@namch/agent-assistant 1.3.0 → 1.3.1

package/commands/docs.md

@@ -1,13 +1,13 @@
 ---
-description: 📝 Docs — Full Documentation Suite (executes ALL sub-commands sequentially)
-version: "1.0"
+description: "📝 Docs - Full Documentation Suite (executes ALL sub-commands sequentially)"
+version: "2.0"
 category: documentation
 execution-mode: execute
 ---
 
 # /docs — Full Documentation Suite
 
-> **MISSION**: Execute ALL documentation sub-commands **SEQUENTIALLY**. Only report "Done" when ALL 13 files are created.
+> **MISSION**: Execute ALL documentation sub-commands **SEQUENTIALLY**. Only report "Done" when ALL deliverables are created: 5 knowledge folders (26+ files) + 4 business folders (22+ files) + 4 audit folders (20+ files).
 
 <scope>$ARGUMENTS</scope>
 
@@ -31,9 +31,9 @@ execution-mode: execute
 >
 > 1. You MUST execute each sub-command **IN ORDER**
 > 2. You MUST wait for each sub-command to **COMPLETE** before starting next
-> 3. You MUST create **ALL 13 FILES** across 3 sub-commands
+> 3. You MUST create ALL deliverables across 3 sub-commands
 > 4. You may **NOT** skip any sub-command
-> 5. Report "Done" **ONLY** when all 13 files exist
+> 5. Report "Done" **ONLY** when all deliverables exist
 
 ---
 
@@ -42,16 +42,17 @@ execution-mode: execute
 ```
 ┌─────────────────────────────────────────────────────────────────┐
 │ STEP 1: Load & Execute /docs:core                               │
-│   → Wait until ALL 5 core files are created                     │
-│   → Verify: knowledge-overview, architecture, domain,       │
-│   →         source-base, standards                            │
+│   → Wait until ALL 5 knowledge folders are created              │
+│   → Each folder: 00-index.md + numbered sub-files               │
+│   → Verify: knowledge-overview/, architecture/, domain/,        │
+│   →         source-base/, standards/                            │
 ├─────────────────────────────────────────────────────────────────┤
 │ STEP 2: Load & Execute /docs:business                           │
-│   → Wait until ALL 4 business files are created                 │
-│   → Verify: business-prd, features, workflows, glossary         │
+│   → Wait until ALL 4 business folders are created               │
+│   → Verify: business-prd/, features/, workflows/, glossary/     │
 ├─────────────────────────────────────────────────────────────────┤
 │ STEP 3: Load & Execute /docs:audit                              │
-│   → Wait until ALL 4 audit files are created                    │
+│   → Wait until ALL 4 audit folders are created                   │
 │   → Verify: audit-security, compliance, dataflow,               │
 │             recommendations                                     │
 └─────────────────────────────────────────────────────────────────┘
@@ -66,15 +67,15 @@ execution-mode: execute
 | **Sub-Command** | `~/.{TOOL}/agent-assistant/commands/docs/core.md` |
 | **Action**      | **LOAD AND FOLLOW** the entire core.md workflow   |
 
-### Files to be Created:
+### Folders to be Created (v3.0 — folder-based):
 
-- [ ] `./documents/knowledge-overview.md`
-- [ ] `./documents/knowledge-architecture.md`
-- [ ] `./documents/knowledge-domain.md`
-- [ ] `./documents/knowledge-source-base.md`
-- [ ] `./documents/knowledge-standards.md`
+- [ ] `./documents/knowledge-overview/` (00-index.md + 4 sub-files)
+- [ ] `./documents/knowledge-architecture/` (00-index.md + 5 sub-files)
+- [ ] `./documents/knowledge-domain/` (00-index.md + 4 sub-files)
+- [ ] `./documents/knowledge-source-base/` (00-index.md + 4 sub-files)
+- [ ] `./documents/knowledge-standards/` (00-index.md + 4 sub-files)
 
-**⏸️ PAUSE HERE** — Do NOT proceed to Step 2 until all 5 core files exist.
+**⏸️ PAUSE HERE** — Do NOT proceed to Step 2 until all 5 knowledge folders with sub-files exist.
 
 ---
 
@@ -85,14 +86,14 @@ execution-mode: execute
 | **Sub-Command** | `~/.{TOOL}/agent-assistant/commands/docs/business.md` |
 | **Action**      | **LOAD AND FOLLOW** the entire business.md workflow   |
 
-### Files to be Created:
+### Folders to be Created (v4.0 — folder-based):
 
-- [ ] `./documents/business/business-prd.md`
-- [ ] `./documents/business/business-features.md`
-- [ ] `./documents/business/business-workflows.md`
-- [ ] `./documents/business/business-glossary.md`
+- [ ] `./documents/business/business-prd/` (00-index.md + 4 sub-files)
+- [ ] `./documents/business/business-features/` (00-index.md + 5 sub-files)
+- [ ] `./documents/business/business-workflows/` (00-index.md + 5 sub-files)
+- [ ] `./documents/business/business-glossary/` (00-index.md + 4 sub-files)
 
-**⏸️ PAUSE HERE** — Do NOT proceed to Step 3 until all 4 business files exist.
+**⏸️ PAUSE HERE** — Do NOT proceed to Step 3 until all 4 business folders with sub-files exist.
 
 ---
 
@@ -103,57 +104,57 @@ execution-mode: execute
 | **Sub-Command** | `~/.{TOOL}/agent-assistant/commands/docs/audit.md` |
 | **Action**      | **LOAD AND FOLLOW** the entire audit.md workflow   |
 
-### Files to be Created:
+### Folders to be Created (v4.0 - folder-based):
 
-- [ ] `./documents/audit/audit-security.md`
-- [ ] `./documents/audit/audit-compliance.md`
-- [ ] `./documents/audit/audit-dataflow.md`
-- [ ] `./documents/audit/audit-recommendations.md`
+- [ ] `./documents/audit/audit-security/` (00-index.md + 4 sub-files)
+- [ ] `./documents/audit/audit-compliance/` (00-index.md + 4 sub-files)
+- [ ] `./documents/audit/audit-dataflow/` (00-index.md + 4 sub-files)
+- [ ] `./documents/audit/audit-recommendations/` (00-index.md + 4 sub-files)
 
 ---
 
 ## ✅ FINAL VERIFICATION (REQUIRED)
 
-Before reporting "Done", verify **ALL 13 FILES** exist:
+Before reporting "Done", verify ALL deliverables exist:
 
 ```
 ./documents/
-├── Core (5 files)
-│   ├── ✅ knowledge-overview.md
-│   ├── ✅ knowledge-architecture.md
-│   ├── ✅ knowledge-domain.md
-│   ├── ✅ knowledge-source-base.md
-│   └── ✅ knowledge-standards.md
-├── Business (folder)
-│   ├── ✅ business-prd.md
-│   ├── ✅ business-features.md
-│   ├── ✅ business-workflows.md
-│   └── ✅ business-glossary.md
-└── Audit (4 files)
-    ├── ✅ audit-security.md
-    ├── ✅ audit-compliance.md
-    ├── ✅ audit-dataflow.md
-    └── ✅ audit-recommendations.md
+├── Core (5 folders, 26+ files)
+│   ├── ✅ knowledge-overview/        (00-index + 01~04)
+│   ├── ✅ knowledge-architecture/    (00-index + 01~05)
+│   ├── ✅ knowledge-domain/          (00-index + 01~04)
+│   ├── ✅ knowledge-source-base/     (00-index + 01~04)
+│   └── ✅ knowledge-standards/       (00-index + 01~04)
+├── Business (4 folders, 22+ files)
+│   ├── ✅ business-prd/          (00-index + 01~04)
+│   ├── ✅ business-features/     (00-index + 01~05)
+│   ├── ✅ business-workflows/    (00-index + 01~05)
+│   └── ✅ business-glossary/     (00-index + 01~04)
+└── Audit (4 folders, 20+ files)
+    ├── ✅ audit-security/         (00-index + 01~04)
+    ├── ✅ audit-compliance/       (00-index + 01~04)
+    ├── ✅ audit-dataflow/         (00-index + 01~04)
+    └── ✅ audit-recommendations/  (00-index + 01~04)
 ```
 
 ---
 
 ## 📊 COMPLETION OUTPUT
 
-Only output this when ALL 13 files are verified:
+Only output this when ALL deliverables are verified:
 
 ```markdown
 ## ✅ Full Documentation Suite Complete
 
-### 📁 All 13 Documents Created
+### 📁 All Documents Created
 
-| Type     | Files Created                                        | Status |
-| -------- | ---------------------------------------------------- | ------ |
-| Core     | overview, architecture, domain, source-base, standards | ✅ 5/5 |
-| Business | prd, features, workflows, glossary                   | ✅ 4/4 |
-| Audit    | security, compliance, dataflow, recommendations      | ✅ 4/4 |
+| Type     | Deliverables                                                | Status   |
+| -------- | ----------------------------------------------------------- | -------- |
+| Core     | 5 knowledge folders (overview, architecture, domain, source-base, standards) | ✅ 5/5 folders |
+| Business | 4 business folders (prd, features, workflows, glossary)     | ✅ 4/4 folders |
+| Audit    | 4 audit folders (security, compliance, dataflow, recommendations) | ✅ 4/4 folders |
 
-**Total: 13/13 files created in `./documents/`**
+**Total: 13 folders (68+ files) created in `./documents/`**
 ```
 
 ---
@@ -161,9 +162,9 @@ Only output this when ALL 13 files are verified:
 ## 🚫 FORBIDDEN
 
 - ❌ Skipping any sub-command
-- ❌ Creating partial files and reporting "Done"
+- ❌ Creating partial deliverables and reporting "Done"
 - ❌ Executing sub-commands in parallel (must be sequential)
-- ❌ Reporting "Done" before all 12 files exist
+- ❌ Reporting "Done" before all deliverables exist
 
 ---
 
@@ -171,8 +172,8 @@ Only output this when ALL 13 files are verified:
 
 If you need only ONE type:
 
-| Route            | Files Created        |
-| ---------------- | -------------------- |
-| `/docs:core`     | 5 knowledge-\* files |
-| `/docs:business` | 4 business-\* files  |
-| `/docs:audit`    | 4 audit-\* files     |
+| Route            | Deliverables Created                           |
+| ---------------- | ---------------------------------------------- |
+| `/docs:core`     | 5 knowledge folders with 00-index + sub-files  |
+| `/docs:business` | 4 business folders with 00-index + sub-files  |
+| `/docs:audit`    | 4 audit folders with 00-index + sub-files      |

package/documents/business/business-features/00-index.md

@@ -0,0 +1,101 @@
+# Agent Assistant — Business Features (MoSCoW)
+
+> **Purpose**: Features summary, table of contents, key facts, cross-references, and known gaps for @namch/agent-assistant v1.3.0
+> **Last Updated**: 2026-03-26
+> **Generated By**: docs-business skill
+
+---
+
+## Quick Summary
+
+This document set catalogs the **23 business features** of @namch/agent-assistant v1.3.0, classified using the MoSCoW prioritization framework. Features span the full product surface — from one-time global installation (BF-001) through autonomous execution (BF-020) — and map directly to 10 business goals (BG-001 through BG-010).
+
+The MoSCoW breakdown is: **10 Must Have** (core orchestration, agents, commands, skills), **8 Should Have** (teams, error healing, dynamic discovery, debate), **5 Could Have** (deployment workflows, autonomous mode, reporting, plan short-circuit, CLI list). All 10 Must Have features shipped in v1.0.0. Should Have features landed across v1.0.3–v1.2.0. Could Have features are partially delivered (BF-019 in v1.2.0, BF-020–BF-022 in v1.0.4, BF-023 pending).
+
+---
+
+## Sub-Files
+
+| # | File | Description |
+|---|------|-------------|
+| 1 | [01-feature-inventory.md](./01-feature-inventory.md) | Complete inventory of all 23 features (BF-001–BF-023) with descriptions and business value |
+| 2 | [02-prioritization-moscow.md](./02-prioritization-moscow.md) | MoSCoW classification with rationale and dependency analysis |
+| 3 | [03-feature-specifications.md](./03-feature-specifications.md) | Per-feature specifications: acceptance criteria (Given/When/Then), technical surface, dependencies |
+| 4 | [04-dependencies-and-release-sequencing.md](./04-dependencies-and-release-sequencing.md) | Dependency graph (Mermaid), release history mapping, recommended rollout order |
+| 5 | [05-success-metrics.md](./05-success-metrics.md) | KPIs per feature, baselines, targets, measurement approach |
+
+---
+
+## Key Facts
+
+| Key | Value |
+|-----|-------|
+| Total Features | 23 (BF-001 through BF-023) |
+| Must Have | 10 |
+| Should Have | 8 |
+| Could Have | 5 |
+| Won't Have | 0 (this release) |
+| Features Delivered | 22 of 23 |
+| Features Pending | 1 (BF-023: CLI List Command) |
+| Business Goals Covered | 10 of 10 (BG-001–BG-010) |
+| First Feature Release | v1.0.0 (2026-01-26) |
+| Latest Feature Release | v1.3.0 (2026-03-23) |
+| Releases with Features | 6 (v1.0.0, v1.0.3, v1.0.4, v1.1.0, v1.2.0, v1.3.0) |
+
+---
+
+## Cross-References
+
+### Knowledge Folders (docs-core)
+
+| Folder | Relationship to Features |
+|--------|--------------------------|
+| [../knowledge-overview/](../knowledge-overview/) | Feature descriptions, capability counts, performance metrics — factual basis for BF inventory |
+| [../knowledge-architecture/](../knowledge-architecture/) | System components, data flow, design patterns — informs technical surface per feature |
+| [../knowledge-domain/](../knowledge-domain/) | Entities, business rules — domain context for feature specifications |
+| [../knowledge-source-base/](../knowledge-source-base/) | Directory structure, key modules — evidence for file mappings in specifications |
+| [../knowledge-standards/](../knowledge-standards/) | Code style, conventions — informs quality-related features (BF-012, BF-014) |
+
+### Business Folders (docs-business)
+
+| Folder | Relationship to Features |
+|--------|--------------------------|
+| [../business-prd/](../business-prd/) | PRD goals (BG-001–BG-010) and requirements (BR-001–BR-023) that features implement |
+| business-features/ (this folder) | MoSCoW feature classification, specifications, dependencies, metrics |
+| business-user-stories/ | User stories derived from these features |
+| business-use-cases/ | Use case specifications exercising these features |
+| business-glossary/ | Canonical terminology for feature descriptions |
+
+### Source Documents
+
+| Document | Relationship |
+|----------|-------------|
+| [../../reports/business-analysis/structured-business-pack.md](../../reports/business-analysis/structured-business-pack.md) | Primary source — features section with MoSCoW table and goal mappings |
+| [../../CHANGELOG.md](../../CHANGELOG.md) | Release history — maps features to versions |
+| [../../README.md](../../README.md) | Public feature descriptions and metrics |
+| [../HSOL-ASSESSMENT.md](../HSOL-ASSESSMENT.md) | HSOL readiness — informs BF-007, BF-013, BF-014 metrics |
+
+---
+
+## Known Gaps
+
+| Gap ID | Description | Impact | Mitigation |
+|--------|-------------|--------|------------|
+| GAP-F01 | Performance metrics (70% faster, 70% bug reduction, 85% token savings) are self-reported and unvalidated by independent testing | Success metrics for BF-003, BF-007, BF-008 rely on unverified baselines | Flag as "UNVALIDATED" in metrics; plan benchmark suite |
+| GAP-F02 | BF-023 (CLI List Command) not yet implemented | Feature inventory shows 22/23 delivered | Low priority — Could Have classification; no business goal blocked |
+| GAP-F03 | Dynamic skill discovery (BF-013) depends on external network and community skill registry that does not yet have a published API | BF-014 (Trust Progression) also blocked without functional discovery | Design offline fallback; define registry API contract |
+| GAP-F04 | No formal A/B testing or telemetry to measure feature adoption rates | Cannot validate success metrics for adoption-related KPIs | Define measurement plan before v2.0 |
+| GAP-F05 | Debate mechanism (BF-016) max rounds and convergence rates not benchmarked | Cannot confirm 3-round max is sufficient for all domains | Collect empirical data from `:team` variant usage |
+
+---
+
+## Evidence Sources
+
+| Source | Path |
+|--------|------|
+| Structured Business Pack (features, goals, MoSCoW) | [../../reports/business-analysis/structured-business-pack.md](../../reports/business-analysis/structured-business-pack.md) |
+| CHANGELOG (release history) | [../../CHANGELOG.md](../../CHANGELOG.md) |
+| README (feature descriptions) | [../../README.md](../../README.md) |
+| Knowledge overview — features | [../knowledge-overview/03-features.md](../knowledge-overview/03-features.md) |
+| PRD — goals and scope | [../business-prd/02-problem-goals-and-scope.md](../business-prd/02-problem-goals-and-scope.md) |
+| PRD — requirements | [../business-prd/03-stakeholders-and-requirements.md](../business-prd/03-stakeholders-and-requirements.md) |

package/documents/business/business-features/01-feature-inventory.md

@@ -0,0 +1,341 @@
+# Agent Assistant — Feature Inventory
+
+> **Purpose**: Complete inventory of all 23 business features (BF-001–BF-023) with descriptions, business value, and goal traceability
+> **Parent**: [00-index.md](./00-index.md)
+> **Last Updated**: 2026-03-26
+> **Generated By**: docs-business skill
+
+---
+
+## Inventory Overview
+
+| Metric | Count |
+|--------|-------|
+| Total Features | 23 |
+| Must Have | 10 (BF-001–BF-010) |
+| Should Have | 8 (BF-011–BF-018) |
+| Could Have | 5 (BF-019–BF-023) |
+| Delivered | 22 |
+| Pending | 1 (BF-023) |
+
+---
+
+## Must Have Features (10)
+
+### BF-001 — One-Time Global Installation
+
+**Description**: The CLI installer copies all framework files (agents, commands, rules, skills, matrix-skills) into the AI tool's global configuration directory. Install once per platform — zero per-project configuration. Supports `install --all` for batch installation across all 5 platforms.
+
+**Business Value**: Eliminates setup friction. Developers start using 21 agents and 1,430+ skills immediately on every project without any per-repository configuration. Reduces onboarding time to under 60 seconds.
+
+**Goal Mapping**: BG-001 (Global setup)
+
+**Key Files**: `cli/install.js`, `package.json` (npm scripts)
+
+---
+
+### BF-002 — Multi-Platform Support (5 Platforms)
+
+**Description**: Identical agent definitions, commands, workflows, and skills work across Cursor, GitHub Copilot, Claude Code, Codex, and Antigravity/Gemini. Platform-specific path resolution and template variable replacement (`{TOOL}`, `{HOME}`) adapt the same source files for each platform's directory structure.
+
+**Business Value**: Write once, orchestrate everywhere. Teams using different AI tools share the same agent intelligence and workflow quality. No vendor lock-in.
+
+**Goal Mapping**: BG-002 (Multi-platform)
+
+**Key Files**: `cli/install.js` (TOOLS config), `code-assistants/*/`, platform entry files (CURSOR.md, COPILOT.md, CLAUDE.md, CODEX.md, GEMINI.md)
+
+---
+
+### BF-003 — Orchestrator Pattern
+
+**Description**: The AI assistant assumes the role of Orchestrator — it coordinates, delegates, and verifies but never implements directly. This is enforced by CORE.md loaded at session boot with mandatory prohibition statements and self-check protocol.
+
+**Business Value**: Prevents the AI from producing unreviewed, unstructured code. Forces specialization, traceability, and quality gates on every task. Directly drives the 70% time-to-production improvement and 70% bug reduction.
+
+**Goal Mapping**: BG-003 (Speed), BG-004 (Quality)
+
+**Key Files**: `rules/CORE.md`, platform entry files
+
+---
+
+### BF-004 — 21 Specialist Agents
+
+**Description**: Each agent is a Markdown file with a defined profile (role, expertise, cognitive anchor), directive (primary mission), protocol (how it executes), and constraints (what it must not do). Agents span implementation (4), architecture (2), quality (4), planning (3), and support (8) domains.
+
+**Business Value**: Specialization produces higher-quality output than generic AI responses. Each agent's profile triggers HSOL skill injection, ensuring domain-relevant knowledge is loaded. Agent constraints prevent scope creep.
+
+**Goal Mapping**: BG-004 (Quality)
+
+**Key Files**: `agents/*.md` (21 files), `agents/teams/` (17 teams × 3 roles = 51 team agent files)
+
+---
+
+### BF-005 — 14 Structured Commands
+
+**Description**: Commands are workflow definitions that orchestrate agent collaboration across phases. Each command file specifies the routing logic, phase sequence, agent assignments, and exit criteria. Categories: Build (`/cook`, `/code`, `/fix`), Quality (`/test`, `/review`, `/debug`), Plan (`/plan`, `/brainstorm`, `/design`), Docs (`/docs`), Report (`/report`), Deploy (`/deploy`), Inquiry (`/ask`), Auto (`/auto`).
+
+**Business Value**: Standardized workflows eliminate ad-hoc prompting. Every task follows a proven sequence of specialist agents, ensuring consistent quality regardless of the user's prompt engineering skill.
+
+**Goal Mapping**: BG-003 (Speed), BG-006 (Structured workflows)
+
+**Key Files**: `commands/*.md` (14 files), `commands/*/` (variant subdirectories)
+
+---
+
+### BF-006 — 4 Variant Strategies
+
+**Description**: Each command supports up to 4 variants controlling scope and rigor: `:fast` (2–3 agents, basic gates), `:hard` (5–8 agents, comprehensive gates including test/review/security), `:focus` (clean execution with context optimization), `:team` (adversarial Golden Triangle with debate mechanism).
+
+**Business Value**: Right-sized workflows for every task. Simple fixes use `:fast` (seconds), production features use `:hard` (thorough), critical systems use `:team` (adversarial review). Token cost scales with complexity.
+
+**Goal Mapping**: BG-003 (Speed), BG-006 (Structured workflows)
+
+**Key Files**: `commands/cook/fast.md`, `commands/cook/hard.md`, `commands/cook/focus.md`, `commands/cook/team.md` (pattern repeated per command)
+
+---
+
+### BF-007 — Matrix Skill Discovery (HSOL)
+
+**Description**: The Hybrid Skill Orchestration Layer automatically resolves and injects relevant skills based on the agent's profile and task context. Resolution algorithm: parse agent profile → load inherited domains from `matrix-skills/_index.yaml` → filter by relevance → apply priority thresholds → calculate fitness scores (semantic 35%, specificity 25%, trust 20%, freshness 10%, success 10%) → return sorted skill set. 1,430+ skills across 19 domains.
+
+**Business Value**: Eliminates manual skill selection. Agents receive precisely the knowledge they need, reducing token waste (85% savings) and improving output relevance. Skills scale independently of agent count.
+
+**Goal Mapping**: BG-005 (Token cost), BG-007 (Skill injection)
+
+**Key Files**: `rules/SKILLS.md`, `matrix-skills/_index.yaml`, `matrix-skills/*.yaml` (19 domain files), `skills/` (1,430+ modules)
+
+---
+
+### BF-008 — Tiered Execution
+
+**Description**: Two-tier execution model — TIER 1 uses `runSubagent` for isolated parallel execution when the platform supports it (Claude Code, Cursor Max mode). TIER 2 falls back to in-context agent embodiment when sub-agents are unavailable. TIER 1 is mandatory when available.
+
+**Business Value**: Maximizes parallelism where supported (multiple agents working simultaneously), while ensuring universal compatibility. Reduces total execution time on capable platforms.
+
+**Goal Mapping**: BG-003 (Speed), BG-005 (Token cost)
+
+**Key Files**: `rules/CORE.md` (Tiered Execution section), `rules/AGENTS.md`
+
+---
+
+### BF-009 — 10 Orchestration Laws
+
+**Description**: Formal governance rules constraining Orchestrator behavior: (L1) Single Point of Truth, (L2) Requirement Integrity, (L3) Phase Completion, (L4) Agent Specialization, (L5) Transparent Delegation, (L6) No Silent Failures, (L7) Skill Authority, (L8) Output Verification, (L9) Context Preservation, (L10) Minimal Intervention.
+
+**Business Value**: Predictable, auditable behavior. Laws prevent common AI failures — scope drift, silent errors, context loss, unauthorized implementation. Every session is governed by the same rules.
+
+**Goal Mapping**: BG-004 (Quality)
+
+**Key Files**: `rules/CORE.md` (Laws section)
+
+---
+
+### BF-010 — Cognitive Anchoring
+
+**Description**: Every agent file contains a cognitive anchor block — a structured identity section that reinforces the agent's role, expertise, and boundaries at the start of execution. This prevents role drift during long sessions.
+
+**Business Value**: Agents maintain consistent behavior across extended conversations. Role-specific expertise is preserved even when context windows approach limits.
+
+**Goal Mapping**: BG-004 (Quality)
+
+**Key Files**: `agents/*.md` (cognitive anchor block in each), `AGENT-TEMPLATE.md`
+
+---
+
+## Should Have Features (8)
+
+### BF-011 — 17 Domain Teams (Golden Triangle)
+
+**Description**: Adversarial collaboration system with 17 specialized domain teams, each composed of 3 roles: Tech Lead (designs approach), Executor (implements), Reviewer (challenges). Teams span backend, frontend, fullstack, database, research, planning, QA, design, debug, devops, security, game, mobile, performance, docs, project, and report domains.
+
+**Business Value**: Multiple expert perspectives on critical features. The adversarial model catches design flaws, implementation bugs, and edge cases that a single agent would miss. 51 team agents total.
+
+**Goal Mapping**: BG-004 (Quality), BG-008 (Adversarial quality)
+
+**Key Files**: `rules/TEAMS.md`, `agents/teams/*/` (17 directories × 3 files each)
+
+---
+
+### BF-012 — Error Self-Healing (E1–E4)
+
+**Description**: Classified error recovery system — E1 (Warning: auto-retry), E2 (Recoverable: fallback strategy), E3 (Blocking: pause for user input), E4 (Critical: halt with diagnostics). No silent failures — every error is surfaced, classified, and handled according to its severity.
+
+**Business Value**: Prevents cascading failures and invisible quality degradation. Users always know the state of execution. Recovery is automatic where safe, manual where necessary.
+
+**Goal Mapping**: BG-004 (Quality)
+
+**Key Files**: `rules/ERRORS.md`
+
+---
+
+### BF-013 — Dynamic Skill Discovery
+
+**Description**: When the matrix fitness score falls below 0.8 for `:hard` or `:focus` variants, the `find-skills` mechanism can discover additional community skills at runtime. Discovered skills are registered in `matrix-skills/_dynamic.yaml`.
+
+**Business Value**: Extends the framework's knowledge beyond the bundled 1,430 skills. Community contributions supplement gaps in niche or emerging domains without requiring a framework release.
+
+**Goal Mapping**: BG-007 (Skill injection), BG-009 (Community ecosystem)
+
+**Key Files**: `rules/SKILLS.md` (dynamic section), `matrix-skills/_dynamic.yaml`
+
+---
+
+### BF-014 — Trust Progression Lifecycle
+
+**Description**: Dynamically discovered skills follow a trust lifecycle: NEW → EVALUATING → VALIDATED → PROMOTED. Skills are gated at each stage based on usage outcomes, preventing untested community skills from ranking alongside verified core skills.
+
+**Business Value**: Balances openness (community skills welcome) with quality (untested skills don't override proven ones). Trust builds through demonstrated success, not popularity.
+
+**Goal Mapping**: BG-007 (Skill injection), BG-009 (Community ecosystem)
+
+**Key Files**: `rules/SKILLS.md` (trust section), `matrix-skills/_dynamic.yaml`
+
+---
+
+### BF-015 — Documentation Generation (/docs)
+
+**Description**: The `/docs` command generates structured documentation across three categories: Core (5 folders: overview, architecture, domain, source-base, standards), Business (4 folders: PRD, user stories, use cases, glossary + features), and Audit (4 folders). Uses scouter for discovery, business-analyst for analysis, and docs-manager for authoring.
+
+**Business Value**: Auto-generates comprehensive project documentation from source code and framework artifacts. Reduces documentation debt and ensures consistency across docs types.
+
+**Goal Mapping**: BG-006 (Structured workflows), BG-010 (Auto-docs)
+
+**Key Files**: `commands/docs.md`, `commands/docs/*.md`, `agents/docs-manager.md`, `agents/scouter.md`, `agents/business-analyst.md`
+
+---
+
+### BF-016 — Debate Mechanism (Mailbox)
+
+**Description**: The `:team` variant uses an append-only mailbox (`./reports/{topic}/MAILBOX-{date}.md`) for inter-agent communication. Message types: TASK_ASSIGNMENT, SUBMISSION, REVIEW, DEFENSE, ARBITRATION, DECISION. Maximum 3 debate rounds before Tech Lead makes a binding arbitration decision.
+
+**Business Value**: Traceable quality improvement. Every challenge, defense, and resolution is recorded. The 3-round limit prevents infinite loops while ensuring substantive review.
+
+**Goal Mapping**: BG-008 (Adversarial quality)
+
+**Key Files**: `rules/TEAMS.md` (mailbox section)
+
+---
+
+### BF-017 — Natural Language Command Detection
+
+**Description**: The Orchestrator detects user intent from natural language and maps it to the correct command. Examples: "implement/build/create" → `/cook` or `/code`, "fix/bug" → `/fix`, "plan" → `/plan`. Routing logic is defined in CORE.md.
+
+**Business Value**: Users do not need to memorize 14 commands and 54 variants. Natural language input is automatically routed to the correct workflow, lowering the learning curve.
+
+**Goal Mapping**: BG-005 (Token cost)
+
+**Key Files**: `rules/CORE.md` (command routing section)
+
+---
+
+### BF-018 — Language Compliance (L6)
+
+**Description**: Responses are always in the user's language. Code, comments, and generated files are always in English. This is enforced as Law L6 in CORE.md and referenced in every platform entry file.
+
+**Business Value**: International accessibility without sacrificing code consistency. Non-English speakers receive guidance in their language while all artifacts remain in English for team collaboration.
+
+**Goal Mapping**: BG-004 (Quality)
+
+**Key Files**: `rules/CORE.md` (Law L6)
+
+---
+
+## Could Have Features (5)
+
+### BF-019 — Deployment Workflows (/deploy)
+
+**Description**: The `/deploy` command provides 4 variants: `check` (pre-deployment validation), `preview` (staging deployment), `production` (production release), `rollback` (revert). Orchestrated by devops-engineer agent.
+
+**Business Value**: Structured deployment reduces release risk. Validation steps catch issues before they reach production. Rollback provides a safety net.
+
+**Goal Mapping**: BG-006 (Structured workflows)
+
+**Key Files**: `commands/deploy.md`, `commands/deploy/*.md`, `agents/devops-engineer.md`
+
+---
+
+### BF-020 — Autonomous Execution (/auto)
+
+**Description**: The `/auto` command enables self-routing execution without user pauses at phase boundaries. The tech-lead agent classifies the task and selects the appropriate command and variant automatically.
+
+**Business Value**: Hands-off execution for confident users. The AI handles the full workflow from classification to delivery without interruption.
+
+**Goal Mapping**: BG-006 (Structured workflows)
+
+**Key Files**: `commands/auto.md`, `agents/tech-lead.md`
+
+---
+
+### BF-021 — Reporting System (/report)
+
+**Description**: The `/report` command generates status reports, sprint summaries, and analysis documents. Uses the reporter agent for authoring and scouter for data gathering. Supports create, update, and template-based output modes.
+
+**Business Value**: Automated project reporting reduces manual effort and ensures reports are grounded in actual project state rather than memory.
+
+**Goal Mapping**: BG-006 (Structured workflows)
+
+**Key Files**: `commands/report.md`, `commands/report/*.md`, `agents/reporter.md`, `agents/scouter.md`
+
+---
+
+### BF-022 — Plan Short-Circuit
+
+**Description**: When the user references an existing plan (`@plan`, `@PLAN-...`, path to `PLAN-*.md`, or phrases like "follow the plan"), research/scout/brainstorm phases are skipped. Execution jumps directly to context optimization → implementation → test → review.
+
+**Business Value**: Eliminates redundant research when planning is already complete. Reduces token cost and execution time for plan-driven development.
+
+**Goal Mapping**: BG-003 (Speed)
+
+**Key Files**: `commands/code.md` (routing), `commands/code/hard.md`, `commands/code/focus.md` (skip logic)
+
+---
+
+### BF-023 — CLI List Command
+
+**Description**: A CLI command to show which platforms have agent-assistant installed, their versions, and installation status.
+
+**Business Value**: Visibility into installation state across platforms. Useful for troubleshooting and verifying multi-platform setup.
+
+**Goal Mapping**: BG-001 (Global setup)
+
+**Key Files**: `cli/install.js` (planned addition)
+
+**Status**: NOT YET IMPLEMENTED
+
+---
+
+## Business Goals → Features Traceability
+
+| Goal | ID | Features |
+|------|----|----------|
+| Global setup | BG-001 | BF-001, BF-023 |
+| Multi-platform | BG-002 | BF-002 |
+| Speed | BG-003 | BF-003, BF-005, BF-006, BF-008, BF-022 |
+| Quality | BG-004 | BF-003, BF-004, BF-009, BF-010, BF-011, BF-012, BF-018 |
+| Token cost | BG-005 | BF-007, BF-008, BF-017 |
+| Structured workflows | BG-006 | BF-005, BF-006, BF-015, BF-019, BF-020, BF-021 |
+| Skill injection | BG-007 | BF-007, BF-013, BF-014 |
+| Adversarial quality | BG-008 | BF-011, BF-016 |
+| Community ecosystem | BG-009 | BF-013, BF-014 |
+| Auto-docs | BG-010 | BF-015 |
+
+---
+
+## Evidence Sources
+
+| Source | Path |
+|--------|------|
+| Structured Business Pack | [../../reports/business-analysis/structured-business-pack.md](../../reports/business-analysis/structured-business-pack.md) |
+| Knowledge overview — features | [../knowledge-overview/03-features.md](../knowledge-overview/03-features.md) |
+| CHANGELOG | [../../CHANGELOG.md](../../CHANGELOG.md) |
+| README | [../../README.md](../../README.md) |
+| CORE rules | [../../rules/CORE.md](../../rules/CORE.md) |
+| SKILLS rules | [../../rules/SKILLS.md](../../rules/SKILLS.md) |
+| TEAMS rules | [../../rules/TEAMS.md](../../rules/TEAMS.md) |
+| ERRORS rules | [../../rules/ERRORS.md](../../rules/ERRORS.md) |
+| AGENTS rules | [../../rules/AGENTS.md](../../rules/AGENTS.md) |
+| CLI installer | [../../cli/install.js](../../cli/install.js) |
+| Agent definitions | [../../agents/](../../agents/) |
+| Commands | [../../commands/](../../commands/) |
+| Matrix skills | [../../matrix-skills/](../../matrix-skills/) |
+| HSOL Assessment | [../HSOL-ASSESSMENT.md](../HSOL-ASSESSMENT.md) |