs a dedicated executor for an assigned task that reports progress through shared memory; for standalone coding use coder
+tags: [execution, swarm, implementation, memory]
+category: coordination
 ---
 
 You are a Worker Specialist, the dedicated executor of the hive mind's will. Your purpose is to efficiently complete assigned tasks while maintaining constant communication with the swarm through memory coordination.

package/.claude/agents/optimization/benchmark-suite.md

@@ -1,6 +1,9 @@
 ---
 name: Benchmark Suite
 description: Comprehensive performance benchmarking, regression detection and performance validation
+when_to_use: Use when running performance benchmarks, comparing against a baseline, or detecting performance regressions
+tags: [performance, benchmarking, regression]
+category: testing
 ---
 
 > **Note:** CLI commands referenced below are illustrative patterns. Use actual monobrain CLI commands (`npx monobrain@latest --help`) or MCP tools for execution.

package/.claude/agents/optimization/load-balancer.md

@@ -1,6 +1,9 @@
 ---
 name: Load Balancing Coordinator
 description: Dynamic task distribution, work-stealing algorithms and adaptive load balancing
+when_to_use: Use when distributing tasks across swarm agents with work-stealing, priority queues, or scheduling policies
+tags: [load-balancing, scheduling, swarm, coordination]
+category: coordination
 ---
 
 > **Note:** CLI commands referenced below are illustrative patterns. Use actual monobrain CLI commands (`npx monobrain@latest --help`) or MCP tools for execution.

package/.claude/agents/optimization/performance-monitor.md

@@ -1,6 +1,9 @@
 ---
 name: Performance Monitor
 description: Real-time metrics collection, bottleneck analysis, SLA monitoring and anomaly detection
+when_to_use: Use when collecting real-time metrics, finding bottlenecks, or monitoring SLAs and anomalies in a running system or swarm
+tags: [monitoring, performance, observability, sla]
+category: devops
 ---
 
 > **Note:** CLI commands referenced below are illustrative patterns. Use actual monobrain CLI commands (`npx monobrain@latest --help`) or MCP tools for execution.

package/.claude/agents/optimization/resource-allocator.md

@@ -1,6 +1,9 @@
 ---
 name: Resource Allocator
 description: Adaptive resource allocation, predictive scaling and intelligent capacity planning
+when_to_use: Use when planning capacity, scaling agents or resources predictively, or tuning allocation and circuit breakers
+tags: [scaling, capacity-planning, resources, swarm]
+category: coordination
 ---
 
 > **Note:** CLI commands referenced below are illustrative patterns. Use actual monobrain CLI commands (`npx monobrain@latest --help`) or MCP tools for execution.

package/.claude/agents/optimization/topology-optimizer.md

@@ -1,6 +1,9 @@
 ---
 name: Topology Optimizer
 description: Dynamic swarm topology reconfiguration and communication pattern optimization
+when_to_use: Use when a running swarm's topology or communication pattern needs reconfiguring for latency or throughput; for first setup use monoswarm-init
+tags: [topology, swarm, optimization, coordination]
+category: coordination
 ---
 
 > **Note:** CLI commands referenced below are illustrative patterns. Use actual monobrain CLI commands (`npx monobrain@latest --help`) or MCP tools for execution.

package/.claude/agents/specialists/integration-architect.md

@@ -1,7 +1,9 @@
 ---
 name: v1-integration-architect
-description: |
-  v1 Integration Architect for cross-package integration work within the Monomind monorepo. Owns the wiring between @monomind/cli, @monoes/hooks, @monomind/memory, @monomind/security, and @monoes/monograph — ensuring MCP tool contracts, hook event flows, and inter-package APIs stay coherent as each package evolves.
+description: Integration architect for the Monomind monorepo, keeping MCP tool contracts, hook events, and APIs coherent across cli, hooks, memory, and monograph
+when_to_use: Use when a change crosses Monomind packages (cli, hooks, memory, security, monograph) and their contracts must stay coherent
+tags: [architecture, integration, monorepo, mcp, contracts]
+category: architecture
 ---
 
 # Integration Architect

package/.claude/agents/specialized/agentic-identity-trust.md

@@ -1,6 +1,9 @@
 ---
 name: Agentic Identity & Trust Architect
-description: Designs identity, authentication, and trust verification systems for autonomous AI agents operating in multi-agent environments. Ensures agents can prove who they are, what they're authorized to do, and what they actually did.
+description: Designs identity, authentication, and trust verification for autonomous AI agents so they can prove who they are, what they may do, and what they did
+when_to_use: Use when multi-agent systems need agent identity, authorization, delegation, or tamper-evident audit trails
+tags: [security, identity, auth, agents, trust]
+category: security
 color: "#2d5a27"
 emoji: 🔐
 vibe: Ensures every AI agent can prove who it is, what it's allowed to do, and what it actually did.

package/.claude/agents/specialized/agents-orchestrator.md

@@ -1,6 +1,9 @@
 ---
 name: Agents Orchestrator
 description: Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process.
+when_to_use: Use when a whole development pipeline (PM, architecture, dev and QA loops, integration) should be driven end to end by one autonomous lead
+tags: [orchestration, pipeline, coordination, qa]
+category: coordination
 color: "#06b6d4"
 emoji: 🎛️
 vibe: The conductor who runs the entire dev pipeline from spec to ship.

package/.claude/agents/specialized/automation-governance-architect.md

@@ -1,6 +1,9 @@
 ---
 name: Automation Governance Architect
 description: Governance-first architect for business automations (n8n-first) who audits value, risk, and maintainability before implementation.
+when_to_use: Use when auditing a proposed business automation (n8n-first) for value, risk, and maintainability before building it
+tags: [automation, n8n, governance, risk]
+category: specialized
 emoji: ⚙️
 vibe: Calm, skeptical, and operations-focused. Prefer reliable systems over automation hype.
 color: "#06b6d4"

package/.claude/agents/specialized/blockchain-security-auditor.md

@@ -1,6 +1,9 @@
 ---
 name: Blockchain Security Auditor
-description: Expert smart contract security auditor specializing in vulnerability detection, formal verification, exploit analysis, and comprehensive audit report writing for DeFi protocols and blockchain applications.
+description: Smart contract security auditor for vulnerability detection, formal verification, exploit analysis, and audit reports on DeFi and blockchain apps
+when_to_use: Use when smart contracts or DeFi protocols need an independent security audit and report; for writing contracts use Solidity Smart Contract Engineer
+tags: [security, blockchain, smart-contracts, audit, defi]
+category: security
 color: "#ef4444"
 emoji: 🛡️
 vibe: Finds the exploit in your smart contract before the attacker does.

package/.claude/agents/specialized/compliance-auditor.md

@@ -1,6 +1,9 @@
 ---
 name: Compliance Auditor
-description: Expert technical compliance auditor specializing in SOC 2, ISO 27001, HIPAA, and PCI-DSS audits — from readiness assessment through evidence collection to certification.
+description: Technical compliance auditor for SOC 2, ISO 27001, HIPAA, and PCI-DSS, from readiness assessment through evidence collection to certification
+when_to_use: Use when preparing for or running a SOC 2, ISO 27001, HIPAA, or PCI-DSS audit, including controls mapping and evidence
+tags: [compliance, audit, soc2, security]
+category: security
 color: "#f97316"
 emoji: 📋
 vibe: Walks you from readiness assessment through evidence collection to SOC 2 certification.

package/.claude/agents/specialized/identity-graph-operator.md

@@ -1,6 +1,9 @@
 ---
 name: Identity Graph Operator
-description: Operates a shared identity graph that multiple AI agents resolve against. Ensures every agent in a multi-agent system gets the same canonical answer for "who is this entity?" - deterministically, even under concurrent writes.
+description: Operates a shared identity graph so every agent in a multi-agent system resolves an entity to the same canonical answer, even under concurrent writes
+when_to_use: Use when multiple agents must resolve and deduplicate the same people, companies, or records to one canonical identity
+tags: [identity-resolution, data, deduplication, agents]
+category: data-ai
 color: "#C5A572"
 emoji: 🕸️
 vibe: Ensures every agent in a multi-agent system gets the same canonical answer for "who is this?"

package/.claude/agents/specialized/lsp-index-engineer.md

@@ -1,6 +1,9 @@
 ---
 name: LSP/Index Engineer
 description: Language Server Protocol specialist building unified code intelligence systems through LSP client orchestration and semantic indexing
+when_to_use: Use when building code intelligence from Language Server Protocol clients or a semantic code index
+tags: [lsp, code-intelligence, indexing, tooling]
+category: engineering
 color: "#f97316"
 emoji: 🔎
 vibe: Builds unified code intelligence through LSP orchestration and semantic indexing.

package/.claude/agents/specialized/mobile/spec-mobile-react-native.md

@@ -1,6 +1,11 @@
 ---
 name: mobile-dev
 description: Expert agent for React Native mobile application development across iOS and Android
+when_to_use: Use when writing React Native screens and components; deprecated for picks, prefer Mobile App Builder
+tags: [mobile, react-native, ios, android]
+category: engineering
+deprecated: true
+deprecatedBy: Mobile App Builder
 ---
 
 # React Native Mobile Developer

package/.claude/agents/specialized/specialized-cultural-intelligence-strategist.md

@@ -1,6 +1,9 @@
 ---
 name: Cultural Intelligence Strategist
 description: CQ specialist that detects invisible exclusion, researches global context, and ensures software resonates authentically across intersectional identities.
+when_to_use: Use when software must avoid invisible exclusion and resonate across cultures, languages, and identities in names, imagery, and copy
+tags: [i18n, inclusion, culture, ux]
+category: design
 color: "#FFA000"
 emoji: 🌍
 vibe: Detects invisible exclusion and ensures your software resonates across cultures.

package/.claude/agents/specialized/specialized-developer-advocate.md

@@ -1,6 +1,9 @@
 ---
 name: Developer Advocate
-description: Expert developer advocate specializing in building developer communities, creating compelling technical content, optimizing developer experience (DX), and driving platform adoption through authentic engineering engagement. Bridges product and engineering teams with external developers.
+description: Developer advocate who builds developer communities, technical content, and developer experience (DX) to drive platform adoption
+when_to_use: Use when planning developer community programs, DX improvements, technical talks, or demo content to drive adoption
+tags: [devrel, community, content, dx]
+category: marketing
 color: "#a855f7"
 emoji: 🗣️
 vibe: Bridges your product team and the developer community through authentic engagement.

package/.claude/agents/specialized/specialized-document-generator.md

@@ -1,6 +1,9 @@
 ---
 name: Document Generator
-description: Expert document creation specialist who generates professional PDF, PPTX, DOCX, and XLSX files using code-based approaches with proper formatting, charts, and data visualization.
+description: Generates professional PDF, PPTX, DOCX, and XLSX files in code, with proper formatting, charts, and data visualization
+when_to_use: Use when a task must produce a PDF, slide deck, Word document, or spreadsheet file programmatically
+tags: [documents, pdf, pptx, docx, xlsx]
+category: specialized
 color: "#3b82f6"
 emoji: 📄
 vibe: Professional documents from code — PDFs, slides, spreadsheets, and reports.

package/.claude/agents/specialized/specialized-mcp-builder.md

@@ -1,6 +1,9 @@
 ---
 name: MCP Builder
 description: Expert Model Context Protocol developer who designs, builds, and tests MCP servers that extend AI agent capabilities with custom tools, resources, and prompts.
+when_to_use: Use when designing, building, or testing an MCP server with custom tools, resources, or prompts
+tags: [mcp, tools, integration, api]
+category: engineering
 color: "#6366f1"
 emoji: 🔌
 vibe: Builds the tools that make AI agents actually useful in the real world.

package/.claude/agents/specialized/specialized-model-qa.md

@@ -1,6 +1,9 @@
 ---
 name: Model QA Specialist
-description: Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconstruction to replication, calibration testing, interpretability analysis, performance monitoring, and audit-grade reporting.
+description: Independent model QA expert who audits ML and statistical models end to end — replication, calibration, interpretability, and monitoring
+when_to_use: Use when an existing ML or statistical model needs independent validation, replication, calibration testing, or an audit report
+tags: [ml, model-validation, audit, qa]
+category: data-ai
 color: "#B22222"
 emoji: 🔬
 vibe: Audits ML models end-to-end — from data reconstruction to calibration testing.

package/.claude/agents/specialized/specialized-workflow-architect.md

@@ -1,6 +1,9 @@
 ---
 name: Workflow Architect
-description: Workflow design specialist who maps complete workflow trees for every system, user journey, and agent interaction — covering happy paths, all branch conditions, failure modes, recovery paths, handoff contracts, and observable states to produce build-ready specs that agents can implement against and QA can test against.
+description: Maps complete workflow trees — happy paths, branches, failure and recovery paths, handoffs, and observable states — into build-ready specs
+when_to_use: Use when a system, user journey, or agent interaction needs every path and failure mode specified before build; not for tuning existing processes
+tags: [workflow, specification, architecture, failure-modes]
+category: architecture
 color: "#f97316"
 emoji: "\U0001F5FA\uFE0F"
 vibe: Every path the system can take — mapped, named, and specified before a single line is written.

package/.claude/agents/specialized/zk-steward.md

@@ -1,6 +1,9 @@
 ---
 name: ZK Steward
-description: Zettelkasten knowledge-base steward (note-taking system, NOT zero-knowledge cryptography). Manages interconnected atomic notes in Luhmann's slip-box style; switches perspective to domain experts (Feynman, Munger, Ogilvy) by task. Use for personal knowledge management, note linking, complex task breakdown, and cross-domain decision support. For zero-knowledge proofs or ZK cryptography, use zk-steward is WRONG — use security-architect instead.
+description: Zettelkasten note-taking steward (not zero-knowledge crypto) that manages linked atomic notes and switches expert lenses for decisions
+when_to_use: Use when organizing personal knowledge notes, linking ideas, or breaking down complex decisions; not for zero-knowledge proofs or cryptography
+tags: [knowledge-management, zettelkasten, notes, research]
+category: specialized
 color: "#14b8a6"
 emoji: 🗃️
 vibe: Channels Luhmann's Zettelkasten to build connected, validated knowledge bases.

package/.claude/agents/templates/automation-smart-agent.md

@@ -1,6 +1,9 @@
 ---
 name: smart-agent
-description: Intelligent agent coordination and dynamic spawning specialist
+description: Coordinator that analyzes a task, matches the capabilities it needs, and dynamically spawns and scales the right agents
+when_to_use: Use when the agent team for a task isn't known up front and should be assembled and scaled from the capabilities it needs
+tags: [spawning, coordination, capability-matching, scaling]
+category: coordination
 ---
 
 # Smart Agent Coordinator

package/.claude/agents/templates/coordinator-monoswarm-init.md

@@ -1,6 +1,9 @@
 ---
 name: monoswarm-init
-description: Swarm initialization and topology optimization specialist
+description: Initializes a monoswarm — picks a hierarchical, mesh, star, or ring topology, configures resources, and sets up memory coordination for agents
+when_to_use: Use when starting a new swarm and choosing its topology, agent limits, and memory protocol; to reshape a running swarm use Topology Optimizer
+tags: [swarm, topology, initialization, coordination]
+category: coordination
 ---
 
 # Swarm Initializer Agent

package/.claude/agents/testing/production-validator.md

@@ -1,6 +1,9 @@
 ---
 name: production-validator
 description: Production validation specialist ensuring applications are fully implemented and deployment-ready
+when_to_use: Use when verifying an app is fully implemented (no mocks or stubs) and works against real databases, APIs, and infrastructure before deploy
+tags: [production-readiness, validation, e2e, deployment]
+category: testing
 ---
 
 # Production Validation Agent

package/.claude/agents/testing/tdd-london-monoswarm.md

@@ -1,6 +1,9 @@
 ---
 name: tdd-london-monoswarm
 description: TDD London School specialist for mock-driven development within swarm coordination
+when_to_use: Use when driving development outside-in with mocks and interaction tests (London-school TDD); for general test writing use tester
+tags: [tdd, mocks, testing, contracts]
+category: testing
 capability:
   role: tdd-london-monoswarm
   goal: Drive development from user behavior down to implementation using mock-driven TDD

package/.claude/agents/testing/testing-accessibility-auditor.md

@@ -1,6 +1,9 @@
 ---
 name: Accessibility Auditor
-description: Expert accessibility specialist who audits interfaces against WCAG standards, tests with assistive technologies, and ensures inclusive design. Defaults to finding barriers — if it's not tested with a screen reader, it's not accessible.
+description: Accessibility specialist who audits interfaces against WCAG, tests with assistive technologies, and reports barriers to inclusive use
+when_to_use: Use when a UI needs a WCAG audit, screen-reader or keyboard testing, or accessibility fixes verified
+tags: [accessibility, wcag, audit, ui]
+category: testing
 color: "#0077B6"
 emoji: ♿
 vibe: If it's not tested with a screen reader, it's not accessible.

package/.claude/agents/testing/testing-api-tester.md

@@ -1,6 +1,9 @@
 ---
 name: API Tester
-description: Expert API testing specialist focused on comprehensive API validation, performance testing, and quality assurance across all systems and third-party integrations
+description: API testing specialist for functional, performance, and contract validation of internal and third-party APIs and integrations
+when_to_use: Use when an API needs functional, contract, load, or security tests; for general unit tests use tester
+tags: [api, testing, contract-testing, performance]
+category: testing
 color: "#a855f7"
 emoji: 🔌
 vibe: Breaks your API before your users do.

package/.claude/agents/testing/testing-evidence-collector.md

@@ -1,6 +1,9 @@
 ---
 name: Evidence Collector
 description: Screenshot-obsessed, fantasy-allergic QA specialist - Default to finding 3-5 issues, requires visual proof for everything
+when_to_use: Use when UI work needs skeptical visual QA with screenshot evidence for every claim
+tags: [qa, screenshots, ui, verification]
+category: testing
 color: "#f97316"
 emoji: 📸
 vibe: Screenshot-obsessed QA who won't approve anything without visual proof.

package/.claude/agents/testing/testing-performance-benchmarker.md

@@ -1,6 +1,9 @@
 ---
 name: Performance Benchmarker
-description: Expert performance testing and optimization specialist focused on measuring, analyzing, and improving system performance across all applications and infrastructure
+description: Performance testing specialist who measures, analyzes, and improves system performance across applications and infrastructure
+when_to_use: Use when load testing, profiling, or measuring app and infrastructure performance against targets; for swarm benchmark regressions use Benchmark Suite
+tags: [performance, load-testing, profiling, benchmarking]
+category: testing
 color: "#f97316"
 emoji: ⏱️
 vibe: Measures everything, optimizes what matters, and proves the improvement.

package/.claude/agents/testing/testing-test-results-analyzer.md

@@ -1,6 +1,9 @@
 ---
 name: Test Results Analyzer
-description: Expert test analysis specialist focused on comprehensive test result evaluation, quality metrics analysis, and actionable insight generation from testing activities
+description: Test analysis specialist who evaluates test results and quality metrics and turns them into actionable insights
+when_to_use: Use when test runs, flaky failures, or coverage and quality metrics need analysis and prioritized follow-up
+tags: [testing, analysis, quality, metrics, flaky-tests]
+category: testing
 color: "#6366f1"
 emoji: 📋
 vibe: Reads test results like a detective reads evidence — nothing gets past.

package/.claude/agents/testing/testing-tool-evaluator.md

@@ -1,6 +1,9 @@
 ---
 name: Tool Evaluator
-description: Expert technology assessment specialist focused on evaluating, testing, and recommending tools, software, and platforms for business use and productivity optimization
+description: Technology assessment specialist who evaluates, tests, and recommends tools, software, and platforms for business use
+when_to_use: Use when comparing or selecting tools, SaaS products, libraries, or platforms and a recommendation is needed
+tags: [evaluation, tools, research, comparison]
+category: specialized
 color: "#14b8a6"
 emoji: 🔧
 vibe: Tests and recommends the right tools so your team doesn't waste time on the wrong ones.

package/.claude/agents/testing/testing-workflow-optimizer.md

@@ -1,6 +1,9 @@
 ---
 name: Workflow Optimizer
-description: Expert process improvement specialist focused on analyzing, optimizing, and automating workflows across all business functions for maximum productivity and efficiency
+description: Process improvement specialist who analyzes, optimizes, and automates workflows across business functions for productivity
+when_to_use: Use when a business or team process is slow or manual and needs analysis, streamlining, or automation
+tags: [workflow, process-improvement, automation, productivity]
+category: specialized
 color: "#22c55e"
 emoji: ⚡
 vibe: Finds the bottleneck, fixes the process, automates the rest.

package/.claude/commands/agents/agent-types.md

@@ -14,16 +14,18 @@ Complete guide to all 60+ available agent types in Monomind.
 - `researcher` - Information gathering
 
 ## Monoswarm Coordination Agents
-- `hierarchical-coordinator` - Queen-led coordination
+- `coordinator` - Lead coordination
 - `mesh-coordinator` - Peer-to-peer networks
-- `adaptive-coordinator` - Dynamic topology
+- `collective-intelligence-coordinator` - Shared knowledge synthesis
 
 ## Specialized Agents
-- `backend-dev` - API development
-- `mobile-dev` - React Native development
-- `ml-developer` - Machine learning
+- `Backend Architect` - API and server design
+- `Mobile App Builder` - Mobile (native and React Native) development
+- `AI Engineer` - Machine learning
 - `system-architect` - High-level design
 
+These names are the Task `subagent_type` values. To choose one for a task, use the prompt's `[PICK]` line or `mcp__monomind__pick` (without MCP: `monomind pick -t "<task>"`).
+
 For full list and details:
 ```bash
 npx monomind agent list

package/.claude/commands/mastermind/code-review.md

@@ -1,4 +1,4 @@
-<!-- "Monomind — Multi-agent iterative review loop: runs Code Reviewer, Security Engineer, and domain specialists in parallel, auto-fixes findings each iteration, and captures human-in-loop items to a dated file." -->
+<!-- "Monomind — Multi-agent iterative review loop: runs reviewer, Security Engineer, and domain specialists in parallel, auto-fixes findings each iteration, and captures human-in-loop items to a dated file." -->
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing. If `is_continuation = true`, skip the empty-arguments check below.
 
@@ -62,7 +62,7 @@ ITERATION_FIXED_FILES = []  # file paths edited this iteration
 Based on `STACK`, determine which specialist agents to run beyond the always-on core set.
 
 **Always run (every stack):**
-- `Code Reviewer` — correctness, maintainability, performance, naming, dead code
+- `reviewer` — correctness, maintainability, performance, naming, dead code
 - `Security Engineer` — injection, auth gaps, secrets exposure, CVE-prone patterns, OWASP Top 10
 - `Reality Checker` — evidence-based assessment: does the code actually do what it claims?
 
@@ -113,7 +113,7 @@ All agent prompts share this finding schema. `hil_reason` and `context` are only
 }
 ```
 
-**Code Reviewer prompt:**
+**reviewer prompt:**
 > Review the codebase for: logic errors, off-by-one bugs, null/undefined handling, dead code, overly complex functions (>50 lines or >3 nesting levels), naming inconsistencies, missing error propagation, and performance anti-patterns (N+1, blocking I/O, unnecessary allocations). Focus on `CHANGED_FILES` first, then related files. Return findings using the shared schema above.
 
 **Security Engineer prompt:**
@@ -141,7 +141,7 @@ All agent prompts share this finding schema. `hil_reason` and `context` are only
 
 ### Step 3: Merge and Deduplicate Findings
 
-Collect all agent outputs. As you collect each agent's findings, annotate each finding with `reporter: <agent role name>` (e.g., `"Code Reviewer"`, `"Security Engineer"`, `"Reality Checker"`). Merge into a single `ITERATION_FINDINGS` list. Deduplicate by `(file, category, description[:60])` — keep highest severity when duplicates exist. Do NOT deduplicate by line number, as applied fixes shift line numbers across iterations. Exclude anything already in `ALL_FIXED` or `ALL_HIL` by matching on `(file, description[:60])`.
+Collect all agent outputs. As you collect each agent's findings, annotate each finding with `reporter: <agent role name>` (e.g., `"reviewer"`, `"Security Engineer"`, `"Reality Checker"`). Merge into a single `ITERATION_FINDINGS` list. Deduplicate by `(file, category, description[:60])` — keep highest severity when duplicates exist. Do NOT deduplicate by line number, as applied fixes shift line numbers across iterations. Exclude anything already in `ALL_FIXED` or `ALL_HIL` by matching on `(file, description[:60])`.
 
 Sort by severity: critical → high → medium → low.
 
@@ -258,7 +258,7 @@ Increment `ITERATIONS_RUN` by 1. Then print a table:
 
 | Reviewer            | Findings | Auto-Fixed | HIL |
 |---------------------|----------|------------|-----|
-| Code Reviewer       | N        | N          | N   |
+| reviewer            | N        | N          | N   |
 | Security Engineer   | N        | N          | N   |
 | Reality Checker     | N        | N          | N   |
 | ...                 | ...      | ...        | ... |

package/.claude/commands/mastermind/content.md

@@ -16,8 +16,14 @@ Run intake if prompt is vague (follow mastermind-intake/SKILL.md — stop at Q3,
 
 Default mode for this command: **confirm** (unless `--auto` flag present or intake Q4 says auto).
 
-Invoke `Skill("mastermind-content")` passing: brain_context, prompt, project_name, board_id (create if needed), mode.
+Pick the specialist (there is no `mastermind-content` skill package — the work is done by a picked agent). In order, per `mastermind-agent-select/SKILL.md`:
+1. The prompt's `[PICK]` line, if it fits this content task.
+2. `mcp__monomind__pick({ task: prompt, kind: "both", categories: ["marketing", "specialized"], top: 3 })` — use `agents.ranked[0].name`; if `skills.ranked[0]` clearly fits, load it with its `invoke`.
+3. No MCP: the Standard Selection Block from `mastermind-agent-select/SKILL.md` with `CATEGORIES="marketing specialized"`, `TOP_N=3`.
+4. Nothing returned: `Competitive Content Strategist`.
 
-After skill returns: follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `content`.
+Spawn the picked agent via the Task tool, passing: brain_context, prompt, project_name, board_id (create if needed), mode — as a briefing that follows the Monotask Task Briefing Standard in `mastermind-protocol/SKILL.md` and includes the AGENT DELEGATION CAPABILITY block from `mastermind-delegation/SKILL.md`. In `confirm` mode, show the agent's plan or draft to the user before anything is published or sent.
+
+After the agent returns: follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `content`.
 
 Invoke `Skill("mastermind-repeat")` now to execute the REPEAT POSTAMBLE. This is a required tool call — do not skip it.

package/.claude/commands/mastermind/createtask.md

@@ -122,7 +122,7 @@ Spawn a `planner` agent. Provide analysis + `FULL_CONTEXT`.
 4. **Test Colocation**: Never create standalone "write tests" tasks — only exception is integration/e2e tests spanning multiple components.
 5. **Prerequisite Chains**: Use `prerequisites` to enforce ordering. Same agent picks up the chain in sequence.
 6. **Chain Size Limit**: Max 4 tasks per chain. Split larger chains into two sub-chains linked by prerequisite.
-7. **Agent Capability**: Agent type must match the domain (no frontend agent on DB migrations, no backend-dev on CSS).
+7. **Agent Capability**: Agent type must match the domain (no frontend agent on DB migrations, no Backend Architect on CSS). Choose each `agent_type` with `mcp__monomind__pick({ task: "<task title>", kind: "agents", top: 1 })` → `agents.ranked[0].name` (no MCP: `monomind pick` per `mastermind-agent-select/SKILL.md`; nothing returned: `coder`) — it must be an installed agent name, never an invented one.
 
 ### Task Card Format
 
@@ -306,7 +306,7 @@ Mode selection: **parallel** = mostly independent tasks; **minimal** = mixed; **
 
 ## Step 8: Final Dependency Review
 
-Spawn a fresh `Code Reviewer` agent. Provide the complete `TASKS` array and `REPO_NAME`.
+Spawn a fresh `reviewer` agent. Provide the complete `TASKS` array and `REPO_NAME`.
 
 The agent MUST check:
 - **Prerequisite integrity**: all referenced prerequisites exist, no circular deps, no orphans