@namch/agent-assistant 1.3.0 → 1.3.2

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 — 3 Variant Strategies
+
+**Description**: Each command supports up to 3 variants controlling scope and rigor: `:fast` (2–3 agents, basic gates), `:hard` (5–8 agents, comprehensive gates including test/review/security), `: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/team.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 `:team` 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/team.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) |

package/documents/business/business-features/02-prioritization-moscow.md

@@ -0,0 +1,148 @@
+# Agent Assistant — MoSCoW Prioritization
+
+> **Purpose**: MoSCoW classification of all 23 features with rationale, dependency analysis, and priority justification
+> **Parent**: [00-index.md](./00-index.md)
+> **Last Updated**: 2026-03-26
+> **Generated By**: docs-business skill
+
+---
+
+## MoSCoW Summary
+
+| Priority | Count | Features | Rationale |
+|----------|-------|----------|-----------|
+| **Must Have** | 10 | BF-001–BF-010 | Core framework — without these, the product has no value proposition |
+| **Should Have** | 8 | BF-011–BF-018 | Significant quality and ecosystem enhancements — differentiate from basic prompt engineering |
+| **Could Have** | 5 | BF-019–BF-023 | Convenience and automation — valuable but not required for core workflows |
+| **Won't Have** | 0 | — | No features deferred from v1.3.0 scope |
+
+---
+
+## Must Have (10) — Core Framework
+
+These features are non-negotiable. Without any one of them, the framework cannot deliver its primary value proposition of structured multi-agent orchestration.
+
+| BF-ID | Feature | Rationale | Dependencies | Delivered |
+|-------|---------|-----------|-------------|-----------|
+| BF-001 | One-Time Global Installation | Entry point to the framework. Without installation, nothing works. Zero-config is the fundamental UX promise. | Node.js >=18, npm | v1.0.0 |
+| BF-002 | Multi-Platform Support (5) | Platform coverage is a stated product goal (BG-002). Single-platform would limit addressable market to one tool's users. | BF-001 (CLI platform config) | v1.0.0–v1.2.0 |
+| BF-003 | Orchestrator Pattern | The defining architectural decision. If the AI implements directly, there is no orchestration — just a chatbot with extra prompts. | CORE.md loaded at boot | v1.0.0 |
+| BF-004 | 21 Specialist Agents | Agents are the execution workforce. Without specialists, the Orchestrator has nobody to delegate to. Agent profiles drive HSOL skill injection. | BF-003 (pattern requires agents) | v1.0.0 |
+| BF-005 | 14 Structured Commands | Commands are the user interface to the framework. Without commands, users have no structured entry point to workflows. | BF-003 (Orchestrator routes), BF-004 (agents execute) | v1.0.0 |
+| BF-006 | 4 Variant Strategies | Variants enable right-sizing — without them, every task gets the same treatment regardless of complexity. `:fast` vs `:hard` is a core efficiency mechanism. | BF-005 (command router logic) | v1.0.0–v1.0.4 |
+| BF-007 | Matrix Skill Discovery (HSOL) | Skill injection is the knowledge layer. Without HSOL, agents operate on generic training data only, losing the 85% token savings and domain-specific quality. | BF-004 (agent profiles), matrix YAML files | v1.0.0 (v1.1.0 rewrite) |
+| BF-008 | Tiered Execution | Platform capability varies. Without tiered execution, the framework either fails on limited platforms or under-utilizes capable ones. | BF-003 (Orchestrator delegates) | v1.0.0 |
+| BF-009 | 10 Orchestration Laws | Laws prevent the Orchestrator from drifting into anti-patterns (silent failures, scope creep, direct implementation). Without governance, quality is inconsistent. | BF-003 (laws govern Orchestrator) | v1.0.0 |
+| BF-010 | Cognitive Anchoring | Prevents role drift in AI agents during long sessions. Without anchoring, agents gradually lose their specialist identity and produce generic output. | BF-004 (agent file format) | v1.0.0 |
+
+### Must Have Dependency Chain
+
+```
+BF-001 (Install) → BF-002 (Platforms)
+BF-001 (Install) → BF-003 (Orchestrator) → BF-009 (Laws)
+BF-003 (Orchestrator) → BF-004 (Agents) → BF-010 (Anchoring)
+BF-003 (Orchestrator) → BF-005 (Commands) → BF-006 (Variants)
+BF-003 (Orchestrator) → BF-008 (Tiered Execution)
+BF-004 (Agents) → BF-007 (HSOL)
+```
+
+**Critical path**: BF-001 → BF-003 → BF-004 → BF-007. If any link in this chain is missing, the core value proposition collapses.
+
+---
+
+## Should Have (8) — Quality & Ecosystem
+
+These features significantly enhance quality, reliability, and extensibility. The framework functions without them, but key differentiators (adversarial quality, self-healing, ecosystem growth) are lost.
+
+| BF-ID | Feature | Rationale | Dependencies | Delivered |
+|-------|---------|-----------|-------------|-----------|
+| BF-011 | 17 Domain Teams | Adversarial collaboration (BG-008) is a key quality differentiator — but single-agent execution still works. Teams are an upgrade, not a requirement. | BF-006 (`:team` variant), `rules/TEAMS.md` | v1.2.0 |
+| BF-012 | Error Self-Healing (E1–E4) | Silent failures degrade trust. Classified recovery is important but the framework can operate (with degraded UX) without it. | `rules/ERRORS.md` | v1.0.0 |
+| BF-013 | Dynamic Skill Discovery | Extends skills beyond bundled 1,430. Important for niche domains but the core skill set covers most use cases. | `find-skills` CLI, network access | v1.3.0 |
+| BF-014 | Trust Progression Lifecycle | Quality gate for dynamic skills. Without it, community skills could degrade output quality. Important but only relevant when BF-013 is active. | BF-013 (dynamic discovery active) | v1.3.0 |
+| BF-015 | Documentation Generation | Auto-docs save significant effort (BG-010) but developers can write docs manually. High value, not existential. | BF-004 (scouter, BA, docs-manager agents) | v1.0.0 |
+| BF-016 | Debate Mechanism (Mailbox) | Traceable inter-agent communication is valuable for audit and quality but teams can function with implicit communication. | BF-011 (teams active), `rules/TEAMS.md` | v1.2.0 |
+| BF-017 | Natural Language Command Detection | Lowers learning curve by mapping plain language to commands. Useful but users can learn the 14 command names directly. | CORE.md routing logic | v1.0.0 |
+| BF-018 | Language Compliance (L6) | International accessibility. English-only users are unaffected. Important for global adoption but not blocking for English-speaking markets. | CORE.md Law L6 | v1.0.0 |
+
+### Should Have Dependency Analysis
+
+| Feature | Hard Dependencies | Soft Dependencies |
+|---------|-------------------|-------------------|
+| BF-011 | BF-006 (`:team` variant exists) | BF-016 (mailbox enhances teams) |
+| BF-012 | None (standalone rules file) | BF-008 (tiered execution generates errors) |
+| BF-013 | BF-007 (HSOL active, fitness score available) | Network access |
+| BF-014 | BF-013 (skills must be discoverable) | BF-007 (trust integrates with fitness scoring) |
+| BF-015 | BF-004 (scouter, BA, docs-manager agents) | BF-005 (`/docs` command) |
+| BF-016 | BF-011 (teams must exist) | — |
+| BF-017 | BF-005 (commands must exist to route to) | — |
+| BF-018 | None (CORE.md law) | — |
+
+---
+
+## Could Have (5) — Convenience & Automation
+
+These features improve user experience and automation but are not required for the primary use cases. They can be deferred or delivered incrementally.
+
+| BF-ID | Feature | Rationale | Dependencies | Delivered |
+|-------|---------|-----------|-------------|-----------|
+| BF-019 | Deployment Workflows | Deployment is valuable but many teams have existing CI/CD pipelines. Agent-assisted deployment is additive, not essential. | BF-004 (devops-engineer agent) | v1.2.0 |
+| BF-020 | Autonomous Execution | Hands-off execution is powerful but users generally want visibility into AI decisions. Higher risk without human checkpoints. | BF-004 (tech-lead agent), BF-005 (command classification) | v1.0.4 |
+| BF-021 | Reporting System | Automated reports save time but are not part of the core build→test→review loop. Additive value. | BF-004 (reporter, scouter agents) | v1.0.3 |
+| BF-022 | Plan Short-Circuit | Optimization for plan-driven workflows. Saves tokens and time but non-critical — redundant research is wasteful, not blocking. | BF-005 (`/code` command), existing `PLAN-*.md` | v1.0.4 |
+| BF-023 | CLI List Command | Diagnostic convenience. Users can check installation status manually by inspecting directories. | BF-001 (CLI exists) | NOT YET |
+
+### Could Have Dependency Analysis
+
+| Feature | Hard Dependencies | Soft Dependencies |
+|---------|-------------------|-------------------|
+| BF-019 | BF-004 (devops-engineer agent) | BF-006 (`:team` variant for deploy) |
+| BF-020 | BF-004 (tech-lead), BF-005 (commands) | All commands (auto routes to them) |
+| BF-021 | BF-004 (reporter, scouter) | BF-005 (`/report` command) |
+| BF-022 | BF-005 (`/code` command) | Existing plan files |
+| BF-023 | BF-001 (CLI) | — |
+
+---
+
+## Priority Justification Matrix
+
+| BF-ID | Without It... | MoSCoW |
+|-------|---------------|--------|
+| BF-001 | Framework cannot be installed | Must |
+| BF-002 | Limited to one platform | Must |
+| BF-003 | No orchestration — just a chatbot | Must |
+| BF-004 | Nothing to delegate to | Must |
+| BF-005 | No structured entry point | Must |
+| BF-006 | Every task gets same treatment | Must |
+| BF-007 | Agents lack domain knowledge | Must |
+| BF-008 | Fails on limited platforms OR wastes capable ones | Must |
+| BF-009 | Orchestrator behavior is unpredictable | Must |
+| BF-010 | Agents drift roles in long sessions | Must |
+| BF-011 | No adversarial review — single-agent quality only | Should |
+| BF-012 | Silent failures degrade trust | Should |
+| BF-013 | Limited to bundled skills only | Should |
+| BF-014 | Community skills could degrade quality | Should |
+| BF-015 | Manual documentation effort | Should |
+| BF-016 | Team communication is implicit, not auditable | Should |
+| BF-017 | Users must memorize commands | Should |
+| BF-018 | English-only interface | Should |
+| BF-019 | Teams use existing CI/CD | Could |
+| BF-020 | Users guide execution manually | Could |
+| BF-021 | Reports written manually | Could |
+| BF-022 | Redundant research when plans exist | Could |
+| BF-023 | Check install status manually | Could |
+
+---
+
+## Evidence Sources
+
+| Source | Path |
+|--------|------|
+| Structured Business Pack (MoSCoW table) | [../../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) |
+| PRD — goals and scope | [../business-prd/02-problem-goals-and-scope.md](../business-prd/02-problem-goals-and-scope.md) |
+| CHANGELOG | [../../CHANGELOG.md](../../CHANGELOG.md) |
+| CORE rules | [../../rules/CORE.md](../../rules/CORE.md) |
+| TEAMS rules | [../../rules/TEAMS.md](../../rules/TEAMS.md) |
+| SKILLS rules | [../../rules/SKILLS.md](../../rules/SKILLS.md) |
+| ERRORS rules | [../../rules/ERRORS.md](../../rules/ERRORS.md) |