@harness-engineering/cli 1.1.1 → 1.2.0

package/dist/agents/commands/claude-code/harness/refactoring.md

@@ -0,0 +1,35 @@
+## <!-- Generated by harness generate-slash-commands. Do not edit. -->
+
+name: harness:refactoring
+description: Safe refactoring with validation before and after changes
+argument-hint: "[--path <path>]"
+allowed-tools:
+
+- Bash
+- Read
+- Write
+- Edit
+- Glob
+- Grep
+
+---
+
+<context>
+Cognitive mode: meticulous-implementer
+Type: flexible
+</context>
+
+<objective>
+Safe refactoring with validation before and after changes
+</objective>
+
+<execution_context>
+@agents/skills/claude-code/harness-refactoring/SKILL.md
+@agents/skills/claude-code/harness-refactoring/skill.yaml
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "harness-refactoring"
+2. If MCP unavailable: read SKILL.md and follow its workflow directly
+3. Pass through any arguments provided by the user
+</process>

package/dist/agents/commands/claude-code/harness/skill-authoring.md

@@ -0,0 +1,35 @@
+## <!-- Generated by harness generate-slash-commands. Do not edit. -->
+
+name: harness:skill-authoring
+description: Create and maintain harness skills following the rich skill format
+argument-hint: "[--path <path>]"
+allowed-tools:
+
+- Bash
+- Read
+- Write
+- Edit
+- Glob
+- Grep
+
+---
+
+<context>
+Cognitive mode: constructive-architect
+Type: flexible
+</context>
+
+<objective>
+Create and maintain harness skills following the rich skill format
+</objective>
+
+<execution_context>
+@agents/skills/claude-code/harness-skill-authoring/SKILL.md
+@agents/skills/claude-code/harness-skill-authoring/skill.yaml
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "harness-skill-authoring"
+2. If MCP unavailable: read SKILL.md and follow its workflow directly
+3. Pass through any arguments provided by the user
+</process>

package/dist/agents/commands/claude-code/harness/state-management.md

@@ -0,0 +1,35 @@
+## <!-- Generated by harness generate-slash-commands. Do not edit. -->
+
+name: harness:state-management
+description: Manage persistent session state across harness agent sessions
+argument-hint: "[--path <path>]"
+allowed-tools:
+
+- Bash
+- Read
+- Write
+- Edit
+- Glob
+
+---
+
+<context>
+Cognitive mode: meticulous-implementer
+Type: flexible
+State: persistent (files: .harness/state.json)
+</context>
+
+<objective>
+Manage persistent session state across harness agent sessions
+</objective>
+
+<execution_context>
+@agents/skills/claude-code/harness-state-management/SKILL.md
+@agents/skills/claude-code/harness-state-management/skill.yaml
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "harness-state-management"
+2. If MCP unavailable: read SKILL.md and follow its workflow directly
+3. Pass through any arguments provided by the user
+</process>

package/dist/agents/commands/claude-code/harness/tdd.md

@@ -0,0 +1,42 @@
+## <!-- Generated by harness generate-slash-commands. Do not edit. -->
+
+name: harness:tdd
+description: Test-driven development integrated with harness validation
+argument-hint: "[--path <path>]"
+allowed-tools:
+
+- Bash
+- Read
+- Write
+- Edit
+- Glob
+- Grep
+
+---
+
+<context>
+Cognitive mode: meticulous-implementer
+Type: rigid
+</context>
+
+<objective>
+Test-driven development integrated with harness validation
+
+Phases:
+
+- red: Write failing test
+- green: Implement minimal code to pass
+- refactor: Clean up while keeping tests green (optional)
+- validate: Run harness checks
+  </objective>
+
+<execution_context>
+@agents/skills/claude-code/harness-tdd/SKILL.md
+@agents/skills/claude-code/harness-tdd/skill.yaml
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "harness-tdd"
+2. If MCP unavailable: read SKILL.md and follow its workflow directly
+3. Pass through any arguments provided by the user
+</process>

package/dist/agents/commands/claude-code/harness/validate-context-engineering.md

@@ -0,0 +1,32 @@
+## <!-- Generated by harness generate-slash-commands. Do not edit. -->
+
+name: harness:validate-context-engineering
+description: Validate repository context engineering practices (AGENTS.md, doc coverage, knowledge map)
+argument-hint: "[--path <path>]"
+allowed-tools:
+
+- Bash
+- Read
+- Glob
+
+---
+
+<context>
+Cognitive mode: meticulous-verifier
+Type: flexible
+</context>
+
+<objective>
+Validate repository context engineering practices (AGENTS.md, doc coverage, knowledge map)
+</objective>
+
+<execution_context>
+@agents/skills/claude-code/validate-context-engineering/SKILL.md
+@agents/skills/claude-code/validate-context-engineering/skill.yaml
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "validate-context-engineering"
+2. If MCP unavailable: read SKILL.md and follow its workflow directly
+3. Pass through any arguments provided by the user
+</process>

package/dist/agents/commands/claude-code/harness/verification.md

@@ -0,0 +1,38 @@
+## <!-- Generated by harness generate-slash-commands. Do not edit. -->
+
+name: harness:verification
+description: Comprehensive harness verification of project health and compliance
+argument-hint: "[--path <path>]"
+allowed-tools:
+
+- Bash
+- Read
+- Glob
+
+---
+
+<context>
+Cognitive mode: meticulous-verifier
+Type: rigid
+</context>
+
+<objective>
+Comprehensive harness verification of project health and compliance
+
+Phases:
+
+- check: Run all harness validation commands
+- report: Summarize findings and violations
+- remediate: Fix any critical violations
+  </objective>
+
+<execution_context>
+@agents/skills/claude-code/harness-verification/SKILL.md
+@agents/skills/claude-code/harness-verification/skill.yaml
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "harness-verification"
+2. If MCP unavailable: read SKILL.md and follow its workflow directly
+3. Pass through any arguments provided by the user
+</process>

package/dist/agents/{agents/skills/claude-code/add-harness-component/SKILL.md → commands/gemini-cli/harness/add-component.toml}

@@ -1,3 +1,17 @@
+# Generated by harness generate-slash-commands. Do not edit.
+description = "Add a component to an existing harness project"
+prompt = """
+<context>
+Cognitive mode: constructive-architect
+Type: flexible
+</context>
+
+<objective>
+Add a component to an existing harness project
+</objective>
+
+<execution_context>
+--- SKILL.md (agents/skills/claude-code/add-harness-component/SKILL.md) ---
 # Add Harness Component
 
 > Add layers, documentation, components, or skills to an existing harness project with proper integration. Validate against existing constraints, wire into architecture, and verify the result.
@@ -180,3 +194,47 @@ VERIFY:
   git add harness.yaml AGENTS.md src/services/notification-service.*
   git commit -m "feat: add notification service to business layer"
 ```
+
+
+--- skill.yaml (agents/skills/claude-code/add-harness-component/skill.yaml) ---
+name: add-harness-component
+version: "1.0.0"
+description: Add a component to an existing harness project
+cognitive_mode: constructive-architect
+triggers:
+  - manual
+platforms:
+  - claude-code
+  - gemini-cli
+tools:
+  - Bash
+  - Read
+  - Write
+  - Edit
+  - Glob
+cli:
+  command: harness skill run add-harness-component
+  args:
+    - name: path
+      description: Project root path
+      required: false
+mcp:
+  tool: run_skill
+  input:
+    skill: add-harness-component
+    path: string
+type: flexible
+state:
+  persistent: false
+  files: []
+depends_on:
+  - initialize-harness-project
+
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "add-harness-component"
+2. If MCP unavailable: follow the SKILL.md workflow provided above directly
+3. Pass through any arguments provided by the user
+</process>
+"""

package/dist/agents/{agents/skills/gemini-cli/align-documentation/SKILL.md → commands/gemini-cli/harness/align-documentation.toml}

@@ -1,3 +1,17 @@
+# Generated by harness generate-slash-commands. Do not edit.
+description = "Auto-fix documentation drift issues"
+prompt = """
+<context>
+Cognitive mode: meticulous-verifier
+Type: flexible
+</context>
+
+<objective>
+Auto-fix documentation drift issues
+</objective>
+
+<execution_context>
+--- SKILL.md (agents/skills/claude-code/align-documentation/SKILL.md) ---
 # Align Documentation
 
 > Sync documentation with code after implementation changes. Keep AGENTS.md, API docs, and architecture docs accurate by mapping code changes to their documentation impact.
@@ -179,3 +193,46 @@ src/services/user-service.ts:15 — JSDoc @returns tag → update, add @throws t
 - **When documentation is in an external system (wiki, Confluence):** Document the needed change and flag it for manual update. Include the specific text that needs changing and the correct replacement.
 - **When the code change is so large that documentation needs a rewrite:** Break the documentation update into sections. Update one section at a time, validating after each. Do not attempt a full rewrite in one pass.
 - **When you disagree with the existing documentation style:** Follow the existing style. Documentation alignment is about accuracy, not style improvement. Style changes should be a separate, deliberate effort.
+
+
+--- skill.yaml (agents/skills/claude-code/align-documentation/skill.yaml) ---
+name: align-documentation
+version: "1.0.0"
+description: Auto-fix documentation drift issues
+cognitive_mode: meticulous-verifier
+triggers:
+  - manual
+platforms:
+  - claude-code
+  - gemini-cli
+tools:
+  - Bash
+  - Read
+  - Write
+  - Edit
+cli:
+  command: harness skill run align-documentation
+  args:
+    - name: path
+      description: Project root path
+      required: false
+mcp:
+  tool: run_skill
+  input:
+    skill: align-documentation
+    path: string
+type: flexible
+state:
+  persistent: false
+  files: []
+depends_on:
+  - detect-doc-drift
+
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "align-documentation"
+2. If MCP unavailable: follow the SKILL.md workflow provided above directly
+3. Pass through any arguments provided by the user
+</process>
+"""

package/dist/agents/{skills/gemini-cli/harness-architecture-advisor/SKILL.md → commands/gemini-cli/harness/architecture-advisor.toml}

@@ -1,3 +1,24 @@
+# Generated by harness generate-slash-commands. Do not edit.
+description = "Interactive architecture advisor that surfaces trade-offs and helps humans choose"
+prompt = """
+<context>
+Cognitive mode: advisory-guide
+Type: flexible
+State: persistent (files: .harness/architecture/)
+</context>
+
+<objective>
+Interactive architecture advisor that surfaces trade-offs and helps humans choose
+
+Phases:
+- discover: Ask questions about the problem space and constraints
+- analyze: Research the codebase and identify relevant patterns
+- propose: Present 2-3 architectural options with trade-offs
+- document: Write an Architecture Decision Record for the chosen option
+</objective>
+
+<execution_context>
+--- SKILL.md (agents/skills/claude-code/harness-architecture-advisor/SKILL.md) ---
 # Harness Architecture Advisor
 
 > Cognitive mode: **advisory-guide**. Ask questions, surface trade-offs, present options. Do NOT execute. The human decides; you inform the decision.
@@ -386,3 +407,63 @@ Recommendation: Option A. The plugin registry provides the clear boundary you ne
 
 **Phase 4 — DOCUMENT:**
 ADR written after human selects Option A. Action items: define widget interface contract, extract existing widgets one at a time (one PR per widget), create registry with type-safe registration, add documentation for "how to add a new widget."
+
+
+--- skill.yaml (agents/skills/claude-code/harness-architecture-advisor/skill.yaml) ---
+name: harness-architecture-advisor
+version: "1.0.0"
+description: Interactive architecture advisor that surfaces trade-offs and helps humans choose
+cognitive_mode: advisory-guide
+triggers:
+  - manual
+  - on_new_feature
+platforms:
+  - claude-code
+  - gemini-cli
+tools:
+  - Read
+  - Glob
+  - Grep
+  - Bash
+cli:
+  command: harness skill run harness-architecture-advisor
+  args:
+    - name: path
+      description: Project root path
+      required: false
+    - name: topic
+      description: "Architecture topic (e.g., api-design, data-modeling, decomposition)"
+      required: false
+mcp:
+  tool: run_skill
+  input:
+    skill: harness-architecture-advisor
+    path: string
+type: flexible
+phases:
+  - name: discover
+    description: Ask questions about the problem space and constraints
+    required: true
+  - name: analyze
+    description: Research the codebase and identify relevant patterns
+    required: true
+  - name: propose
+    description: Present 2-3 architectural options with trade-offs
+    required: true
+  - name: document
+    description: Write an Architecture Decision Record for the chosen option
+    required: true
+state:
+  persistent: true
+  files:
+    - .harness/architecture/
+depends_on: []
+
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "harness-architecture-advisor"
+2. If MCP unavailable: follow the SKILL.md workflow provided above directly
+3. Pass through any arguments provided by the user
+</process>
+"""

package/dist/agents/{skills/gemini-cli/harness-brainstorming/SKILL.md → commands/gemini-cli/harness/brainstorming.toml}

@@ -1,3 +1,23 @@
+# Generated by harness generate-slash-commands. Do not edit.
+description = "Structured ideation and exploration with harness methodology"
+prompt = """
+<context>
+Cognitive mode: constructive-architect
+Type: rigid
+</context>
+
+<objective>
+Structured ideation and exploration with harness methodology
+
+Phases:
+- explore: Generate ideas and possibilities
+- evaluate: Assess ideas against constraints
+- prioritize: Select and sequence top ideas
+- validate: Run harness checks on selected approach
+</objective>
+
+<execution_context>
+--- SKILL.md (agents/skills/claude-code/harness-brainstorming/SKILL.md) ---
 # Harness Brainstorming
 
 > Design exploration to spec to plan. No implementation before design approval. Think first, build second.
@@ -245,3 +265,62 @@ These are hard stops. Violating any gate means the process has broken down.
 - **When the problem domain is unfamiliar:** State what you do not know. Ask the human if they have domain expertise, documentation, or a reference implementation. Do not guess at domain-specific requirements.
 - **When requirements conflict with existing architecture:** Flag the conflict explicitly: "The spec calls for X, but the current architecture assumes Y. Should we (A) change the spec to work within current architecture, or (B) plan an architecture change as a prerequisite?"
 - **When you have asked more than 10 questions without converging:** The problem is too large or too ambiguous. Stop and propose a decomposition or a scoping exercise before continuing.
+
+
+--- skill.yaml (agents/skills/claude-code/harness-brainstorming/skill.yaml) ---
+name: harness-brainstorming
+version: "1.0.0"
+description: Structured ideation and exploration with harness methodology
+cognitive_mode: constructive-architect
+triggers:
+  - manual
+  - on_new_feature
+platforms:
+  - claude-code
+  - gemini-cli
+tools:
+  - Bash
+  - Read
+  - Write
+  - Edit
+  - Glob
+  - Grep
+cli:
+  command: harness skill run harness-brainstorming
+  args:
+    - name: path
+      description: Project root path
+      required: false
+mcp:
+  tool: run_skill
+  input:
+    skill: harness-brainstorming
+    path: string
+type: rigid
+phases:
+  - name: explore
+    description: Generate ideas and possibilities
+    required: true
+  - name: evaluate
+    description: Assess ideas against constraints
+    required: true
+  - name: prioritize
+    description: Select and sequence top ideas
+    required: true
+  - name: validate
+    description: Run harness checks on selected approach
+    required: true
+state:
+  persistent: false
+  files: []
+depends_on:
+  - harness-planning
+
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "harness-brainstorming"
+2. If MCP unavailable: follow the SKILL.md workflow provided above directly
+3. Pass through any arguments provided by the user
+</process>
+"""

package/dist/agents/{agents/skills/gemini-cli/check-mechanical-constraints/SKILL.md → commands/gemini-cli/harness/check-mechanical-constraints.toml}

@@ -1,3 +1,17 @@
+# Generated by harness generate-slash-commands. Do not edit.
+description = "Run all mechanical constraint checks (context validation + architecture)"
+prompt = """
+<context>
+Cognitive mode: meticulous-verifier
+Type: rigid
+</context>
+
+<objective>
+Run all mechanical constraint checks (context validation + architecture)
+</objective>
+
+<execution_context>
+--- SKILL.md (agents/skills/claude-code/check-mechanical-constraints/SKILL.md) ---
 # Check Mechanical Constraints
 
 > Run all mechanical constraint checks: linter rules, boundary schemas, and forbidden imports. These are automated, enforceable rules — if it can be checked by a machine, it must be.
@@ -189,3 +203,47 @@ These are hard stops. Mechanical constraints are non-negotiable.
 - **When a violation cannot be fixed without a larger refactor:** Document the violation, create a task for the refactor, and get team approval for a temporary inline suppression with a TODO linking to the task.
 - **When auto-fix produces unexpected changes:** Undo the auto-fix, report the issue, and fix manually. Auto-fix tools are not infallible.
 - **When multiple constraints conflict:** The stricter constraint wins. If `harness validate` says a file is required but `harness linter validate` says its contents violate a rule, fix the contents to satisfy both. Escalate if truly irreconcilable.
+
+
+--- skill.yaml (agents/skills/claude-code/check-mechanical-constraints/skill.yaml) ---
+name: check-mechanical-constraints
+version: "1.0.0"
+description: Run all mechanical constraint checks (context validation + architecture)
+cognitive_mode: meticulous-verifier
+triggers:
+  - manual
+  - on_pr
+platforms:
+  - claude-code
+  - gemini-cli
+tools:
+  - Bash
+  - Read
+  - Glob
+cli:
+  command: harness skill run check-mechanical-constraints
+  args:
+    - name: path
+      description: Project root path
+      required: false
+mcp:
+  tool: run_skill
+  input:
+    skill: check-mechanical-constraints
+    path: string
+type: rigid
+state:
+  persistent: false
+  files: []
+depends_on:
+  - validate-context-engineering
+  - enforce-architecture
+
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "check-mechanical-constraints"
+2. If MCP unavailable: follow the SKILL.md workflow provided above directly
+3. Pass through any arguments provided by the user
+</process>
+"""

package/dist/agents/{skills/gemini-cli/cleanup-dead-code/SKILL.md → commands/gemini-cli/harness/cleanup-dead-code.toml}

@@ -1,3 +1,17 @@
+# Generated by harness generate-slash-commands. Do not edit.
+description = "Detect unused exports and dead code"
+prompt = """
+<context>
+Cognitive mode: diagnostic-investigator
+Type: flexible
+</context>
+
+<objective>
+Detect unused exports and dead code
+</objective>
+
+<execution_context>
+--- SKILL.md (agents/skills/claude-code/cleanup-dead-code/SKILL.md) ---
 # Cleanup Dead Code
 
 > Entropy analysis and safe cleanup. Find unused exports, dead files, and pattern violations — then remove them without breaking anything.
@@ -200,3 +214,45 @@ ORPHANED DEPENDENCY: moment (package.json)
 - **When the entropy report is very large (>50 items):** Do not attempt to clean everything at once. Pick the highest-confidence dead code (files with zero imports, no dynamic patterns) and clean those first. Schedule the rest across multiple sessions.
 - **When you are unsure if an export is used externally:** Check if the code is in a published package. If so, removing an export is a breaking change. Deprecate first, then remove in a major version.
 - **When dead code is tangled with live code in the same file:** Extract the live code first (using harness-refactoring), then delete the remaining dead code. Do not try to surgically remove dead code from a complex file in one step.
+
+
+--- skill.yaml (agents/skills/claude-code/cleanup-dead-code/skill.yaml) ---
+name: cleanup-dead-code
+version: "1.0.0"
+description: Detect unused exports and dead code
+cognitive_mode: diagnostic-investigator
+triggers:
+  - manual
+platforms:
+  - claude-code
+  - gemini-cli
+tools:
+  - Bash
+  - Read
+  - Glob
+  - Grep
+cli:
+  command: harness skill run cleanup-dead-code
+  args:
+    - name: path
+      description: Project root path
+      required: false
+mcp:
+  tool: run_skill
+  input:
+    skill: cleanup-dead-code
+    path: string
+type: flexible
+state:
+  persistent: false
+  files: []
+depends_on: []
+
+</execution_context>
+
+<process>
+1. Try: invoke mcp__harness__run_skill with skill: "cleanup-dead-code"
+2. If MCP unavailable: follow the SKILL.md workflow provided above directly
+3. Pass through any arguments provided by the user
+</process>
+"""