@namch/agent-assistant 1.0.2 → 1.0.3

package/commands/report/hard.md

@@ -0,0 +1,112 @@
+---
+description: ⚡ Detailed Report — Comprehensive project analysis and documentation
+version: "1.0"
+category: documentation
+execution-mode: execute
+---
+
+# /report:hard — Comprehensive Project Report
+
+> **MISSION**: Generate detailed output for **any topic** — reports, doc updates, or template-based files.
+>
+> Use for: sprint reviews, technical docs, any-topic reports, updating existing files, or generating from user format/template.
+
+<task>$ARGUMENTS</task>
+
+---
+
+## 🛑 PRE-FLIGHT (DO FIRST — BLOCKS PHASE 1)
+
+**LOAD now** (in order; path `./rules/` or `~/.{TOOL}/skills/agent-assistant/rules/`):
+
+1. ORCHESTRATION-LAWS.md
+2. ADAPTIVE-EXECUTION.md
+3. EXECUTION-PROTOCOL.md
+
+**⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
+
+---
+
+## 🔀 TIERED EXECUTION
+
+| Tier       | When               | Action                       |
+| ---------- | ------------------ | ---------------------------- |
+| **TIER 1** | runSubagent EXISTS | Invoke sub-agent (MANDATORY) |
+| **TIER 2** | Tool MISSING       | EMBODY agent file (FALLBACK) |
+
+**❌ Anti-Lazy**: Never use TIER 2 when TIER 1 tool available.
+
+---
+
+## 📁 DELIVERABLES (Reporter chooses from user intent)
+
+| User intent | Reporter output |
+| ----------- | ---------------- |
+| **Create report** | New file: `./reports/general/REPORT-{type}-{date}.md` (or path user asks) |
+| **Update existing** | **Edit** related files (docs, README, etc.); do **not** create new report unless also asked |
+| **From template** | New file(s) matching user format/template (e.g. after scouting source) |
+
+| Agent      | Output (when creating)                          |
+| ---------- | ------------------------------------------------ |
+| researcher | `./reports/researchers/RESEARCH-{task}.md` (optional) |
+| scouter    | `./reports/scouts/SCOUT-{task}.md` (optional)    |
+| reporter   | Per table above — create report **or** update existing **or** generate from template |
+
+All files in `./reports/` → English only.
+
+---
+
+## ⛔ INCREMENTAL EXECUTION (MANDATORY)
+
+One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in one reply. No batching (load only what each phase needs). **Within each phase:** when doing a part, output it in format so user sees what's happening (announce before doing). Format: rules/EXECUTION-PROTOCOL.md § Phase output structure.
+
+---
+
+## 🎭 Phase 1: RESEARCH
+
+| Agent  | `researcher`                                                |
+| ------ | ---------------------------------------------------------- |
+| Goal   | Research report scope, audience, and best practices for project/technical reports |
+| Output | `./reports/researchers/RESEARCH-{task}.md` (optional)       |
+| Exit   | Report scope and criteria defined, templates identified   |
+
+---
+
+## 🎭 Phase 2: DEEP SCAN
+
+| Agent  | `scouter`                         |
+| ------ | --------------------------------- |
+| Goal   | Full codebase structural analysis |
+| Output | `./reports/scouts/SCOUT-{task}.md` |
+| Exit   | Architecture and recent changes documented                 |
+
+---
+
+## 🎭 Phase 3: DATA SYNTHESIS
+
+| Agent       | `reporter`                                      |
+| ----------- | ------------------------------------------------ |
+| Prerequisite| **READ** RESEARCH + SCOUT outputs if present     |
+| Goal        | Aggregate data from Scouter, Plans, and History; identify discrepancies and milestones |
+| Exit        | Data synthesized, gaps and milestones identified |
+
+---
+
+## 🎭 Phase 4: OUTPUT (create / update / from template)
+
+| Agent | `reporter`                                                                 |
+| ----- | --------------------------------------------------------------------------- |
+| Goal  | From **user intent**: (1) create new report, (2) **update** existing files, or (3) generate from template/format |
+| Output| **Create**: `./reports/general/REPORT-{type}-{date}.md` or path user asked. **Update**: edit related files. **Template**: file(s) matching user format. |
+| Exit  | Deliverable matches intent — report file, updated docs, or template-based file(s). |
+
+---
+
+## COMPLETION
+
+Deliverable per **user intent**:
+
+1. ✅ **Create report** → `./reports/general/REPORT-{type}-{date}.md` (or path user asked)
+2. ✅ **Update existing** → Related files edited; list what was updated
+3. ✅ **From template** → File(s) matching user format; list path(s)
+4. 📢 **Share** → `/internal-comms` (optional)

package/commands/report.md

@@ -0,0 +1,89 @@
+---
+description: 📝 Report Router — Multi-purpose reporting (create report, update docs, or generate from template)
+version: "1.0"
+category: documentation
+execution-mode: router
+---
+
+# /report — Reporting Router
+
+> **ROUTER DIRECTIVE**: Analyze reporting needs and route to appropriate reporting workflow.
+>
+> **MULTI-PURPOSE**: Report supports any topic and three output modes — create new report, update existing files, or generate from user template/format.
+
+<task>$ARGUMENTS</task>
+
+---
+
+## 🛑 PRE-FLIGHT (DO FIRST — BLOCKS EXECUTION)
+
+**LOAD now** (in order; path `./rules/` or `~/.{TOOL}/skills/agent-assistant/rules/`):
+
+1. ORCHESTRATION-LAWS.md
+2. ADAPTIVE-EXECUTION.md
+3. EXECUTION-PROTOCOL.md
+
+**⛔ Do not run any workflow phase until all are loaded.** Follow **all** rules in those files. Then run this file's ROUTING LOGIC, LOAD the chosen variant workflow, and execute it.
+
+---
+
+## OUTPUT MODES (infer from user request)
+
+Reporter **infers** the mode from what the user asks for — no fixed phrase list. Choose by **intent**:
+
+| Mode | User intent | Reporter action |
+|------|-------------|-----------------|
+| **Create report** | User wants a **new** deliverable (report, summary, analysis, documentation). | Scout/synthesize → write **new** file under `./reports/` or path user specifies. |
+| **Update existing** | User wants **changes reflected in existing** files (docs, README, specs, etc.). | Scout → identify related files → **edit** those files. Do not create a new report unless also asked. |
+| **From template** | User provides a **format, template, or structure** to follow. | Use that format/structure → generate file(s) matching it (e.g. after scouting source). |
+
+**Topic-agnostic**: Subject is whatever the user asks for — infer from the request; not limited to status or technical only.
+
+---
+
+## ROUTING LOGIC
+
+```
+IF task is simple status update OR summary:
+  → Route to /report:fast
+
+IF task is comprehensive analysis OR deep dive OR any non-trivial topic (infer from request):
+  → Route to /report:hard
+
+IF task requires absolute context clarity OR "clean slate" analysis:
+  → Route to /report:focus
+
+IF user explicitly asks to UPDATE existing files (not create report):
+  → Still use /report:hard or /report:focus; reporter OUTPUT MODE = update existing files
+
+IF unsure:
+  → Default to /report:fast (escalate if needed)
+```
+
+---
+
+## AVAILABLE ROUTES
+
+| Route           | When to Use                                                                 |
+| --------------- | --------------------------------------------------------------------------- |
+| `/report:fast`  | Quick status updates, daily summaries                                       |
+| `/report:hard`  | Detailed analysis, any topic (algorithms, docs, changes), template-based  |
+| `/report:focus` | Deep analysis with **enforced context optimization**; update or create      |
+
+---
+
+## PRESENT OPTIONS
+
+```markdown
+## 📝 Reporting Mode Selection
+
+**Task**: [parsed task]
+
+**Choose workflow:**
+
+1. ⚡ **Fast** → `/report:fast` — Quick summary
+2. ⚡⚡⚡ **Hard** → `/report:hard` — Full analysis, any topic; create report **or** update existing files / use template
+3. 🎯 **Focus** → `/report:focus` — Deep analysis with **automatic context clearing**; create or update per task
+
+⏳ Awaiting selection...
+```

package/commands/test/focus.md

@@ -0,0 +1,165 @@
+---
+description: 🔒 Focused Test — Comprehensive QA with enforced context optimization
+version: "1.0"
+category: validation
+execution-mode: execute
+---
+
+# /test:focus — Focus Comprehensive Testing
+
+> **MISSION**: Full QA workflow with **enforced context optimization**.
+> 
+> This variant automatically clears context before test execution—no user prompt required.
+> Use when you want guaranteed focused test execution without strategy noise.
+
+<scope>$ARGUMENTS</scope>
+
+---
+
+## 🛑 PRE-FLIGHT (DO FIRST — BLOCKS PHASE 1)
+
+**LOAD now** (in order; path `./rules/` or `~/.{TOOL}/skills/agent-assistant/rules/`):
+
+1. ORCHESTRATION-LAWS.md
+2. ADAPTIVE-EXECUTION.md
+3. EXECUTION-PROTOCOL.md
+
+**⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
+
+---
+
+## 🔀 TIERED EXECUTION
+
+| Tier       | When               | Action                       |
+| ---------- | ------------------ | ---------------------------- |
+| **TIER 1** | runSubagent EXISTS | Invoke sub-agent (MANDATORY) |
+| **TIER 2** | Tool MISSING       | EMBODY agent file (FALLBACK) |
+
+---
+
+## 📁 PLAN CHECKPOINT VERIFICATION
+
+```
+IF ./reports/plans/PLAN-{scope}.md exists:
+  1. READ plan completely
+  2. EXTRACT all checkpoints
+  3. FOR EACH checkpoint → Create test
+  4. OUTPUT: "Checkpoint Coverage: X/Y"
+```
+
+---
+
+## ⛔ INCREMENTAL EXECUTION (MANDATORY)
+
+One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in one reply. No batching (load only what each phase needs). **Within each phase:** when doing a part, output it in format so user sees what's happening (announce before doing).
+
+---
+
+## 🎭 Phase 1: TEST STRATEGY
+
+| Agent | `tester`                                |
+| ----- | --------------------------------------- |
+| Goal  | Design test strategy                    |
+| Exit  | Strategy defined, test types identified |
+
+---
+
+## 🛡️ STRICT CONTEXT GATE — Automatic Context Optimization
+
+> **⚡ FOCUS MODE**: This checkpoint executes automatically. NO user input required.
+> 
+> **PURPOSE**: Prevent "context rot" by forcibly clearing strategy discussion noise.
+> This acts as a mandatory "firewall" before test execution phases.
+
+### 🔒 AUTOMATIC EXECUTION (NO PROMPT)
+
+```yaml
+strict_context_gate:
+  mode: "AUTOMATIC - No user interaction"
+  behavior: "Force Clear context & Execute"
+  
+  execution:
+    1. ANNOUNCE: |
+       ## 🛡️ Strict Context Gate — Automatic
+       
+       ✅ **Test Strategy Complete**: Strategy defined, test types identified.
+       🔒 **Focus Mode**: Automatically clearing context for test execution.
+       
+       ⚡ Executing: **Clear context & Execute**...
+    
+    2. CONTEXT_DIRECTIVE: |
+       ╔══════════════════════════════════════════════════════════════════╗
+       ║  ⛔ MANDATORY CONTEXT RESET — FOCUS MODE                         ║
+       ╠══════════════════════════════════════════════════════════════════╣
+       ║  IGNORE: All strategy discussions, rejected approaches,          ║
+       ║          and intermediate test planning reasoning.               ║
+       ║                                                                  ║
+       ║  SOLE SOURCE OF TRUTH: Finalized test strategy.                  ║
+       ║                                                                  ║
+       ║  PROCEED: Execute test phases with FRESH context mindset.        ║
+       ║           Focus purely on test execution and verification.       ║
+       ╚══════════════════════════════════════════════════════════════════╝
+    
+    3. LOAD: Finalized test strategy as if seeing it for the first time
+    
+    4. PROCEED: Start Phase 2 (Dependency Mapping) immediately
+```
+
+### 📋 Post-Gate Status
+
+```markdown
+🔒 **Context Gate Passed**
+- Previous context: DISCARDED
+- Active context: Test strategy only
+- Mode: Fresh execution start
+
+Proceeding to Test Execution...
+```
+
+---
+
+## 🎭 Phase 2: DEPENDENCY MAPPING
+
+| Agent | `scouter`                              |
+| ----- | -------------------------------------- |
+| Goal  | Map test dependencies                  |
+| Exit  | Dependencies mapped, environment ready |
+
+---
+
+## 🎭 Phase 3: TEST EXECUTION
+
+| Agent        | `tester`                                                        |
+| ------------ | --------------------------------------------------------------- |
+| Prerequisite | READ PLAN file if exists                                        |
+| Goal         | Run full test suite                                             |
+| Exit         | All tests run, coverage measured, checkpoint mapping documented |
+
+---
+
+## 🎭 Phase 4: FAILURE ANALYSIS (IF FAILURES)
+
+| Agent   | `debugger`             |
+| ------- | ---------------------- |
+| Trigger | If failures exist      |
+| Goal    | Analyze failures       |
+| Exit    | Root causes identified |
+
+---
+
+## 🎭 Phase 5: QUALITY GATES
+
+| Agent | `tester`                          |
+| ----- | --------------------------------- |
+| Goal  | Verify quality gates              |
+| Exit  | All gates pass, coverage adequate |
+
+---
+
+## COMPLETION
+
+Present test report with:
+
+1. ✅ **Pass** — All tests green (Focus Mode)
+2. 🔧 **Fix** → `/fix:fast`
+3. 📝 **Review** → `/review`

package/commands/test/hard.md

@@ -61,6 +61,59 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 
 ---
 
+## 🛡️ VERIFICATION CHECKPOINT — Context Optimization
+
+> **PURPOSE**: Prevent "context rot" by clearing strategy discussion before test execution.
+> 
+> Test strategy discussions may include rejected approaches that can confuse execution.
+> This checkpoint ensures clean handoff to test execution phases.
+
+### ⚡ OPTIONS (Present to User)
+
+```markdown
+## 🛡️ Context Optimization Checkpoint
+
+**Test Strategy Complete** — Strategy defined, ready for execution.
+
+**Choose how to proceed:**
+
+| Option | Action | Description |
+|--------|--------|-------------|
+| **1. 🚀 Clear context & Execute** | `RECOMMENDED` | Fresh start: Focus on strategy, ignore discussion history |
+| **2. ⏸️ Review Strategy** | `SAFE` | Clear context, show strategy summary, wait for approval |
+| **3. ⚠️ Continue (No Clear)** | `RISKY` | Keep full history (may affect test focus) |
+
+⏳ Awaiting selection...
+```
+
+### 🔄 EXECUTION BEHAVIOR
+
+```yaml
+option_1_clear_execute:
+  behavior: "RECOMMENDED - Clean execution"
+  steps:
+    1. ACKNOWLEDGE: "🚀 Context optimized. Executing test strategy."
+    2. CONTEXT_DIRECTIVE: |
+       ⛔ IGNORE strategy discussion and rejected approaches.
+       ✅ FINALIZED STRATEGY is SOLE SOURCE OF TRUTH.
+    3. PROCEED: Continue to test execution phases
+
+option_2_review_strategy:
+  behavior: "Clear and show summary"
+  steps:
+    1. ACKNOWLEDGE: "⏸️ Context cleared."
+    2. OUTPUT: Display strategy summary
+    3. WAIT: For user approval
+
+option_3_continue_no_clear:
+  behavior: "Proceed with caution"
+  steps:
+    1. WARN: "⚠️ Discussion history retained."
+    2. PROCEED: Continue with existing context
+```
+
+---
+
 ## 🎭 Phase 2: DEPENDENCY MAPPING
 
 | Agent | `scouter`                              |

package/commands/test.md

@@ -33,6 +33,9 @@ IF scope is limited (unit tests, quick check):
 IF scope is comprehensive (full suite, E2E):
   → Route to /test:hard
 
+IF scope is comprehensive AND clean execution focus is critical:
+  → Route to /test:focus
+
 IF unsure:
   → Default to /test:fast
 ```
@@ -41,10 +44,11 @@ IF unsure:
 
 ## AVAILABLE ROUTES
 
-| Route        | When to Use             |
-| ------------ | ----------------------- |
-| `/test:fast` | Quick tests, unit tests |
-| `/test:hard` | Full test suite, E2E    |
+| Route          | When to Use                                        |
+| -------------- | -------------------------------------------------- |
+| `/test:fast`   | Quick tests, unit tests                            |
+| `/test:hard`   | Full test suite, E2E                               |
+| `/test:focus` | Full testing with **enforced context optimization** |
 
 ---
 
@@ -59,6 +63,7 @@ IF unsure:
 
 1. ⚡ **Fast** → `/test:fast` — Quick tests
 2. ⚡⚡⚡ **Hard** → `/test:hard` — Comprehensive testing
+3. 🔒 **Focus** → `/test:focus` — Comprehensive testing with **automatic context clearing** (focused execution)
 
 ⏳ Awaiting selection...
 ```

package/documents/business/business-features.md

@@ -14,7 +14,7 @@ Agent Assistant provides a comprehensive feature set organized into six categori
 | Category | Feature Count | Description |
 |----------|---------------|-------------|
 | Specialist Agents | 20 | Domain expert personas |
-| Command Workflows | 40+ | Development workflow automations |
+| Command Workflows | 50+ | Development workflow automations (incl. /report, focus variant) |
 | Domain Skills | 310+ | On-demand knowledge modules |
 | Quality Gates | 5 | Automated verification checkpoints |
 | Orchestration Rules | 8 | Governance and coordination protocols |

package/documents/business/business-glossary.md

@@ -40,7 +40,7 @@ A **slash-prefixed workflow trigger** that initiates a structured development pr
 | With variant | `/cook:hard` |
 | With argument | `/cook:hard "implement OAuth"` |
 
-**Available Commands**: `/cook`, `/fix`, `/plan`, `/test`, `/review`, `/debug`, `/design`, `/docs`, `/deploy`, `/ask`, `/auto`, `/brainstorm`, `/code`
+**Available Commands**: `/cook`, `/fix`, `/plan`, `/test`, `/review`, `/debug`, `/design`, `/docs`, `/report`, `/deploy`, `/ask`, `/auto`, `/brainstorm`, `/code`
 
 ---
 
@@ -477,16 +477,17 @@ A **document specifying** what a product should do, including features, requirem
 
 | Command | Purpose | Variants |
 |---------|---------|----------|
-| `/cook` | Implement features | `:fast`, `:hard` |
-| `/code` | Generate code snippets | `:fast`, `:hard` |
-| `/fix` | Fix bugs | `:fast`, `:hard` |
-| `/test` | Generate tests | `:fast`, `:hard` |
+| `/cook` | Implement features | `:fast`, `:hard`, `:focus` |
+| `/code` | Generate code snippets | `:fast`, `:hard`, `:focus` |
+| `/fix` | Fix bugs | `:fast`, `:hard`, `:focus` |
+| `/test` | Generate tests | `:fast`, `:hard`, `:focus` |
 | `/review` | Code review | `:fast`, `:hard` |
-| `/debug` | Debug issues | `:fast`, `:hard` |
-| `/plan` | Create implementation plans | `:fast`, `:hard` |
+| `/debug` | Debug issues | `:fast`, `:hard`, `:focus` |
+| `/plan` | Create implementation plans | `:fast`, `:hard`, `:focus` |
 | `/brainstorm` | Discover requirements | `:fast`, `:hard` |
-| `/design` | UI/UX design | `:fast`, `:hard` |
+| `/design` | UI/UX design | `:fast`, `:hard`, `:focus` |
 | `/docs` | Generate documentation | `:core`, `:business`, `:audit` |
+| `/report` | Create/update reports, summaries | `:fast`, `:hard`, `:focus` |
 | `/deploy` | Deployment operations | `:check`, `:preview`, `:production`, `:rollback` |
 | `/ask` | Q&A about codebase | `:fast`, `:hard` |
 | `/auto` | Auto-detect best command | — |

package/documents/business/business-prd.md

@@ -11,7 +11,7 @@
 
 ### 1.1 Product Overview
 
-**Agent Assistant** is an open-source multi-agent orchestration framework that transforms a single AI coding assistant into a coordinated team of 20 specialist agents. It provides structured workflows, quality gates, and 310+ domain skills for production-grade AI-assisted software development.
+**Agent Assistant** is an open-source multi-agent orchestration framework that transforms a single AI coding assistant into a coordinated team of 21 specialist agents. It provides structured workflows, quality gates, and 310+ domain skills for production-grade AI-assisted software development.
 
 ### 1.2 Vision Statement
 
@@ -19,7 +19,7 @@
 
 ### 1.3 Mission Statement
 
-> **"To democratize software engineering excellence by orchestrating AI coding assistants into a cohesive team of 20 specialist agents, enabling developers to ship faster, safer, and more consistently through repeatable workflows and automated quality verification."**
+> **"To democratize software engineering excellence by orchestrating AI coding assistants into a cohesive team of 21 specialist agents, enabling developers to ship faster, safer, and more consistently through repeatable workflows and automated quality verification."**
 
 ### 1.4 Key Metrics
 
@@ -135,7 +135,7 @@ AI coding assistants are powerful but unstructured. Developers use AI tools in a
 
 | ID | Requirement | Priority | Status |
 |----|-------------|----------|--------|
-| FR-001.1 | System SHALL support 20 specialist agents | Must-Have | ✅ Complete |
+| FR-001.1 | System SHALL support 21 specialist agents | Must-Have | ✅ Complete |
 | FR-001.2 | System SHALL route tasks to appropriate agents | Must-Have | ✅ Complete |
 | FR-001.3 | System SHALL support tiered execution (sub-agent + embody) | Must-Have | ✅ Complete |
 | FR-001.4 | System SHALL enforce orchestration laws | Must-Have | ✅ Complete |
@@ -145,7 +145,7 @@ AI coding assistants are powerful but unstructured. Developers use AI tools in a
 
 | ID | Requirement | Priority | Status |
 |----|-------------|----------|--------|
-| FR-002.1 | System SHALL support 40+ command workflows | Must-Have | ✅ Complete |
+| FR-002.1 | System SHALL support 50+ command workflows | Must-Have | ✅ Complete |
 | FR-002.2 | System SHALL support workflow variants (:fast, :hard) | Must-Have | ✅ Complete |
 | FR-002.3 | System SHALL execute phases sequentially | Must-Have | ✅ Complete |
 | FR-002.4 | System SHALL verify exit criteria before phase transition | Must-Have | ✅ Complete |
@@ -284,8 +284,8 @@ AI coding assistants are powerful but unstructured. Developers use AI tools in a
 
 | Feature | Description | Status |
 |---------|-------------|--------|
-| 20 Specialist Agents | Domain experts | ✅ Complete |
-| Core Command Workflows | /cook, /fix, /plan, etc. | ✅ Complete |
+| 21 Specialist Agents | Domain experts | ✅ Complete |
+| Core Command Workflows | /cook, /fix, /plan, /report, etc. | ✅ Complete |
 | Quality Gates | 5 automated gates | ✅ Complete |
 | Matrix Skill Discovery | 310+ skills | ✅ Complete |
 | Multi-Tool Support | 4 AI tools | ✅ Complete |
@@ -324,8 +324,8 @@ AI coding assistants are powerful but unstructured. Developers use AI tools in a
 
 | Feature | Status |
 |---------|--------|
-| 20 Specialist Agents | ✅ |
-| 40+ Command Workflows | ✅ |
+| 21 Specialist Agents | ✅ |
+| 50+ Command Workflows | ✅ |
 | 310+ Domain Skills | ✅ |
 | Matrix Skill Discovery | ✅ |
 | Multi-Tool Support | ✅ |

package/documents/knowledge-architecture.md

@@ -41,7 +41,7 @@ Agent Assistant is a **multi-agent orchestration framework** that transforms a s
                     └─────────────────┬─────────────────┘
                                       ▼
 ┌─────────────────────────────────────────────────────────────────────────────┐
-│                         SPECIALIST AGENTS (20)                               │
+│                         SPECIALIST AGENTS (21)                               │
 │  ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐           │
 │  │ tech-lead   │ │ backend-    │ │ frontend-   │ │ security-   │ ...       │
 │  │             │ │ engineer    │ │ engineer    │ │ engineer    │           │

package/documents/knowledge-domain.md

@@ -11,7 +11,7 @@ Agent Assistant operates in the domain of **AI-assisted software development orc
 ```
 ┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
 │     AGENTS      │────▶│    COMMANDS     │────▶│     SKILLS      │
-│  (20 entities)  │     │  (40+ entities) │     │ (310+ entities)  │
+│  (21 entities)  │     │  (50+ entities) │     │ (310+ entities)  │
 └─────────────────┘     └─────────────────┘     └─────────────────┘
          │                      │                       │
          ▼                      ▼                       ▼
@@ -123,13 +123,14 @@ execution-mode: string          # "execute" | "router"
 
 | Command | Description | Variants | Category |
 |---------|-------------|----------|----------|
-| `/cook` | Implement features | `:fast`, `:hard` | development |
+| `/cook` | Implement features | `:fast`, `:hard`, `:focus` | development |
 | `/code` | Write code snippets | `:fast`, `:hard` | development |
-| `/fix` | Fix bugs and refactor | `:fast`, `:hard` | development |
+| `/fix` | Fix bugs and refactor | `:fast`, `:hard`, `:focus` | development |
 | `/test` | Generate tests | `:fast`, `:hard` | quality |
 | `/review` | Code review | `:fast`, `:hard` | quality |
 | `/debug` | Systematic debugging | `:fast`, `:hard` | quality |
-| `/plan` | Implementation planning | `:fast`, `:hard` | planning |
+| `/plan` | Implementation planning | `:fast`, `:hard`, `:focus` | planning |
+| `/report` | Create/update reports, summaries | `:fast`, `:hard`, `:focus` | documentation |
 | `/brainstorm` | Requirements discovery | `:fast`, `:hard` | planning |
 | `/design` | UI/UX design | `:fast`, `:hard` | planning |
 | `/docs` | Documentation | `:core`, `:business`, `:audit` | documentation |

package/documents/knowledge-overview.md

@@ -19,7 +19,7 @@
 
 ## 2. Purpose and Mission
 
-Agent Assistant transforms a single AI coding assistant into a **coordinated team of 20 specialist agents** with structured workflows, quality gates, and 310+ domain skills.
+Agent Assistant transforms a single AI coding assistant into a **coordinated team of 21 specialist agents** with structured workflows, quality gates, and 310+ domain skills.
 
 ### Core Value Proposition
 
@@ -35,7 +35,7 @@ With Agent Assistant:
 
 | Benefit            | Description                                           |
 | ------------------ | ----------------------------------------------------- |
-| **Specialization** | 20 domain expert agents instead of one generalist     |
+| **Specialization** | 21 domain expert agents instead of one generalist     |
 | **Consistency**    | Shared rules, skills, and conventions across all work |
 | **Quality**        | Built-in test, review, and security workflows         |
 | **Efficiency**     | 85% token cost reduction through targeted expertise   |
@@ -47,8 +47,8 @@ With Agent Assistant:
 
 | Metric            | Count | Description                                                |
 | ----------------- | ----- | ---------------------------------------------------------- |
-| Specialist Agents | 20    | Domain experts (backend, frontend, security, tester, etc.) |
-| Command Workflows | 40+   | Development workflows (/cook, /fix, /plan, /deploy, etc.)  |
+| Specialist Agents | 21    | Domain experts (backend, frontend, security, tester, reporter, etc.) |
+| Command Workflows | 50+   | Development workflows (/cook, /fix, /plan, /report, /deploy, etc.; variants: fast, hard, focus) |
 | Domain Skills     | 310   | On-demand knowledge (React, APIs, databases, DevOps, AI/ML, Security, etc.) |
 | Matrix Domains    | 19    | Skill categories (backend, frontend, security, ai-ml, etc.)       |
 | Quality Gates     | 5     | Compile, lint, test, security, review                      |
@@ -200,7 +200,7 @@ Then try development commands:
 
 ## 7. Key Features
 
-### 7.1 20 Specialist Agents
+### 7.1 21 Specialist Agents
 
 | Category           | Agents                                                              |
 | ------------------ | ------------------------------------------------------------------- |
@@ -214,7 +214,7 @@ Then try development commands:
 | **Design**         | designer                                                            |
 | **Management**     | project-manager                                                     |
 
-### 7.2 40+ Command Workflows
+### 7.2 50+ Command Workflows
 
 | Category          | Commands                                                                     |
 | ----------------- | ---------------------------------------------------------------------------- |
@@ -222,6 +222,7 @@ Then try development commands:
 | **Quality**       | `/test`, `/review`, `/debug`                                                 |
 | **Planning**      | `/plan`, `/brainstorm`, `/design`                                            |
 | **Documentation** | `/docs:core`, `/docs:business`, `/docs:audit`                                |
+| **Report**        | `/report:fast`, `/report:hard`, `/report:focus`                               |
 | **Deployment**    | `/deploy:check`, `/deploy:preview`, `/deploy:production`, `/deploy:rollback` |
 | **Utility**       | `/ask`, `/auto`                                                              |