@dragonflymcp/plugin 1.0.0

package/templates/stubs/agents/documentation-concept.md

@@ -0,0 +1,39 @@
+---
+name: documentation-concept
+type: workflow
+execution: task-tool
+model: sonnet
+color: magenta
+description: Documentation Concept - Generates comprehensive documentation at every workflow phase using Sonnet 4.5
+
+tools: "*"
+
+# Enhanced Metadata (Phase 3)
+cost_per_action: 0.003
+optimization_level: "baseline"
+expected_context_tokens: 800
+expected_duration_seconds: 5
+
+# Component-Scoped Hooks
+hooks:
+  Stop:
+    - type: command
+      command: "bash .claude/hooks/concept-complete.sh documentation"
+
+# Skills (Phase 7)
+skills:
+  # P0 - Critical
+  - documentation-generation      # Templates, formats, standards
+  - project-structure             # Correct file placement
+  # P1 - Core
+  - api-design-patterns           # API documentation standards
+  - changelog-generation          # Keep a Changelog format
+  # P2 - Enhancement
+  - code-style-enforcement        # Consistent formatting
+  # Existing Skills
+  - schema-validation
+  - wysiwid-principles
+---
+
+Call zen_get_agent_prompt with agent="documentation-concept" and taskContext from your current task.
+Use the returned prompt as your instructions. Follow it exactly.

package/templates/stubs/agents/implementation-concept.md

@@ -0,0 +1,41 @@
+---
+name: implementation-concept
+type: workflow
+execution: task-tool
+model: sonnet
+color: green
+description: Implementation Concept - Generates code from architecture specifications using Sonnet 4.5 for high-quality code generation
+tools: "*"
+
+# Enhanced Metadata (Phase 3)
+cost_per_action: 0.003
+optimization_level: "phase2"
+expected_context_tokens: 1000
+expected_duration_seconds: 10
+
+# Component-Scoped Hooks
+hooks:
+  Stop:
+    - type: command
+      command: "bash .claude/hooks/concept-complete.sh implementation"
+
+# Skills (Phase 7)
+skills:
+  # P0 - Critical
+  - project-structure             # Directory boundaries, file placement rules
+  - security-vulnerability-scanning # Prevent introducing security issues
+  - error-classification          # Handle errors appropriately
+  # P1 - Core
+  - test-generation-strategy      # Coverage optimization, edge case detection, test structure
+  - code-template-patterns        # Reusable scaffolding patterns
+  - refactoring-patterns          # Code smell detection, safe transformations
+  # P2 - Enhancement
+  - code-style-enforcement        # Project-aware formatting and linting
+  # Operational
+  - smart-retry
+  - batch-processing
+  - output-caching
+---
+
+Call zen_get_agent_prompt with agent="implementation-concept" and taskContext from your current task.
+Use the returned prompt as your instructions. Follow it exactly.

package/templates/stubs/agents/quality-concept.md

@@ -0,0 +1,41 @@
+---
+name: quality-concept
+type: workflow
+execution: task-tool
+model: sonnet
+color: yellow
+description: Quality Concept - Reviews code and runs tests using Sonnet 4.5 for thorough code review and quality analysis
+tools: "*"
+
+# Enhanced Metadata (Phase 3)
+cost_per_action: 0.003
+optimization_level: "phase2"
+expected_context_tokens: 1000
+expected_duration_seconds: 8
+
+# Component-Scoped Hooks
+hooks:
+  Stop:
+    - type: command
+      command: "bash .claude/hooks/concept-complete.sh quality"
+
+# Skills (Phase 7)
+skills:
+  # P0 - Security & Structure
+  - ide-diagnostics               # TypeScript/ESLint errors via native mcp__ide__getDiagnostics
+  - security-vulnerability-scanning # SQL injection, XSS, command injection detection
+  - project-structure             # Validate files are in correct locations
+  - documentation-generation      # Validate documentation completeness
+  - error-classification          # Error taxonomy, retryability, response strategies
+  # P2 - Enhancement
+  - code-coverage-analysis        # Gap identification, prioritized test recommendations
+  # P3 - Additional
+  - performance-testing-patterns  # Load testing, stress testing, benchmarking
+  - accessibility-checking        # WCAG compliance, ARIA best practices
+  # Existing Skills
+  - smart-retry
+  - workflow-replay
+---
+
+Call zen_get_agent_prompt with agent="quality-concept" and taskContext from your current task.
+Use the returned prompt as your instructions. Follow it exactly.

package/templates/stubs/agents/research-concept.md

@@ -0,0 +1,35 @@
+---
+name: research-concept
+type: workflow
+execution: task-tool
+model: sonnet
+color: purple
+description: Research Concept - Gathers academic papers, documentation, and evidence before architecture decisions
+
+tools: "*"
+
+# Enhanced Metadata (Phase 3)
+cost_per_action: 0.02
+optimization_level: "thorough"
+expected_context_tokens: 2000
+expected_duration_seconds: 300
+
+# Component-Scoped Hooks
+hooks:
+  Stop:
+    - type: command
+      command: "bash .claude/hooks/concept-complete.sh research"
+
+# Skills (Phase 7)
+skills:
+  # P0 - Critical
+  - project-structure             # Understand codebase layout
+  # P1 - Core
+  - cross-project-knowledge       # Apply patterns from other projects
+  - dependency-impact-analysis    # Understand what's affected
+  # Research Skills
+  - smart-summarization           # Synthesize findings
+---
+
+Call zen_get_agent_prompt with agent="research-concept" and taskContext from your current task.
+Use the returned prompt as your instructions. Follow it exactly.

package/templates/stubs/agents/security-concept.md

@@ -0,0 +1,40 @@
+---
+name: security-concept
+type: workflow
+execution: task-tool
+model: sonnet
+color: red
+description: Security Concept - Continuous security assurance with threat modeling, vulnerability scanning, and commit verification
+
+tools: "*"
+
+# Enhanced Metadata (Phase 3)
+cost_per_action: 0.002
+optimization_level: "phase2"
+expected_context_tokens: 1500
+expected_duration_seconds: 8
+
+# Component-Scoped Hooks
+hooks:
+  Stop:
+    - type: command
+      command: "bash .claude/hooks/concept-complete.sh security"
+
+# Skills (Phase 7)
+skills:
+  # P0 - Critical
+  - security-vulnerability-scanning # OWASP Top 10, injection, XSS, secrets
+  - security-design-patterns        # Auth, authz, crypto patterns
+  - error-classification           # Security error handling
+  # P1 - Core
+  - schema-validation              # Validate security state files
+  - dependency-impact-analysis     # Understand security implications of changes
+  # P2 - Enhancement
+  - code-coverage-analysis         # Security test coverage
+  # Operational
+  - smart-retry
+  - workflow-replay
+---
+
+Call zen_get_agent_prompt with agent="security-concept" and taskContext from your current task.
+Use the returned prompt as your instructions. Follow it exactly.

package/templates/stubs/agents/spec-concept.md

@@ -0,0 +1,35 @@
+---
+name: spec-concept
+type: workflow
+execution: task-tool
+model: sonnet
+color: cyan
+description: Spec Concept - Defines structured specifications and generates type-safe code generation prompts using Sonnet 4.5
+tools: "*"
+
+# Enhanced Metadata (Phase 3)
+cost_per_action: 0.005
+optimization_level: "phase2"
+expected_context_tokens: 800
+expected_duration_seconds: 8
+
+# Component-Scoped Hooks
+hooks:
+  Stop:
+    - type: command
+      command: "bash .claude/hooks/concept-complete.sh spec"
+
+# Skills (Phase 7)
+skills:
+  # P0 - Critical
+  - project-structure
+  - error-classification
+  # P1 - Core
+  - code-template-patterns
+  - test-generation-strategy
+  # Operational
+  - output-caching
+---
+
+Call zen_get_agent_prompt with agent="spec-concept" and taskContext from your current task.
+Use the returned prompt as your instructions. Follow it exactly.

package/templates/stubs/agents/story-concept.md

@@ -0,0 +1,36 @@
+---
+name: story-concept
+type: workflow
+execution: task-tool
+model: sonnet
+color: blue
+description: Story Concept - Captures and validates user requirements using Sonnet 4.5 for thorough story analysis
+tools: "*"
+
+# Enhanced Metadata (Phase 3)
+cost_per_action: 0.003
+optimization_level: "baseline"
+expected_context_tokens: 500
+expected_duration_seconds: 5
+
+# Component-Scoped Hooks
+hooks:
+  Stop:
+    - type: command
+      command: "bash .claude/hooks/concept-complete.sh story"
+
+# Skills (Phase 7)
+skills:
+  # P0 - Critical
+  - schema-validation             # Validate story structure
+  # P1 - Core
+  - story-decomposition           # INVEST criteria, task breakdown, dependency mapping
+  - acceptance-criteria-generation # Given-When-Then templates, coverage checklist
+  - semantic-memory               # Remember patterns from previous stories
+  # P2 - Enhancement
+  - effort-estimation             # Story points, T-shirt sizing, three-point estimation
+  - requirement-prioritization    # MoSCoW, RICE scoring, value/effort matrices
+---
+
+Call zen_get_agent_prompt with agent="story-concept" and taskContext from your current task.
+Use the returned prompt as your instructions. Follow it exactly.

package/templates/stubs/agents/verification-concept.md

@@ -0,0 +1,39 @@
+---
+name: verification-concept
+type: workflow
+execution: task-tool
+model: sonnet
+color: indigo
+description: Verification Concept - Multi-pass verification of architecture and implementation for 39.7% accuracy improvement
+
+tools: "*"
+
+# Enhanced Metadata (Phase 3)
+cost_per_action: 0.003
+optimization_level: "phase2"
+expected_context_tokens: 2500
+expected_duration_seconds: 12
+
+# Component-Scoped Hooks
+hooks:
+  Stop:
+    - type: command
+      command: "bash .claude/hooks/concept-complete.sh verification"
+
+# Skills (Phase 7)
+skills:
+  # P0 - Critical
+  - security-vulnerability-scanning # Deep security analysis
+  - error-classification          # Error taxonomy for issues found
+  # P1 - Core
+  - dependency-impact-analysis    # Understand change impact
+  - cross-project-knowledge       # Apply patterns from other projects
+  # P2 - Enhancement
+  - code-coverage-analysis        # Validate test coverage
+  # Existing Skills
+  - smart-retry
+  - workflow-replay
+---
+
+Call zen_get_agent_prompt with agent="verification-concept" and taskContext from your current task.
+Use the returned prompt as your instructions. Follow it exactly.

package/templates/stubs/agents/version-concept.md

@@ -0,0 +1,37 @@
+---
+name: version-concept
+type: workflow
+execution: task-tool
+model: sonnet
+color: orange
+description: Version Concept - Manages git operations (branches, commits, tags) using Sonnet 4.5 for intelligent version control
+tools: "*"
+
+# Enhanced Metadata (Phase 3)
+cost_per_action: 0.003
+optimization_level: "baseline"
+expected_context_tokens: 500
+expected_duration_seconds: 5
+
+# Component-Scoped Hooks
+hooks:
+  Stop:
+    - type: command
+      command: "bash .claude/hooks/concept-complete.sh version"
+
+# Skills (Phase 7)
+skills:
+  # P1 - Core
+  - changelog-generation          # Conventional commit parsing, Keep a Changelog format
+  # P2 - Enhancement
+  - semantic-versioning           # Version bump determination, breaking change detection
+  # P3 - Additional
+  - release-management            # Release planning, deployment strategies, rollback
+  - branch-strategy               # Git flow, trunk-based, GitHub flow patterns
+  # Existing Skills
+  - provenance-analysis
+  - synchronization-patterns
+---
+
+Call zen_get_agent_prompt with agent="version-concept" and taskContext from your current task.
+Use the returned prompt as your instructions. Follow it exactly.

package/templates/stubs/commands/cache.md.template

@@ -0,0 +1,2 @@
+Manage the concept output cache. Call zen_get_workflow with command="cache" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/checkpoint.md.template

@@ -0,0 +1,2 @@
+Create a state checkpoint to preserve context. Call zen_get_workflow with command="checkpoint" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/classify.md.template

@@ -0,0 +1,2 @@
+Classify task difficulty and recommend a model tier. Call zen_get_workflow with command="classify" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/compete.md.template

@@ -0,0 +1,2 @@
+Run a competitive evaluation comparing Zen-assisted vs vanilla Claude Code. Call zen_get_workflow with command="compete" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/costs.md.template

@@ -0,0 +1,2 @@
+Show cost analysis for AI model usage. Call zen_get_workflow with command="costs" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/estimate.md.template

@@ -0,0 +1,2 @@
+Estimate implementation effort for a task. Call zen_get_workflow with command="estimate" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/explore.md.template

@@ -0,0 +1,2 @@
+Explore multiple solution approaches using Tree-of-Thoughts. Call zen_get_workflow with command="explore" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/feature.md.template

@@ -0,0 +1,2 @@
+Create a new feature using the Story concept workflow. Call zen_get_workflow with command="feature" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/forget.md.template

@@ -0,0 +1,2 @@
+Remove a memory from semantic storage. Call zen_get_workflow with command="forget" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/global-recall.md.template

@@ -0,0 +1,2 @@
+Recall memories from the global knowledge store. Call zen_get_workflow with command="global-recall" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/global-remember.md.template

@@ -0,0 +1,2 @@
+Store knowledge in the global memory store. Call zen_get_workflow with command="global-remember" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/health.md.template

@@ -0,0 +1,2 @@
+Display context health status and safety warnings. Call zen_get_workflow with command="health" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/help.md.template

@@ -0,0 +1,2 @@
+Display context-aware help for Zen workflows and commands. Call zen_get_workflow with command="help" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/observe.md.template

@@ -0,0 +1,2 @@
+Observe and monitor workflow execution patterns. Call zen_get_workflow with command="observe" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/pr-review.md.template

@@ -0,0 +1,2 @@
+Review a pull request with automated analysis. Call zen_get_workflow with command="pr-review" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/predict-cost.md.template

@@ -0,0 +1,2 @@
+Predict the cost of implementing a feature. Call zen_get_workflow with command="predict-cost" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/profile.md.template

@@ -0,0 +1,2 @@
+View or update the project profile. Call zen_get_workflow with command="profile" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/reasoning.md.template

@@ -0,0 +1,2 @@
+View and analyze reasoning chains from architecture decisions. Call zen_get_workflow with command="reasoning" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/recall.md.template

@@ -0,0 +1,2 @@
+Retrieve memories from semantic storage. Call zen_get_workflow with command="recall" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/remember.md.template

@@ -0,0 +1,2 @@
+Store a fact or knowledge in semantic memory. Call zen_get_workflow with command="remember" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/replay.md.template

@@ -0,0 +1,2 @@
+Replay a failed workflow from provenance to debug issues. Call zen_get_workflow with command="replay" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/restore.md.template

@@ -0,0 +1,2 @@
+Restore context from a checkpoint. Call zen_get_workflow with command="restore" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/retrospective.md.template

@@ -0,0 +1,2 @@
+Run a retrospective on completed workflows. Call zen_get_workflow with command="retrospective" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/slo.md.template

@@ -0,0 +1,2 @@
+Check and manage service level objectives. Call zen_get_workflow with command="slo" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/spec.md.template

@@ -0,0 +1,2 @@
+Define a specification and generate type-safe code. Call zen_get_workflow with command="spec" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/sync.md.template

@@ -0,0 +1,2 @@
+Evaluate synchronization rules and execute next workflow step. Call zen_get_workflow with command="sync" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/task.md.template

@@ -0,0 +1,2 @@
+Manage workflow tasks. Call zen_get_workflow with command="task" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/trace.md.template

@@ -0,0 +1,2 @@
+Trace provenance chain for an action, story, or flow. Call zen_get_workflow with command="trace" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/visualize.md.template

@@ -0,0 +1,2 @@
+Visualize workflow state and dependencies. Call zen_get_workflow with command="visualize" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.

package/templates/stubs/commands/workflow.md.template

@@ -0,0 +1,2 @@
+Execute a complete feature workflow from story to deployment. Call zen_get_workflow with command="workflow" and args="${ARGUMENTS}".
+Follow the returned instructions exactly.