@namch/agent-assistant 1.3.1 → 1.3.2

package/documents/business/business-prd/03-stakeholders-and-requirements.md

@@ -125,7 +125,7 @@
 | Req ID | Requirement | Priority | INVEST Score | Stakeholders | Goals |
 |--------|-------------|----------|-------------|--------------|-------|
 | BR-006 | 14 structured commands available (`/cook`, `/fix`, `/plan`, `/debug`, `/test`, `/review`, `/docs`, `/design`, `/deploy`, `/report`, `/brainstorm`, `/ask`, `/code`, `/auto`) | Must | 25/30 | S1 | BG-006 |
-| BR-007 | 4 variant strategies per command: `fast`, `hard`, `focus`, `team` | Should | 26/30 | S1 | BG-006 |
+| BR-007 | 4 variant strategies per command: `fast`, `hard`, `team` | Should | 26/30 | S1 | BG-006 |
 | BR-015 | Natural language command detection maps free-text to structured commands | Must | 27/30 | S1 | BG-006 |
 | BR-016 | Plan-already-provided short-circuit skips planning when user supplies a plan | Should | 28/30 | S1 | BG-003, BG-005 |
 | BR-017 | Documentation generation via `/docs` creates knowledge, business, and audit docs | Should | 23/30 | S1, S6 | BG-010 |

package/documents/business/business-workflows/02-workflow-catalog.md

@@ -109,7 +109,7 @@ All 12 workflows are classified by complexity (Low / Medium / High) and frequenc
 | **ID** | BW-006 |
 | **Name** | Dynamic Skill Discovery |
 | **Actor** | HSOL System |
-| **Trigger** | Fitness score < 0.8 for hard/focus command variants |
+| **Trigger** | Fitness score < 0.8 for hard/team command variants |
 | **Outcome** | `npx skills find` → evaluate candidates → check superiority delta (>0.15) → if low-trust + critical: user confirmation → `npx skills add` → register in `_dynamic.yaml` |
 | **Exception Handling** | Timeout (5s) → matrix-only fallback; install failure → rollback + offer matrix skills |
 | **Complexity** | High |
@@ -194,7 +194,7 @@ All 12 workflows are classified by complexity (Low / Medium / High) and frequenc
 | **ID** | BW-011 |
 | **Name** | Plan Short-Circuit |
 | **Actor** | Orchestrator |
-| **Trigger** | User references an existing `PLAN-*.md` file in `/code:hard` or `/code:focus` commands |
+| **Trigger** | User references an existing `PLAN-*.md` file in `/code:hard` or `/code:team` commands |
 | **Outcome** | Detect plan reference → skip research/scout/brainstorm phases → jump to context optimization → implement → test → review |
 | **Exception Handling** | Plan file must exist and be valid; invalid plan → fall back to standard BW-003 flow |
 | **Complexity** | Low |

package/documents/business/business-workflows/03-detailed-workflows.md

@@ -123,7 +123,7 @@ This is the core workflow of the framework. When a user types a command (explici
 1. User input received (prompt or natural language)
 2. **Pre-flight**: Orchestrator validates input is actionable
 3. **Command Detection**: Match input to command (`/cook`, `/fix`, `/plan`, etc.) or natural language mapping
-4. **Variant Resolution**: Determine variant (`:easy`, `:hard`, `:focus`, `:team`, etc.) — default if unspecified
+4. **Variant Resolution**: Determine variant (`:easy`, `:hard`, `:team`, etc.) — default if unspecified
 5. **Workflow File Load**: Read `commands/{cmd}.md` → `commands/{cmd}/{variant}.md`
 6. **Phase Initialization**: Parse phase sequence from workflow file
 7. **For each phase (sequential)**:
@@ -562,11 +562,11 @@ flowchart TD
 
 ### Narrative
 
-When a user references an existing plan file in a `/code:hard` or `/code:focus` command, the Orchestrator detects this and skips early research phases, jumping directly to implementation.
+When a user references an existing plan file in a `/code:hard` or `/code:team` command, the Orchestrator detects this and skips early research phases, jumping directly to implementation.
 
 ### Steps
 
-1. User invokes `/code:hard` or `/code:focus` referencing `PLAN-*.md`
+1. User invokes `/code:hard` or `/code:team` referencing `PLAN-*.md`
 2. Orchestrator detects plan file reference
 3. Validate that plan file exists and is parseable
 4. Extract implementation plan from file
@@ -576,7 +576,7 @@ When a user references an existing plan file in a `/code:hard` or `/code:focus`
 
 ```mermaid
 flowchart TD
-    A[/code:hard or /code:focus with PLAN ref] --> B{PLAN-*.md exists?}
+    A[/code:hard or /code:team with PLAN ref] --> B{PLAN-*.md exists?}
     B -->|No| C[Fall back to standard BW-003]
     B -->|Yes| D{Plan valid?}
     D -->|No| C
@@ -638,4 +638,4 @@ flowchart TD
 - `rules/PHASES.md` — Phase sequencing constraints, exit criteria definitions
 - `cli/install.js` — Installation and uninstallation implementation details
 - `commands/*.md` — Command definitions, variant routing rules
-- `commands/code/*.md` — Plan short-circuit detection in hard/focus variants
+- `commands/code/*.md` — Plan short-circuit detection in hard/team variants

package/documents/business/business-workflows/04-decision-rules-and-exceptions.md

@@ -61,7 +61,7 @@ The 10 Orchestration Laws define absolute behavioral constraints on the Orchestr
 | PS-003 | Input immutability | A phase receives prior deliverables as read-only inputs (Law 8) |
 | PS-004 | Halt on failure | If exit criteria not met and BW-010 cannot recover → halt workflow |
 | PS-005 | No skip | Phases cannot be skipped except via explicit short-circuit (BW-011) |
-| PS-006 | Plan short-circuit | If valid PLAN-*.md referenced in /code:hard or /code:focus → skip research/scout/brainstorm phases |
+| PS-006 | Plan short-circuit | If valid PLAN-*.md referenced in /code:hard or /code:team → skip research/scout/brainstorm phases |
 | PS-007 | Variant authority | The variant file defines the phase sequence — no deviation |
 
 ---
@@ -84,7 +84,7 @@ The 10 Orchestration Laws define absolute behavioral constraints on the Orchestr
 | HS-005 | Confirmation gate | Low-trust skill + critical task → Framework User confirmation required |
 | HS-006 | Timeout ceiling | Discovery must complete within 5 seconds; timeout → matrix-only |
 | HS-007 | Install rollback | Failed installation → rollback + offer matrix alternatives |
-| HS-008 | Hard/focus only | Dynamic discovery only triggers for hard and focus command variants |
+| HS-008 | Hard/team only | Dynamic discovery only triggers for hard and team command variants |
 
 ### Trust Progression Rules
 

package/documents/business/business-workflows/05-sla-and-handoffs.md

@@ -33,7 +33,7 @@ These timings depend on the AI model's inference speed and context window. They
 |----------|-----------|---------------|------------|
 | BW-003 | Single phase execution | 5s – 60s | Model inference + tool execution |
 | BW-003 | Full command (simple variant) | 30s – 5min | Phase count × phase time |
-| BW-003 | Full command (hard/focus variant) | 2min – 30min | Research + implementation complexity |
+| BW-003 | Full command (hard/team variant) | 2min – 30min | Research + implementation complexity |
 | BW-004 | Agent delegation (TIER 1) | 5s – 30s per phase | Sub-agent spawn + execution |
 | BW-004 | Agent delegation (TIER 2) | 3s – 20s per phase | No spawn overhead |
 | BW-008 | Team collaboration (full cycle) | 5min – 45min | 1–3 debate rounds × 3 agents |

package/documents/knowledge-architecture/00-index.md

@@ -29,7 +29,7 @@ graph TB
 
     subgraph "Command Layer"
         ROUTER["14 Command Routers"]
-        VARIANTS["54 Workflow Variants<br/>(fast, hard, focus, team)"]
+        VARIANTS["54 Workflow Variants<br/>(fast, hard, team)"]
     end
 
     subgraph "Agent Layer"
@@ -95,7 +95,7 @@ graph TB
 | Platform Entry Points | 5 (CLAUDE.md, COPILOT.md, CURSOR.md, CODEX.md, GEMINI.md) |
 | Rule Files | 7 (CORE, PHASES, AGENTS, SKILLS, TEAMS, ERRORS, REFERENCE) |
 | Command Routers | 14 |
-| Workflow Variants | 4 per command (fast, hard, focus, team) |
+| Workflow Variants | 4 per command (fast, hard, team) |
 | Individual Agents | 21 across 5 categories (meta, execution, validation, research, support) |
 | Team Configurations | 17 teams × 3 roles = 51 team agents |
 | Skill Modules | 1,430 matrix + dynamic community skills |

package/documents/knowledge-architecture/01-system-overview.md

@@ -48,7 +48,7 @@ The framework draws from several patterns without being a pure instance of any:
 | **Orchestrator/Choreography** | Single orchestrator delegates to specialist agents via tiered execution |
 | **Plugin Architecture** | 1,430 skill modules are independently discoverable and composable |
 | **Pipeline** | Commands execute as phase-sequential pipelines with exit criteria |
-| **Strategy Pattern** | Command routers select variant workflows (fast/hard/focus/team) at runtime |
+| **Strategy Pattern** | Command routers select variant workflows (fast/hard/team/team) at runtime |
 | **Actor Model** | Agents communicate through append-only mailbox files, not direct calls |
 
 ---
@@ -82,7 +82,7 @@ graph TB
 
     subgraph "COMMAND LAYER — Routing"
         ROUTERS["14 Command Routers<br/>cook · fix · plan · debug<br/>test · review · docs · design<br/>deploy · report · brainstorm<br/>ask · code · auto"]
-        VARIANTS["Workflow Variants<br/>:fast · :hard · :focus · :team"]
+        VARIANTS["Workflow Variants<br/>:fast · :hard · :team"]
     end
 
     subgraph "AGENT LAYER — Execution"

package/documents/knowledge-architecture/02-components.md

@@ -132,19 +132,19 @@ graph LR
 
 | Command | Router File | Variants | Category |
 |---------|------------|----------|----------|
-| `/cook` | `commands/cook.md` | fast, hard, focus, team | Engineering |
-| `/fix` | `commands/fix.md` | fast, hard, focus, team | Engineering |
-| `/plan` | `commands/plan.md` | fast, hard, focus, team | Planning |
-| `/debug` | `commands/debug.md` | fast, hard, focus, team | Validation |
-| `/test` | `commands/test.md` | fast, hard, focus, team | Validation |
+| `/cook` | `commands/cook.md` | fast, hard, team | Engineering |
+| `/fix` | `commands/fix.md` | fast, hard, team | Engineering |
+| `/plan` | `commands/plan.md` | fast, hard, team | Planning |
+| `/debug` | `commands/debug.md` | fast, hard, team | Validation |
+| `/test` | `commands/test.md` | fast, hard, team | Validation |
 | `/review` | `commands/review.md` | fast, hard | Validation |
 | `/docs` | `commands/docs.md` | core, business, audit | Documentation |
-| `/design` | `commands/design.md` | fast, hard, focus, team | Design |
+| `/design` | `commands/design.md` | fast, hard, team | Design |
 | `/deploy` | `commands/deploy.md` | check, preview, production, rollback | Operations |
-| `/report` | `commands/report.md` | fast, hard, focus, team | Reporting |
+| `/report` | `commands/report.md` | fast, hard, team | Reporting |
 | `/brainstorm` | `commands/brainstorm.md` | fast, hard | Research |
 | `/ask` | `commands/ask.md` | fast, hard | Research |
-| `/code` | `commands/code.md` | fast, hard, focus, team | Engineering |
+| `/code` | `commands/code.md` | fast, hard, team | Engineering |
 | `/auto` | `commands/auto.md` | — | Meta |
 
 ### Router Structure (common pattern from cook.md)

package/documents/knowledge-architecture/03-data-flow.md

@@ -219,8 +219,7 @@ stateDiagram-v2
 |---------|-------------------|
 | `:fast` | Skip — use matrix skills only, no dynamic discovery |
 | `:hard` | Check matrix fitness; trigger discovery if < 0.8 |
-| `:focus` | Check matrix fitness; trigger discovery if < 0.8 |
-| `:team` | Same as `:hard`/`:focus` — applies per agent in the triangle |
+| `:team` | Same as `:hard` — applies per agent in the triangle |
 
 ---
 

package/documents/knowledge-architecture/04-design-patterns.md

@@ -156,7 +156,6 @@ Each command router selects from up to 4 strategy variants at runtime:
 |---------|----------|-------------|---------------|
 | `:fast` | Minimal workflow, skip research | 2–3 phases | Simple, clear specification |
 | `:hard` | Full workflow with research and planning | 5–7 phases | Complex, multi-component |
-| `:focus` | Full workflow with enforced context optimization | 5–7 phases | Complex + context-critical |
 | `:team` | Golden Triangle adversarial collaboration | 5–7 phases × 3 agents each | Maximum quality required |
 
 Special variants exist for some commands:
@@ -167,7 +166,7 @@ Special variants exist for some commands:
 
 From `rules/REFERENCE.md`:
 ```
-| `/cook` | cook.md | fast, hard, focus |
+| `/cook` | cook.md | fast, hard, team |
 | `/deploy` | deploy.md | check, preview, production, rollback |
 ```
 

package/documents/knowledge-architecture/05-decisions.md

@@ -312,7 +312,7 @@ Matrix skills (1,430 across 19 domains) provide a trusted baseline. Dynamic disc
   - 0.10 × Freshness — recency
   - 0.10 × Success Rate — execution history
 - Trust progression prevents untested skills from affecting critical workflows
-- Variant-gated discovery (`:fast` skips, `:hard`/`:focus` may trigger) keeps fast paths fast
+- Variant-gated discovery (`:fast` skips, `:hard`/`:team` may trigger) keeps fast paths fast
 
 ### Trade-offs
 
@@ -322,14 +322,14 @@ Matrix skills (1,430 across 19 domains) provide a trusted baseline. Dynamic disc
 | Community discovery fills gaps automatically | Dynamic skills start untrusted (0.3) |
 | 5-factor scoring balances multiple dimensions | Scoring is interpretive (AI evaluates), not deterministic |
 | Trust progression protects quality | New skills need 10 successful executions to reach VALIDATED |
-| Variant gating preserves fast path performance | Discovery only runs for hard/focus variants |
+| Variant gating preserves fast path performance | Discovery only runs for hard/team variants |
 
 ### Evidence
 
 - `matrix-skills/_index.yaml`: `total_matrix_skills: 1430`, 19 domain files, HSOL config with `async_threshold: 0.8`
 - `rules/SKILLS.md`: Resolution algorithm (6 steps), fitness formula (5 factors with weights), trust lifecycle (4 stages with criteria)
 - `matrix-skills/_dynamic.yaml`: Dynamic skill governance fields (owner, checksum, support_state, promotion_state)
-- `_index.yaml` discovery config: `apply_for_variants: ["hard", "focus"]` — confirms `:fast` skips discovery
+- `_index.yaml` discovery config: `apply_for_variants: ["hard", "team"]` — confirms `:fast` skips discovery
 
 ---
 

package/documents/knowledge-domain/00-index.md

@@ -76,7 +76,7 @@ erDiagram
     COMMAND_VARIANT {
         string filename PK "e.g. cook/fast.md"
         string parent_command FK "cook"
-        string variant_type "fast, hard, focus, team"
+        string variant_type "fast, hard, team"
         int phase_count "Number of phases"
         string agents_used "Agent assignments"
     }

package/documents/knowledge-domain/01-entities.md

@@ -199,15 +199,15 @@ Each team domain folder contains exactly 3 files:
 
 | Command | Slug | Category | Variants |
 |---------|------|----------|----------|
-| /cook | `cook` | engineering | fast, hard, focus, team |
-| /code | `code` | engineering | fast, hard, focus, team |
-| /fix | `fix` | engineering | fast, hard, focus, team |
-| /debug | `debug` | validation | fast, hard, focus, team |
-| /test | `test` | validation | fast, hard, focus, team |
-| /plan | `plan` | planning | fast, hard, focus, team |
-| /design | `design` | design | fast, hard, focus, team |
+| /cook | `cook` | engineering | fast, hard, team |
+| /code | `code` | engineering | fast, hard, team |
+| /fix | `fix` | engineering | fast, hard, team |
+| /debug | `debug` | validation | fast, hard, team |
+| /test | `test` | validation | fast, hard, team |
+| /plan | `plan` | planning | fast, hard, team |
+| /design | `design` | design | fast, hard, team |
 | /review | `review` | validation | fast, hard, team |
-| /report | `report` | support | fast, hard, focus, team |
+| /report | `report` | support | fast, hard, team |
 | /brainstorm | `brainstorm` | research | fast, hard, team |
 | /docs | `docs` | support | core, business, audit |
 | /deploy | `deploy` | devops | check, preview, production, rollback |
@@ -257,7 +257,6 @@ Each variant defines a sequence of phases:
 |------|-------------|-------------|
 | `fast` | cook, code, fix, debug, test, plan, design, report, brainstorm, ask | Minimal phases, quick execution, skip discovery |
 | `hard` | cook, code, fix, debug, test, plan, design, review, report, brainstorm, ask | Full workflow, all phases, full skill resolution |
-| `focus` | cook, code, fix, debug, test, plan, design, report | Hard workflow with enforced context optimization |
 | `team` | cook, code, fix, debug, test, plan, design, review, report, brainstorm | Golden Triangle (3 agents per phase) |
 | `core` | docs | Core documentation workflow |
 | `business` | docs | Business documentation workflow |
@@ -528,7 +527,7 @@ All entry points follow the same pattern:
 | `hsol.discovery.timeout_ms` | integer | `5000` | Discovery timeout in milliseconds |
 | `hsol.discovery.cache_ttl_seconds` | integer | `3600` | Cache time-to-live |
 | `hsol.discovery.async_threshold` | float | `0.8` | Matrix fitness above this skips discovery |
-| `hsol.discovery.apply_for_variants` | string[] | `[hard, focus]` | Variants that trigger discovery |
+| `hsol.discovery.apply_for_variants` | string[] | `[hard, team]` | Variants that trigger discovery |
 | `hsol.trust.new_skill` | float | `0.3` | Initial trust for new skills |
 | `hsol.trust.after_3_executions` | float | `0.5` | Trust after 3 successes |
 | `hsol.trust.after_10_executions` | float | `0.7` | Trust after 10 successes |

package/documents/knowledge-domain/03-api-contracts.md

@@ -208,14 +208,13 @@ The Orchestrator also detects commands from natural language:
 |----------|-------|
 | Purpose | Implement new features end-to-end |
 | Input | Feature description |
-| Variants | `fast`, `hard`, `focus`, `team` |
-| Default routing | Simple spec → fast; Complex → hard; Context-critical → focus; Max quality → team |
+| Variants | `fast`, `hard`, `team` |
+| Default routing | Simple spec → fast; Complex → hard; Max quality → team |
 
 | Variant | Phases | Discovery | Team |
 |---------|--------|-----------|------|
 | `fast` | Minimal (typically 2-3) | Matrix only, skip dynamic | Single agent per phase |
 | `hard` | Full (typically 5-7) | Matrix + dynamic discovery | Single agent per phase |
-| `focus` | Full with context clearing | Matrix + dynamic discovery | Single agent per phase |
 | `team` | Full with Golden Triangle | Matrix + dynamic discovery | 3 agents per phase |
 
 #### `/code` — Code Generation
@@ -224,7 +223,7 @@ The Orchestrator also detects commands from natural language:
 |----------|-------|
 | Purpose | Generate code snippets or modules |
 | Input | Code specification |
-| Variants | `fast`, `hard`, `focus`, `team` |
+| Variants | `fast`, `hard`, `team` |
 | Default routing | Same as `/cook` |
 
 #### `/fix` — Bug Fixing
@@ -233,7 +232,7 @@ The Orchestrator also detects commands from natural language:
 |----------|-------|
 | Purpose | Identify and fix bugs |
 | Input | Bug description or error message |
-| Variants | `fast`, `hard`, `focus`, `team` |
+| Variants | `fast`, `hard`, `team` |
 | Default routing | Clear bug → fast; Complex/multi-component → hard |
 
 #### `/debug` — Debugging
@@ -242,7 +241,7 @@ The Orchestrator also detects commands from natural language:
 |----------|-------|
 | Purpose | Deep investigation of issues |
 | Input | Issue description or symptoms |
-| Variants | `fast`, `hard`, `focus`, `team` |
+| Variants | `fast`, `hard`, `team` |
 | Default routing | Quick investigation → fast; Root cause analysis → hard |
 
 #### `/test` — Test Generation
@@ -251,7 +250,7 @@ The Orchestrator also detects commands from natural language:
 |----------|-------|
 | Purpose | Generate test suites |
 | Input | Component or feature to test |
-| Variants | `fast`, `hard`, `focus`, `team` |
+| Variants | `fast`, `hard`, `team` |
 | Default routing | Unit tests → fast; Full coverage strategy → hard |
 
 #### `/plan` — Planning
@@ -260,7 +259,7 @@ The Orchestrator also detects commands from natural language:
 |----------|-------|
 | Purpose | Create implementation plans and task breakdowns |
 | Input | Feature or project to plan |
-| Variants | `fast`, `hard`, `focus`, `team` |
+| Variants | `fast`, `hard`, `team` |
 | Default routing | Quick plan → fast; Detailed architecture → hard |
 
 #### `/design` — UI/UX Design
@@ -269,7 +268,7 @@ The Orchestrator also detects commands from natural language:
 |----------|-------|
 | Purpose | Design user interfaces and experiences |
 | Input | UI/UX requirements |
-| Variants | `fast`, `hard`, `focus`, `team` |
+| Variants | `fast`, `hard`, `team` |
 | Default routing | Simple component → fast; Full design system → hard |
 
 #### `/review` — Code Review
@@ -287,7 +286,7 @@ The Orchestrator also detects commands from natural language:
 |----------|-------|
 | Purpose | Generate reports and summaries |
 | Input | Topic or scope for report |
-| Variants | `fast`, `hard`, `focus`, `team` |
+| Variants | `fast`, `hard`, `team` |
 | Default routing | Quick summary → fast; Detailed analysis → hard |
 
 #### `/brainstorm` — Ideation
@@ -349,14 +348,14 @@ Execution is blocked until all three are loaded.
 
 ### Variant Behavior Matrix
 
-| Behavior | fast | hard | focus | team |
-|----------|------|------|-------|------|
-| Phase count | Minimal (2-3) | Full (5-7) | Full (5-7) | Full (5-7) |
-| Skill discovery | Matrix only | Matrix + dynamic | Matrix + dynamic | Matrix + dynamic |
-| Context clearing | No | No | Yes (between phases) | No |
-| Agents per phase | 1 | 1 | 1 | 3 (Golden Triangle) |
-| Debate rounds | N/A | N/A | N/A | Up to 3 |
-| Deliverable review | Exit criteria only | Exit criteria | Exit criteria + context check | Consensus stamp required |
+| Behavior | fast | hard | team |
+|----------|------|------|------|
+| Phase count | Minimal (2-3) | Full (5-7) | Full (5-7) |
+| Skill discovery | Matrix only | Matrix + dynamic | Matrix + dynamic |
+| Context clearing | No | No | No |
+| Agents per phase | 1 | 1 | 3 (Golden Triangle) |
+| Debate rounds | N/A | N/A | Up to 3 |
+| Deliverable review | Exit criteria only | Exit criteria | Consensus stamp required |
 
 ---
 
@@ -444,7 +443,6 @@ The HSOL maps agent profiles to skill domains via the `agent_profiles` section i
 |---------|-------------------|
 | `fast` | Skip dynamic discovery entirely — matrix skills only |
 | `hard` | Full resolution — matrix first, dynamic discovery if fitness < 0.8 |
-| `focus` | Same as `hard` — full resolution with dynamic discovery |
 | `team` | Same as `hard` — full resolution with dynamic discovery |
 | Other (core, business, audit, check, etc.) | Standard matrix resolution |
 

package/documents/knowledge-domain/04-business-rules.md

@@ -197,7 +197,6 @@ The superiority delta of 0.15 means a dynamic skill must exceed the best matrix
 |---------|-------------------|
 | `fast` | Always skipped — matrix only |
 | `hard` | Enabled — full resolution |
-| `focus` | Enabled — full resolution |
 | `team` | Enabled — full resolution |
 
 ### Complexity Gate

package/documents/knowledge-overview/00-index.md

@@ -58,7 +58,7 @@ Built with Node.js >=18.0.0 using only built-in modules (fs, path, os, readline)
 | Specialist Agents | 21 |
 | Team Configurations | 17 teams (51 team agents) |
 | Commands | 14 |
-| Command Variants | 4 (fast, hard, focus, team) |
+| Command Variants | 4 (fast, hard, team) |
 | Skill Modules | 1,430+ |
 | Skill Domains | 19 |
 | Rules | 7 |

package/documents/knowledge-overview/01-project-identity.md

@@ -51,7 +51,7 @@ Agent Assistant solves these by:
 1. **Global one-time installation** — Markdown and YAML configurations installed into each AI tool's global directory (`~/.cursor/`, `~/.claude/`, `~/.copilot/`, etc.) apply to all projects automatically.
 2. **Orchestrator pattern** — The AI reads a platform entry file that transforms it into an Orchestrator role. It delegates work to specialist agents rather than attempting everything itself.
 3. **21 specialist agents** — Each with a defined profile, responsibility scope, and skill set. Examples: `backend-engineer`, `tester`, `security-engineer`, `tech-lead`.
-4. **14 structured commands** — `/cook`, `/code`, `/fix`, `/debug`, `/test`, `/plan`, `/design`, `/review`, `/report`, `/brainstorm`, `/docs`, `/deploy`, `/ask`, `/auto` — each with variant strategies (fast, hard, focus, team).
+4. **14 structured commands** — `/cook`, `/code`, `/fix`, `/debug`, `/test`, `/plan`, `/design`, `/review`, `/report`, `/brainstorm`, `/docs`, `/deploy`, `/ask`, `/auto` — each with variant strategies (fast, hard, team).
 5. **Automatic skill injection (HSOL)** — 1,430+ skills across 19 domains resolved by agent profile and request context, with no manual skill selection required.
 6. **Cross-platform parity** — The same workflows and agent definitions work across all 5 supported AI coding tools.
 

package/documents/knowledge-overview/03-features.md

@@ -71,7 +71,7 @@ The Hybrid Skill Orchestration Layer automatically resolves and injects relevant
 5. Calculate fitness scores (semantic match 35%, specificity 25%, trust 20%, freshness 10%, success rate 10%)
 6. Return sorted skill set
 
-**Dynamic discovery**: When matrix fitness score falls below 0.8 for `:hard` or `:focus` variants, the `find-skills` mechanism can discover additional community skills at runtime.
+**Dynamic discovery**: When matrix fitness score falls below 0.8 for `:hard` or `:team` variants, the `find-skills` mechanism can discover additional community skills at runtime.
 
 **Evidence**: [../../rules/SKILLS.md](../../rules/SKILLS.md), [../../matrix-skills/_index.yaml](../../matrix-skills/_index.yaml), [../../matrix-skills/](../../matrix-skills/)
 
@@ -142,7 +142,6 @@ Each command supports up to 4 variants that control scope, agent count, and qual
 |---------|-------|--------|---------------|----------|
 | `:fast` | Minimal | 2–3 | Basic | Simple tasks, quick fixes |
 | `:hard` | Full | 5–8 | Comprehensive (test, review, security) | Complex features, production code |
-| `:focus` | Clean | Variable | Targeted | Focused execution with clean output |
 | `:team` | Adversarial | 3 per team (Golden Triangle) | Debate mechanism | Critical features needing multiple perspectives |
 
 **Evidence**: [../../README.md](../../README.md), [../../commands/cook/](../../commands/cook/)
@@ -204,7 +203,7 @@ Classified error recovery system that prevents silent failures:
 | Specialist Agents | 21 |
 | Team Configurations | 17 (51 team agents) |
 | Commands | 14 |
-| Variants | 4 (fast, hard, focus, team) |
+| Variants | 4 (fast, hard, team) |
 | Skill Modules | 1,430+ |
 | Skill Domains | 19 |
 | Orchestration Rules | 7 files |

package/documents/knowledge-source-base/01-directory-structure.md

@@ -118,27 +118,27 @@ agent-assistant/                          # Project root — npm package @namch/
 │   ├── brainstorm.md                     # /brainstorm command router
 │   ├── brainstorm/                       # fast.md, hard.md, team.md (3 variants)
 │   ├── code.md                           # /code command router
-│   ├── code/                             # fast.md, focus.md, hard.md, team.md (4 variants)
+│   ├── code/                             # fast.md, hard.md, team.md (4 variants)
 │   ├── cook.md                           # /cook command router
-│   ├── cook/                             # fast.md, focus.md, hard.md, team.md (4 variants)
+│   ├── cook/                             # fast.md, hard.md, team.md (4 variants)
 │   ├── debug.md                          # /debug command router
-│   ├── debug/                            # fast.md, focus.md, hard.md, team.md (4 variants)
+│   ├── debug/                            # fast.md, hard.md, team.md (4 variants)
 │   ├── deploy.md                         # /deploy command router
 │   ├── deploy/                           # check.md, preview.md, production.md, rollback.md (4 variants)
 │   ├── design.md                         # /design command router
-│   ├── design/                           # fast.md, focus.md, hard.md, team.md (4 variants)
+│   ├── design/                           # fast.md, hard.md, team.md (4 variants)
 │   ├── docs.md                           # /docs command router
 │   ├── docs/                             # audit.md, business.md, core.md (3 variants)
 │   ├── fix.md                            # /fix command router
-│   ├── fix/                              # fast.md, focus.md, hard.md, team.md (4 variants)
+│   ├── fix/                              # fast.md, hard.md, team.md (4 variants)
 │   ├── plan.md                           # /plan command router
-│   ├── plan/                             # fast.md, focus.md, hard.md, team.md (4 variants)
+│   ├── plan/                             # fast.md, hard.md, team.md (4 variants)
 │   ├── report.md                         # /report command router
-│   ├── report/                           # fast.md, focus.md, hard.md, team.md (4 variants)
+│   ├── report/                           # fast.md, hard.md, team.md (4 variants)
 │   ├── review.md                         # /review command router
 │   ├── review/                           # fast.md, hard.md, team.md (3 variants)
 │   ├── test.md                           # /test command router
-│   └── test/                             # fast.md, focus.md, hard.md, team.md (4 variants)
+│   └── test/                             # fast.md, hard.md, team.md (4 variants)
 │
 ├── documents/                            # Project documentation
 │   ├── HSOL-ASSESSMENT.md                # Assessment of HSOL system
@@ -228,7 +228,7 @@ The only directory containing executable code. Houses `install.js` (~600 lines,
 Contains 5 subdirectories, one per supported AI coding tool. Each provides platform-specific assets (entry point files, config files, rule files) that are copied during installation. The CLI reads from these directories to customize the installation for each platform's directory structure and file conventions.
 
 ### `commands/` — Command Workflows
-Contains 14 command router files (`.md`) at the top level and corresponding subdirectories with variant strategies. Standard variants are `fast.md`, `focus.md`, `hard.md`, `team.md`; deploy uses `check.md`, `preview.md`, `production.md`, `rollback.md`; docs uses `audit.md`, `business.md`, `core.md`. The command router file defines the base workflow, and variants modify execution strategy. Total: 61 Markdown files.
+Contains 14 command router files (`.md`) at the top level and corresponding subdirectories with variant strategies. Standard variants are `fast.md`, `hard.md`, `team.md`; deploy uses `check.md`, `preview.md`, `production.md`, `rollback.md`; docs uses `audit.md`, `business.md`, `core.md`. The command router file defines the base workflow, and variants modify execution strategy. Total: 61 Markdown files.
 
 ### `documents/` — Project Documentation
 Stores long-form project documentation including the HSOL design blueprint, HSOL assessment, and the knowledge source base (this folder). Files here are included in the npm package and copied during installation to `~/.{tool}/skills/agent-assistant/documents/`.

package/documents/knowledge-source-base/03-key-modules.md

@@ -205,24 +205,23 @@ Implements the command routing system — the primary user-facing interface. Use
 | `ask.md` | `ask/` | `fast`, `hard` |
 | `auto.md` | — | (no variants) |
 | `brainstorm.md` | `brainstorm/` | `fast`, `hard`, `team` |
-| `code.md` | `code/` | `fast`, `focus`, `hard`, `team` |
-| `cook.md` | `cook/` | `fast`, `focus`, `hard`, `team` |
-| `debug.md` | `debug/` | `fast`, `focus`, `hard`, `team` |
+| `code.md` | `code/` | `fast`, `hard`, `team` |
+| `cook.md` | `cook/` | `fast`, `hard`, `team` |
+| `debug.md` | `debug/` | `fast`, `hard`, `team` |
 | `deploy.md` | `deploy/` | `check`, `preview`, `production`, `rollback` |
-| `design.md` | `design/` | `fast`, `focus`, `hard`, `team` |
+| `design.md` | `design/` | `fast`, `hard`, `team` |
 | `docs.md` | `docs/` | `audit`, `business`, `core` |
-| `fix.md` | `fix/` | `fast`, `focus`, `hard`, `team` |
-| `plan.md` | `plan/` | `fast`, `focus`, `hard`, `team` |
-| `report.md` | `report/` | `fast`, `focus`, `hard`, `team` |
+| `fix.md` | `fix/` | `fast`, `hard`, `team` |
+| `plan.md` | `plan/` | `fast`, `hard`, `team` |
+| `report.md` | `report/` | `fast`, `hard`, `team` |
 | `review.md` | `review/` | `fast`, `hard`, `team` |
-| `test.md` | `test/` | `fast`, `focus`, `hard`, `team` |
+| `test.md` | `test/` | `fast`, `hard`, `team` |
 
 **Variant Pattern Categories**:
 
 | Pattern | Variants | Used By |
 |---------|----------|---------|
-| Standard (4 variants) | `fast`, `focus`, `hard`, `team` | code, cook, debug, design, fix, plan, report, test |
-| Standard-3 (no focus) | `fast`, `hard`, `team` | brainstorm, review |
+| Standard-3 | `fast`, `hard`, `team` | code, cook, debug, design, fix, plan, report, test, brainstorm, review |
 | Minimal (2 variants) | `fast`, `hard` | ask |
 | Deploy-specific | `check`, `preview`, `production`, `rollback` | deploy |
 | Docs-specific | `audit`, `business`, `core` | docs |
@@ -310,7 +309,7 @@ HSOL Resolution Flow:
 
 | File | Purpose |
 |------|---------|
-| `_index.yaml` | Master HSOL configuration v1.1: enables HSOL, sets discovery parameters, defines `find-skills` integration commands, configures async threshold (0.8), variant applicability (`hard`, `focus` only — `fast` skips discovery) |
+| `_index.yaml` | Master HSOL configuration v1.1: enables HSOL, sets discovery parameters, defines `find-skills` integration commands, configures async threshold (0.8), variant applicability (`hard`, `team` only — `fast` skips discovery) |
 | `_dynamic.yaml` | Manifest for community-installed skills added via `npx skills add` |
 | 19 domain `.yaml` files | Pre-curated skill registries mapped to agent profiles |
 
@@ -345,7 +344,7 @@ HSOL Resolution Flow:
 | `version` | 1.1 | HSOL protocol version |
 | `total_matrix_skills` | 1,430 | Total pre-curated skills |
 | `async_threshold` | 0.8 | Matrix fitness above this skips dynamic discovery |
-| `apply_for_variants` | `["hard", "focus"]` | Dynamic discovery only runs for these variants |
+| `apply_for_variants` | `["hard", "team"]` | Dynamic discovery only runs for these variants |
 | `timeout_ms` | 5,000 | Discovery timeout |
 | `cache_ttl_seconds` | 3,600 | Discovery cache duration |
 | `find-skills` CLI commands | `npx skills find`, `npx skills add`, `npx skills check`, `npx skills update` | External skill service integration |

package/documents/knowledge-source-base/04-configuration.md

@@ -223,7 +223,7 @@ The central config for the Hybrid Skill Orchestration Layer:
 | `hsol.discovery.timeout_ms` | `5000` | Discovery request timeout |
 | `hsol.discovery.cache_ttl_seconds` | `3600` | Cache duration (1 hour) |
 | `hsol.discovery.async_threshold` | `0.8` | Skip discovery if matrix fitness exceeds this |
-| `hsol.discovery.apply_for_variants` | `["hard", "focus"]` | Only run discovery for these variants; `fast` skips it |
+| `hsol.discovery.apply_for_variants` | `["hard", "team"]` | Only run discovery for these variants; `fast` skips it |
 
 ### matrix-skills/_dynamic.yaml
 

package/documents/knowledge-standards/02-conventions.md

@@ -27,7 +27,6 @@ agent-assistant/
 │   └── cook/                # Variant subdirectory
 │       ├── fast.md
 │       ├── hard.md
-│       ├── focus.md
 │       └── team.md
 ├── documents/               # Project knowledge base
 │   ├── knowledge-overview/

package/matrix-skills/_index.yaml

@@ -56,7 +56,7 @@ hsol:
     cache_ttl_seconds: 3600
     async_threshold: 0.8  # Matrix fitness above this skips discovery
     # Only run dynamic discovery (find-skills) for these variants; "fast" skips discovery so fast stays fast
-    apply_for_variants: ["hard", "focus"]
+    apply_for_variants: ["hard", "team"]
     
   # Fitness scoring weights
   fitness_weights:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@namch/agent-assistant",
-  "version": "1.3.1",
+  "version": "1.3.2",
   "description": "Multi-agent orchestration framework for AI coding assistants (Cursor, Copilot, Antigravity, Claude Code, Codex) with Hybrid Skill Orchestration Layer (HSOL).",
   "main": "cli/install.js",
   "bin": {

package/rules/AGENTS.md

@@ -142,7 +142,7 @@ result:
 
 | When | Use |
 |------|-----|
-| Standard `:fast`, `:hard`, `:focus` variants | Single agent per phase |
+| Standard `:fast`, `:hard` variants | Single agent per phase |
 | `:team` variant | Golden Triangle per phase |
 | User explicitly requests team review/collaboration | `:team` variant |
 | Maximum quality with adversarial debate is priority | `:team` variant |

package/rules/REFERENCE.md

@@ -8,19 +8,19 @@
 
 | Command | Router | Variants |
 |---------|--------|----------|
-| `/cook` | `cook.md` | `fast`, `hard`, `focus` |
-| `/fix` | `fix.md` | `fast`, `hard`, `focus` |
-| `/plan` | `plan.md` | `fast`, `hard`, `focus` |
-| `/debug` | `debug.md` | `fast`, `hard`, `focus` |
-| `/test` | `test.md` | `fast`, `hard`, `focus` |
+| `/cook` | `cook.md` | `fast`, `hard`, `team` |
+| `/fix` | `fix.md` | `fast`, `hard`, `team` |
+| `/plan` | `plan.md` | `fast`, `hard`, `team` |
+| `/debug` | `debug.md` | `fast`, `hard`, `team` |
+| `/test` | `test.md` | `fast`, `hard`, `team` |
 | `/review` | `review.md` | `fast`, `hard` |
 | `/docs` | `docs.md` | `core`, `business`, `audit` |
-| `/design` | `design.md` | `fast`, `hard`, `focus` |
+| `/design` | `design.md` | `fast`, `hard`, `team` |
 | `/deploy` | `deploy.md` | `check`, `preview`, `production`, `rollback` |
-| `/report` | `report.md` | `fast`, `hard`, `focus` |
+| `/report` | `report.md` | `fast`, `hard`, `team` |
 | `/brainstorm` | `brainstorm.md` | `fast`, `hard` |
 | `/ask` | `ask.md` | `fast`, `hard` |
-| `/code` | `code.md` | `fast`, `hard`, `focus` |
+| `/code` | `code.md` | `fast`, `hard`, `team` |
 
 ---
 

package/rules/SKILLS.md

@@ -61,7 +61,7 @@ Dynamic skills: trust = 0.3 - 1.0 (based on history)
 | Variant | Discovery |
 |---------|----------|
 | `fast` | **Skip** — use matrix only |
-| `hard`, `focus` | Check matrix fitness, may trigger discovery |
+| `hard`, `team` | Check matrix fitness, may trigger discovery |
 
 ### By Matrix Fitness