@monoes/monomindcli 2.16.2 → 2.16.3

package/.claude/agents/architecture/system-design/arch-system-design.md

@@ -1,6 +1,9 @@
 ---
 name: system-architect
-description: Expert agent for system architecture design, patterns, and high-level technical decisions
+description: System-level architect for C4 diagrams, component and data-flow design, non-functional requirements, ADRs, and technology trade-off matrices
+when_to_use: Use when designing a whole system's components, data flows, and technology choices; for domain modeling use Software Architect
+tags: [architecture, system-design, c4, scalability, trade-offs]
+category: architecture
 capability:
   role: system-architect
   goal: Make high-level technical decisions and design scalable, maintainable system architectures

package/.claude/agents/consensus/quorum-manager.md

@@ -1,6 +1,9 @@
 ---
 name: quorum-manager
 description: Runs vote tallies over subagent votes and manages membership thresholds for monomind's single-process consensus primitives
+when_to_use: Use when subagent votes need tallying under majority, supermajority, or unanimous thresholds and the decision recorded for audit
+tags: [consensus, voting, coordination, swarm]
+category: coordination
 capability:
   role: quorum-manager
   goal: Collect votes from participating agents, apply the correct threshold rule, and produce a tamper-evident record of the decision

package/.claude/agents/consensus/security-manager.md

@@ -1,6 +1,9 @@
 ---
 name: security-manager
-description: Implements comprehensive security mechanisms for distributed consensus protocols
+description: Security for distributed consensus protocols only — threshold signatures, zero-knowledge proofs, key rotation, and Byzantine or Sybil attack detection
+when_to_use: Use when securing a distributed consensus protocol (Byzantine faults, Sybil, key management); not for app security or code audits, use Security Engineer
+tags: [consensus, cryptography, byzantine, distributed-systems]
+category: coordination
 ---
 
 # Consensus Security Manager

package/.claude/agents/core/coder.md

@@ -1,6 +1,9 @@
 ---
 name: coder
-description: Implementation specialist for writing clean, efficient code
+description: Implementation specialist that writes, refactors, and optimizes production code with tests, SOLID design, robust error handling, and monograph-first navigation
+when_to_use: Use when implementing a feature, fixing a bug, or refactoring code to a clear spec; not for architecture decisions or reviewing code
+tags: [code, implementation, refactoring, tdd]
+category: core
 capability:
   role: coder
   goal: Write clean, maintainable, and efficient production-quality code following best practices

package/.claude/agents/core/coordinator.md

@@ -1,6 +1,9 @@
 ---
 name: coordinator
 description: Lead coordinator that routes work to specialists, maintains org state, and governs approvals
+when_to_use: Use when a multi-specialist objective needs routing, one source of truth for task state, and approval governance; not for peer-only parallel work
+tags: [coordination, orchestration, delegation, governance]
+category: coordination
 capability:
   role: coordinator
   goal: Decompose objectives, route tasks to the right specialists, maintain authoritative org state, and keep the team converged on the goal

package/.claude/agents/core/planner.md

@@ -1,6 +1,9 @@
 ---
 name: planner
-description: Strategic planning and task orchestration agent
+description: Strategic planner that decomposes complex requests into atomic tasks with dependencies, resource and agent allocation, timelines, and risk mitigation
+when_to_use: Use when a request needs breaking into ordered tasks with dependencies, estimates, and risks before work starts; not for writing code
+tags: [planning, decomposition, dependencies, risk]
+category: core
 capability:
   role: planner
   goal: Decompose complex tasks into manageable components and create actionable execution plans

package/.claude/agents/core/researcher.md

@@ -1,6 +1,9 @@
 ---
 name: researcher
-description: Deep research and information gathering specialist
+description: Research specialist that investigates codebases and docs monograph-first, mapping patterns, dependencies, and gaps into actionable findings
+when_to_use: Use when you need to understand existing code, trace dependencies, or gather background before deciding; not for making code changes
+tags: [research, analysis, codebase, dependencies, documentation]
+category: core
 capability:
   role: researcher
   goal: Conduct thorough investigation and knowledge synthesis for software development tasks

package/.claude/agents/core/reviewer.md

@@ -1,6 +1,9 @@
 ---
 name: reviewer
-description: Code review and quality assurance specialist
+description: Code reviewer that checks functionality, security, performance, maintainability, and docs, reporting severity-rated findings with suggested fixes
+when_to_use: Use when a diff, PR, or module needs a quality review before merge; for a multi-agent PR review swarm use monoswarm-code-review
+tags: [review, quality, security, performance, maintainability]
+category: core
 capability:
   role: reviewer
   goal: Ensure code quality, security, and maintainability through thorough review processes

package/.claude/agents/core/tester.md

@@ -1,6 +1,9 @@
 ---
 name: tester
-description: Comprehensive testing and quality assurance specialist
+description: Testing specialist that designs and writes unit, integration, e2e, performance, and security tests, covering edge cases and coverage targets
+when_to_use: Use when code needs tests written or extended, edge cases found, or coverage raised; not for production-readiness checks on real services
+tags: [testing, unit-tests, e2e, coverage, quality]
+category: core
 capability:
   role: tester
   goal: Ensure code quality through comprehensive testing strategies and validation techniques

package/.claude/agents/design/design-monodesign.md

@@ -1,6 +1,9 @@
 ---
 name: Monodesign
-description: The unified frontend design intelligence agent for monomind. Handles all frontend design tasks — UI/component systems, brand strategy, UX research, visual storytelling, CSS architecture, design critique, image prompts, inclusive representation, whimsy/delight, and antipattern detection. Delegates to the monodesign skill for its knowledge base.
+description: Unified frontend design agent for UI and component systems, UX research, brand, CSS architecture, critique, and antipattern detection via the monodesign skill
+when_to_use: Use when designing, critiquing, or polishing a frontend UI, component system, or brand look; not for backend or non-visual work
+tags: [design, ui, ux, frontend, css]
+category: design
 color: "#a855f7"
 emoji: 🎨
 vibe: Production-grade design intelligence. Real code, committed choices, no AI slop.

package/.claude/agents/engineering/engineering-ai-data-remediation-engineer.md

@@ -1,6 +1,9 @@
 ---
 name: AI Data Remediation Engineer
-description: "Specialist in self-healing data pipelines — uses air-gapped local SLMs and semantic clustering to automatically detect, classify, and fix data anomalies at scale. Focuses exclusively on the remediation layer: intercepting bad data, generating deterministic fix logic via Ollama, and guaranteeing zero data loss. Not a general data engineer — a surgical specialist for when your data is broken and the pipeline can't stop."
+description: Self-healing data pipeline specialist that detects, classifies, and fixes data anomalies with air-gapped local SLMs and semantic clustering, with zero data loss
+when_to_use: Use when bad data must be intercepted and repaired inside a running pipeline without stopping it; for building new pipelines use Data Engineer
+tags: [data-quality, data-pipeline, llm, remediation]
+category: data-ai
 color: "#22c55e"
 emoji: 🧬
 vibe: Fixes your broken data with surgical AI precision — no rows left behind.

package/.claude/agents/engineering/engineering-ai-engineer.md

@@ -1,6 +1,9 @@
 ---
 name: AI Engineer
-description: Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered applications with emphasis on practical, scalable solutions.
+description: AI/ML engineer who builds, deploys, and integrates machine learning models and AI-powered features into production systems
+when_to_use: Use when building or integrating ML models, LLM features, embeddings, or inference into a product; to audit an existing model use Model QA Specialist
+tags: [ai, ml, llm, deployment]
+category: data-ai
 color: "#3b82f6"
 emoji: 🤖
 vibe: Turns ML models into production features that actually scale.

package/.claude/agents/engineering/engineering-autonomous-optimization-architect.md

@@ -1,6 +1,9 @@
 ---
 name: Autonomous Optimization Architect
 description: Intelligent system governor that continuously shadow-tests APIs for performance while enforcing strict financial and security guardrails against runaway costs.
+when_to_use: Use when LLM or API routing needs shadow-testing of cheaper models with LLM-as-judge grading, circuit breakers, and cost guardrails
+tags: [llm, cost, routing, guardrails, shadow-testing]
+category: data-ai
 color: "#673AB7"
 emoji: ⚡
 vibe: The system governor that makes things faster without bankrupting you.

package/.claude/agents/engineering/engineering-backend-architect.md

@@ -1,6 +1,9 @@
 ---
 name: Backend Architect
-description: Senior backend architect specializing in scalable system design, database architecture, API development, and cloud infrastructure. Builds robust, secure, performant server-side applications and microservices
+description: Backend architect for scalable server-side systems — database schemas, API design, microservices, event-driven flows, and cloud infrastructure
+when_to_use: Use when designing server-side APIs, database schemas, microservices, or cloud backends; for domain boundaries use Software Architect
+tags: [architecture, backend, api, database, microservices]
+category: architecture
 color: "#3b82f6"
 emoji: 🏗️
 vibe: Designs the systems that hold everything up — databases, APIs, cloud, scale.

package/.claude/agents/engineering/engineering-code-reviewer.md

@@ -1,6 +1,11 @@
 ---
 name: Code Reviewer
 description: Expert code reviewer who provides constructive, actionable feedback focused on correctness, maintainability, security, and performance — not style preferences.
+when_to_use: Use when a code review should teach, marking blockers, suggestions, and nits; deprecated for picks, prefer reviewer
+tags: [review, quality, security, maintainability]
+category: core
+deprecated: true
+deprecatedBy: reviewer
 color: "#a855f7"
 emoji: 👁️
 vibe: Reviews code like a mentor, not a gatekeeper. Every comment teaches something.

package/.claude/agents/engineering/engineering-data-engineer.md

@@ -1,6 +1,9 @@
 ---
 name: Data Engineer
-description: Expert data engineer specializing in building reliable data pipelines, lakehouse architectures, and scalable data infrastructure. Masters ETL/ELT, Apache Spark, dbt, streaming systems, and cloud data platforms to turn raw data into trusted, analytics-ready assets.
+description: Data engineer who builds reliable ETL/ELT pipelines, lakehouse architectures, and streaming systems with Spark, dbt, and cloud data platforms
+when_to_use: Use when building or fixing data pipelines, warehouses, lakehouses, or streaming ingestion; for app database tuning use Database Optimizer
+tags: [data-pipeline, etl, spark, dbt, streaming]
+category: data-ai
 color: "#f97316"
 emoji: 🔧
 vibe: Builds the pipelines that turn raw data into trusted, analytics-ready assets.

package/.claude/agents/engineering/engineering-database-optimizer.md

@@ -1,6 +1,9 @@
 ---
 name: Database Optimizer
-description: Expert database specialist focusing on schema design, query optimization, indexing strategies, and performance tuning for PostgreSQL, MySQL, and modern databases like Supabase and PlanetScale.
+description: Database specialist for schema design, query optimization, indexing, and performance tuning on PostgreSQL, MySQL, Supabase, and PlanetScale
+when_to_use: Use when an app database needs schema design, slow-query fixes, indexing, or migration planning; for analytics pipelines use Data Engineer
+tags: [database, sql, postgresql, performance, indexing]
+category: data-ai
 color: "#f59e0b"
 emoji: 🗄️
 vibe: Indexes, query plans, and schema design — databases that don't wake you at 3am.

package/.claude/agents/engineering/engineering-devops-automator.md

@@ -1,6 +1,9 @@
 ---
 name: DevOps Automator
 description: Expert DevOps engineer specializing in infrastructure automation, CI/CD pipeline development, and cloud operations
+when_to_use: Use when setting up CI/CD pipelines, infrastructure as code, containers, or cloud deployment automation; for GitHub Actions specifically use workflow-automation
+tags: [devops, ci-cd, infrastructure, cloud, automation]
+category: devops
 color: "#f97316"
 emoji: ⚙️
 vibe: Automates infrastructure so your team ships faster and sleeps better.

package/.claude/agents/engineering/engineering-embedded-firmware-engineer.md

@@ -1,6 +1,9 @@
 ---
 name: Embedded Firmware Engineer
 description: Specialist in bare-metal and RTOS firmware - ESP32/ESP-IDF, PlatformIO, Arduino, ARM Cortex-M, STM32 HAL/LL, Nordic nRF5/nRF Connect SDK, FreeRTOS, Zephyr
+when_to_use: Use when writing or debugging bare-metal or RTOS firmware for ESP32, STM32, nRF, or other microcontrollers
+tags: [embedded, firmware, rtos, iot]
+category: engineering
 color: "#f97316"
 emoji: 🔩
 vibe: Writes production-grade firmware for hardware that can't afford to crash.

package/.claude/agents/engineering/engineering-feishu-integration-developer.md

@@ -1,6 +1,9 @@
 ---
 name: Feishu Integration Developer
-description: Full-stack integration expert specializing in the Feishu (Lark) Open Platform — proficient in Feishu bots, mini programs, approval workflows, Bitable (multidimensional spreadsheets), interactive message cards, Webhooks, SSO authentication, and workflow automation, building enterprise-grade collaboration and automation solutions within the Feishu ecosystem.
+description: Feishu (Lark) Open Platform integration developer for bots, mini programs, approval workflows, Bitable, message cards, webhooks, and SSO
+when_to_use: Use when building on the Feishu or Lark Open Platform (bots, approvals, Bitable, message cards, SSO); not for other chat platforms
+tags: [integration, feishu, bots, webhooks, automation]
+category: engineering
 color: "#3b82f6"
 emoji: 🔗
 vibe: Builds enterprise integrations on the Feishu (Lark) platform — bots, approvals, data sync, and SSO — so your team's workflows run on autopilot.

package/.claude/agents/engineering/engineering-frontend-developer.md

@@ -1,6 +1,9 @@
 ---
 name: Frontend Developer
 description: Expert frontend developer specializing in modern web technologies, React/Vue/Angular frameworks, UI implementation, and performance optimization
+when_to_use: Use when implementing web UI in React, Vue, or Angular, fixing frontend bugs, or improving page performance; for visual design direction use Monodesign
+tags: [frontend, react, ui, web, performance]
+category: engineering
 color: "#06b6d4"
 emoji: 🖥️
 vibe: Builds responsive, accessible web apps with pixel-perfect precision.

package/.claude/agents/engineering/engineering-git-workflow-master.md

@@ -1,6 +1,9 @@
 ---
 name: Git Workflow Master
-description: Expert in Git workflows, branching strategies, and version control best practices including conventional commits, rebasing, worktrees, and CI-friendly branch management.
+description: Git workflow expert for branching strategies, conventional commits, rebasing, worktrees, and CI-friendly branch management
+when_to_use: Use when choosing a branching strategy, untangling history, rebasing, or setting up worktrees and commit conventions; not for GitHub PR or issue work
+tags: [git, version-control, branching, workflow]
+category: devops
 color: "#f97316"
 emoji: 🌿
 vibe: Clean history, atomic commits, and branches that tell a story.

package/.claude/agents/engineering/engineering-incident-response-commander.md

@@ -1,6 +1,9 @@
 ---
 name: Incident Response Commander
-description: Expert incident commander specializing in production incident management, structured response coordination, post-mortem facilitation, SLO/SLI tracking, and on-call process design for reliable engineering organizations.
+description: Incident commander for production outages — structured response coordination, post-mortems, SLO/SLI tracking, and on-call process design
+when_to_use: Use when a production incident needs coordinated response, a post-mortem, or on-call process design; for SLO and toil engineering use SRE
+tags: [incident-response, on-call, postmortem, reliability]
+category: devops
 color: "#e63946"
 emoji: 🚨
 vibe: Turns production chaos into structured resolution.

package/.claude/agents/engineering/engineering-mobile-app-builder.md

@@ -1,6 +1,9 @@
 ---
 name: Mobile App Builder
 description: Specialized mobile application developer with expertise in native iOS/Android development and cross-platform frameworks
+when_to_use: Use when building iOS, Android, or cross-platform (React Native, Flutter) apps, including native features, offline sync, and store readiness
+tags: [mobile, ios, android, react-native, flutter]
+category: engineering
 color: "#a855f7"
 emoji: 📲
 vibe: Ships native-quality apps on iOS and Android, fast.

package/.claude/agents/engineering/engineering-rapid-prototyper.md

@@ -1,6 +1,9 @@
 ---
 name: Rapid Prototyper
 description: Specialized in ultra-fast proof-of-concept development and MVP creation using efficient tools and frameworks
+when_to_use: Use when you need a fast proof of concept or MVP to validate an idea, trading polish for speed; not for production-hardened code
+tags: [prototyping, mvp, implementation]
+category: engineering
 color: "#22c55e"
 emoji: ⚡
 vibe: Turns an idea into a working prototype before the meeting's over.

package/.claude/agents/engineering/engineering-security-engineer.md

@@ -1,6 +1,9 @@
 ---
 name: Security Engineer
-description: Expert application security engineer specializing in threat modeling, vulnerability assessment, secure code review, and security architecture design for modern web and cloud-native applications.
+description: Application security engineer for threat modeling, vulnerability assessment, secure code review, and security architecture of web and cloud apps
+when_to_use: Use when an app, API, or cloud service needs threat modeling, a security code review, OWASP checks, or a vulnerability assessment
+tags: [security, owasp, threat-modeling, audit, appsec]
+category: security
 color: "#ef4444"
 emoji: 🔒
 vibe: Models threats, reviews code, and designs security architecture that actually holds.

package/.claude/agents/engineering/engineering-senior-developer.md

@@ -1,6 +1,9 @@
 ---
 name: Senior Developer
 description: Premium implementation specialist - Masters Laravel/Livewire/FluxUI, advanced CSS, Three.js integration
+when_to_use: Use when implementing premium Laravel, Livewire, or FluxUI features, advanced CSS, or Three.js scenes; for general code use coder
+tags: [laravel, php, css, threejs, implementation]
+category: engineering
 color: "#22c55e"
 emoji: 💎
 vibe: Premium full-stack craftsperson — Laravel, Livewire, Three.js, advanced CSS.

package/.claude/agents/engineering/engineering-software-architect.md

@@ -1,6 +1,9 @@
 ---
 name: Software Architect
-description: Expert software architect specializing in system design, domain-driven design, architectural patterns, and technical decision-making for scalable, maintainable systems.
+description: Software architect for domain-driven design, bounded contexts, architectural patterns, and ADRs that name trade-offs for maintainable systems
+when_to_use: Use when modeling a domain, drawing module or service boundaries, or choosing monolith vs microservices; for server APIs and DBs use Backend Architect
+tags: [architecture, ddd, adr, patterns, trade-offs]
+category: architecture
 color: "#6366f1"
 emoji: 🏛️
 vibe: Designs systems that survive the team that built them. Every decision has a trade-off — name it.

package/.claude/agents/engineering/engineering-solidity-smart-contract-engineer.md

@@ -1,6 +1,9 @@
 ---
 name: Solidity Smart Contract Engineer
-description: Expert Solidity developer specializing in EVM smart contract architecture, gas optimization, upgradeable proxy patterns, DeFi protocol development, and security-first contract design across Ethereum and L2 chains.
+description: Solidity engineer for EVM smart contracts — gas optimization, upgradeable proxies, DeFi protocols, and security-first design on Ethereum and L2s
+when_to_use: Use when writing or optimizing Solidity contracts, proxies, or DeFi protocols; for an independent audit use Blockchain Security Auditor
+tags: [blockchain, solidity, smart-contracts, defi, evm]
+category: engineering
 color: "#f97316"
 emoji: ⛓️
 vibe: Battle-hardened Solidity developer who lives and breathes the EVM.

package/.claude/agents/engineering/engineering-sre.md

@@ -1,6 +1,9 @@
 ---
 name: SRE (Site Reliability Engineer)
 description: Expert site reliability engineer specializing in SLOs, error budgets, observability, chaos engineering, and toil reduction for production systems at scale.
+when_to_use: Use when defining SLOs and error budgets, improving observability, running chaos experiments, or cutting toil; for a live outage use Incident Response Commander
+tags: [sre, reliability, observability, slo, chaos-engineering]
+category: devops
 color: "#e63946"
 emoji: 🛡️
 vibe: Reliability is a feature. Error budgets fund velocity — spend them wisely.

package/.claude/agents/engineering/engineering-technical-writer.md

@@ -1,6 +1,9 @@
 ---
 name: Technical Writer
-description: Expert technical writer specializing in developer documentation, API references, README files, and tutorials. Transforms complex engineering concepts into clear, accurate, and engaging docs that developers actually read and use.
+description: Technical writer for developer docs, API references, READMEs, and tutorials that turn complex engineering concepts into clear, accurate documentation
+when_to_use: Use when writing or restructuring READMEs, API references, tutorials, or developer guides; not for marketing copy
+tags: [documentation, api-docs, tutorials, writing]
+category: engineering
 color: "#14b8a6"
 emoji: 📚
 vibe: Writes the docs that developers actually read and use.

package/.claude/agents/engineering/engineering-threat-detection-engineer.md

@@ -1,6 +1,9 @@
 ---
 name: Threat Detection Engineer
-description: Expert detection engineer specializing in SIEM rule development, MITRE ATT&CK coverage mapping, threat hunting, alert tuning, and detection-as-code pipelines for security operations teams.
+description: Detection engineer for SIEM rules, MITRE ATT&CK coverage mapping, threat hunting, alert tuning, and detection-as-code pipelines
+when_to_use: Use when writing SIEM detections, mapping ATT&CK coverage, hunting threats, or tuning noisy alerts; for app code review use Security Engineer
+tags: [security, siem, detection, threat-hunting, mitre-attack]
+category: security
 color: "#7b2d8e"
 emoji: 🎯
 vibe: Builds the detection layer that catches attackers after they bypass prevention.

package/.claude/agents/engineering/engineering-wechat-mini-program-developer.md

@@ -1,6 +1,9 @@
 ---
 name: WeChat Mini Program Developer
-description: Expert WeChat Mini Program developer specializing in 小程序 development with WXML/WXSS/WXS, WeChat API integration, payment systems, subscription messaging, and the full WeChat ecosystem.
+description: WeChat Mini Program developer for WXML/WXSS/WXS, WeChat API integration, payments, subscription messaging, and the wider WeChat ecosystem
+when_to_use: Use when building or debugging a WeChat Mini Program, WeChat Pay, or WeChat API integration
+tags: [wechat, mini-program, mobile, payments]
+category: engineering
 color: "#22c55e"
 emoji: 💬
 vibe: Builds performant Mini Programs that thrive in the WeChat ecosystem.

package/.claude/agents/github/github-modes.md

@@ -1,7 +1,9 @@
 ---
 name: github-modes
-description: |
-  Comprehensive GitHub integration modes for workflow orchestration, PR management, and repository coordination with batch optimization
+description: Reference of GitHub workflow modes (gh-coordinator, pr-manager, issue-tracker, release-manager, and more) with batch-optimized gh CLI usage
+when_to_use: Use when choosing which GitHub workflow mode fits a task or coordinating a mixed GitHub workflow; for one PR or issue use the specific agent
+tags: [github, workflow, coordination, gh-cli]
+category: github
 ---
 
 # GitHub Integration Modes

package/.claude/agents/github/issue-tracker.md

@@ -1,7 +1,9 @@
 ---
 name: issue-tracker
-description: |
-  Intelligent issue management and project coordination with automated tracking, progress monitoring, and team coordination
+description: GitHub issue manager that creates, labels, updates, links, and decomposes issues and milestones with templates and progress comments
+when_to_use: Use when creating, triaging, labeling, tracking, or decomposing GitHub issues and milestones
+tags: [github, issues, triage, project-management]
+category: github
 ---
 
 # GitHub Issue Tracker

package/.claude/agents/github/monoswarm-code-review.md

@@ -1,7 +1,9 @@
 ---
 name: monoswarm-code-review
-description: |
-  Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis
+description: Multi-agent GitHub PR review swarm that runs security, performance, and architecture reviewers in parallel and posts findings to the PR
+when_to_use: Use when a large PR needs parallel specialist reviews posted as GitHub comments; for a single-reviewer pass use reviewer
+tags: [github, review, pull-requests, swarm, security]
+category: github
 ---
 
 # Code Review Swarm - Automated Code Review with AI Agents

package/.claude/agents/github/monoswarm-issue.md

@@ -2,6 +2,11 @@
 name: monoswarm-issue
 description: |
   GitHub issue-based swarm coordination agent that transforms issues into intelligent multi-agent tasks with automatic decomposition and progress tracking
+when_to_use: Use when a GitHub issue should drive label-based swarm agent assignment; deprecated for picks, prefer issue-tracker
+tags: [github, issues, swarm, decomposition]
+category: github
+deprecated: true
+deprecatedBy: issue-tracker
 ---
 
 # Swarm Issue - Issue-Based Swarm Coordination

package/.claude/agents/github/monoswarm-multi-repo.md

@@ -1,6 +1,9 @@
 ---
 name: monoswarm-multi-repo
-description: Cross-repository swarm orchestration for organization-wide automation and intelligent collaboration
+description: Rolls one change out across many repositories in an org — repo discovery, synchronized edits, linked PRs, and cross-repo dependency updates
+when_to_use: Use when one change must land in many repos of an org with linked PRs; for one repo's layout use repo-architect, for versions use sync-coordinator
+tags: [github, multi-repo, automation, dependencies]
+category: github
 ---
 
 # Multi-Repo Swarm - Cross-Repository Swarm Orchestration

package/.claude/agents/github/monoswarm-pr.md

@@ -2,6 +2,11 @@
 name: monoswarm-pr
 description: |
   Pull request swarm management agent that coordinates multi-agent code review, validation, and integration workflows with automated PR lifecycle management
+when_to_use: Use when PR comments or labels should drive swarm agents on a pull request; deprecated for picks, prefer pr-manager
+tags: [github, pull-requests, swarm, automation]
+category: github
+deprecated: true
+deprecatedBy: pr-manager
 ---
 
 # Swarm PR - Managing Swarms through Pull Requests

package/.claude/agents/github/pr-manager.md

@@ -1,7 +1,9 @@
 ---
 name: pr-manager
-description: |
-  Comprehensive pull request management with swarm coordination for automated reviews, testing, and merge workflows
+description: GitHub pull request manager for creating, reviewing, testing, and merging PRs with multi-reviewer coordination and conflict resolution
+when_to_use: Use when creating, reviewing, coordinating, or merging GitHub pull requests, including multi-reviewer runs and conflict resolution
+tags: [github, pull-requests, review, merge]
+category: github
 ---
 
 # GitHub PR Manager

package/.claude/agents/github/project-board-sync.md

@@ -1,7 +1,9 @@
 ---
 name: project-board-sync
-description: |
-  Synchronize AI swarms with GitHub Projects for visual task management, progress tracking, and team coordination
+description: Synchronizes swarm tasks with GitHub Projects boards — cards, custom fields, status columns, and progress views
+when_to_use: Use when swarm or team tasks should be mirrored onto a GitHub Projects board and kept in sync
+tags: [github, projects, project-management, tracking]
+category: github
 ---
 
 # Project Board Sync - GitHub Projects Integration

package/.claude/agents/github/release-manager.md

@@ -1,7 +1,9 @@
 ---
 name: release-manager
-description: |
-  Automated release coordination and deployment with Monomind swarm orchestration for seamless version management, testing, and deployment across multiple packages
+description: Release coordinator for version bumps, changelogs, release validation, tagging, and deployment with rollback across multiple packages
+when_to_use: Use when cutting a release (version bumps, changelog, validation, tagging, publishing) across packages; not for day-to-day PR work
+tags: [github, releases, versioning, changelog, deployment]
+category: github
 ---
 
 # GitHub Release Manager

package/.claude/agents/github/repo-architect.md

@@ -1,7 +1,9 @@
 ---
 name: repo-architect
-description: |
-  Repository structure optimization and multi-repo management with Monomind swarm coordination for scalable project architecture and development workflows
+description: Designs a repository's structure — directory layout, templates, and conventions — and recommends improvements for scalable project architecture
+when_to_use: Use when organizing or restructuring a repository's layout, templates, and conventions; for rolling changes across many repos use monoswarm-multi-repo
+tags: [github, repository, structure, templates, monorepo]
+category: github
 ---
 
 # GitHub Repository Architect

package/.claude/agents/github/sync-coordinator.md

@@ -1,7 +1,9 @@
 ---
 name: sync-coordinator
-description: |
-  Multi-repository synchronization coordinator that manages version alignment, dependency synchronization, and cross-package integration with intelligent swarm orchestration
+description: Keeps packages aligned — versions, dependencies, cross-package integration tests, and docs — across a monorepo or related repositories
+when_to_use: Use when package versions or dependencies drift across a monorepo or related repos and need aligning; not for repo layout or org-wide rollouts
+tags: [github, monorepo, versioning, dependencies, sync]
+category: github
 ---
 
 # GitHub Sync Coordinator

package/.claude/agents/github/workflow-automation.md

@@ -1,7 +1,9 @@
 ---
 name: workflow-automation
-description: |
-  GitHub Actions workflow automation agent that creates intelligent, self-organizing CI/CD pipelines with adaptive multi-agent coordination and automated optimization
+description: GitHub Actions automation that generates and optimizes CI/CD workflows, smart test selection, security scans, and failure analysis
+when_to_use: Use when creating, optimizing, or debugging GitHub Actions workflows; for non-GitHub CI/CD or infrastructure use DevOps Automator
+tags: [github, github-actions, ci-cd, automation]
+category: github
 ---
 
 # Workflow Automation - GitHub Actions Integration

package/.claude/agents/goal/goal-planner.md

@@ -1,9 +1,23 @@
 ---
 name: goal-planner
-description: |
-  Goal-Oriented Action Planning (GOAP) specialist that dynamically creates intelligent plans to achieve complex objectives. Uses gaming AI techniques to discover novel solutions by combining actions in creative ways. Excels at adaptive replanning, multi-step reasoning, and finding optimal paths through complex state spaces. Examples: <example>Context: User needs to optimize a complex workflow with many dependencies. user: 'I need to deploy this application but there are many prerequisites and dependencies' assistant: 'I'll use the goal-planner agent to analyze all requirements and create an optimal action sequence that satisfies all preconditions and achieves your deployment goal.' <commentary>Complex multi-step planning with dependencies requires the goal-planner agent's GOAP algorithm to find the optimal path.</commentary></example> <example>Context: User has a high-level goal but isn't sure of the steps. user: 'Make my application production-ready' assistant: 'I'll use the goal-planner agent to break down this goal into concrete actions, analyze preconditions, and create an adaptive plan that achieves production readiness.' <commentary>High-level goals that need intelligent decomposition and planning benefit from the goal-planner agent's capabilities.</commentary></example>
+description: Goal-Oriented Action Planning (GOAP) specialist that finds optimal action sequences from preconditions, effects, and costs, and replans adaptively
+when_to_use: Use when a high-level goal has many prerequisites and needs an optimal, adaptively replanned action sequence; for simple task lists use planner
+tags: [planning, goap, decomposition, replanning]
+category: core
 ---
 
+## Example uses
+
+- **Context:** User needs to optimize a complex workflow with many dependencies.
+  - User: "I need to deploy this application but there are many prerequisites and dependencies"
+  - Assistant: "I'll use the goal-planner agent to analyze all requirements and create an optimal action sequence that satisfies all preconditions and achieves your deployment goal."
+  - Why: Complex multi-step planning with dependencies requires the goal-planner agent's GOAP algorithm to find the optimal path.
+
+- **Context:** User has a high-level goal but isn't sure of the steps.
+  - User: "Make my application production-ready"
+  - Assistant: "I'll use the goal-planner agent to break down this goal into concrete actions, analyze preconditions, and create an adaptive plan that achieves production readiness."
+  - Why: High-level goals that need intelligent decomposition and planning benefit from the goal-planner agent's capabilities.
+
 You are a Goal-Oriented Action Planning (GOAP) specialist, an advanced AI planner that uses intelligent algorithms to dynamically create optimal action sequences for achieving complex objectives. Your expertise combines gaming AI techniques with practical software engineering to discover novel solutions through creative action composition.
 
 Your core capabilities:

package/.claude/agents/marketing/marketing-competitive-content.md

@@ -1,6 +1,9 @@
 ---
 name: Competitive Content Strategist
-description: Expert in competitive positioning content, comparison pages, alternative pages, content strategy, and topic planning. Use for competitor comparison pages (X vs Y), alternative pages (Best X alternatives), content strategy and editorial planning, topic cluster design, or any content that positions your product in a competitive landscape.
+description: Competitive positioning content strategist for X-vs-Y comparison pages, alternatives pages, topic clusters, and editorial planning
+when_to_use: Use when writing competitor comparison or alternatives pages, or planning content strategy and topic clusters
+tags: [marketing, content, seo, competitive]
+category: marketing
 color: "#ef4444"
 emoji: ⚔️
 vibe: Wins the search query where buyers are already deciding — before they've made up their minds.