@namch/agent-assistant 1.3.1 → 1.3.2

package/CHANGELOG.md

@@ -5,6 +5,19 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.3.2] - 2026-03-30
+
+### Removed
+- **Focus workflow variant deprecation (complete)**:
+  - Removed remaining focus workflow files and command-level focus routing references.
+  - Removed focus variant mentions from active command metadata and workflow documentation.
+  - Removed stale focus references from business analysis docs that still listed `fast/hard/focus/team`.
+
+### Changed
+- **Changelog and docs normalization after focus cleanup**:
+  - Updated changelog wording to avoid legacy focus workflow terminology in active release notes.
+  - Kept accessibility/UI focus semantics (e.g., `:focus`, `:focus-visible`) untouched where they are unrelated to command variants.
+
 ## [1.3.1] - 2026-03-26
 
 ### Changed

package/README.md

@@ -22,7 +22,7 @@ Transform one AI into a coordinated team of 21 specialist agents with structured
 | **One-Time Setup, Forever Use** | Configure once at global level (`~/.cursor/`, `~/.claude/`, etc.) and it auto-applies to ALL your projects. No more repetitive config for every new repo.                                      |
 | **Sub-Agent Orchestration**     | When supported (Claude Code, Cursor Max mode), the main agent spawns specialized sub-agents to handle tasks **in parallel** — backend, frontend, testing, security all working simultaneously. |
 | **Multi-Platform Support**      | Works seamlessly across **Cursor**, **GitHub Copilot**, **Claude Code**, **Codex**, and **Antigravity/Gemini**. Same workflows, any tool.                                                                 |
-| **Matrix Skill Discovery (HSOL)** | Injects the right skills by profile and request; optional dynamic discovery (find-skills) for `hard`/`focus` when matrix fitness < 0.8. 1400+ matrix skills, zero manual config. |
+| **Matrix Skill Discovery (HSOL)** | Injects the right skills by profile and request; optional dynamic discovery (find-skills) for `hard`/`team` when matrix fitness < 0.8. 1400+ matrix skills, zero manual config. |
 
 ### The Goal
 
@@ -140,7 +140,6 @@ Creates `./documents/` files that agents reference. Without docs, agents work ge
 | ------- | ---------------- | -------------------------- |
 | `:fast` | Simple tasks     | 2-3 agents                 |
 | `:hard` | Complex features | 5-8 agents + quality gates |
-| `:focus` | Clean execution | (cook, code, fix, debug, design, plan, test, report) |
 | `:team` | Team workflows   | All agents, structured phases |
 
 ## Commands Reference
@@ -151,7 +150,7 @@ Creates `./documents/` files that agents reference. Without docs, agents work ge
 | **Quality** | `/test`, `/review`, `/debug`                             |
 | **Plan**    | `/plan`, `/brainstorm`, `/design`                        |
 | **Docs**    | `/docs:core`, `/docs:business`, `/docs:audit`            |
-| **Report**  | `/report:fast`, `/report:hard`, `/report:focus`           |
+| **Report**  | `/report:fast`, `/report:hard`, `/report:team`           |
 | **Deploy**  | `/deploy:check`, `/deploy:preview`, `/deploy:production` |
 
 ---
@@ -188,7 +187,7 @@ profile: "backend:execution"
 ```
 agent-assistant/
 ├── agents/          # 21 specialist agents
-├── commands/        # 50+ workflow commands (routers + variants: fast, hard, focus)
+├── commands/        # 50+ workflow commands (routers + variants: fast, hard, team)
 ├── rules/           # 8 orchestration rules
 ├── matrix-skills/   # 19 domain skill registries
 ├── skills/          # 1400+ domain skills

package/code-assistants/codex-assistant/CODEX.md

@@ -133,9 +133,8 @@ Append `:variant` to any command for specialized workflows:
 | `:hard` | `commands/{cmd}/hard.md` | Complex/deep variant |
 | `:fast` | `commands/{cmd}/fast.md` | Quick/lightweight variant |
 | `:team` | `commands/{cmd}/team.md` | Parallel multi-agent team |
-| `:focus` | `commands/{cmd}/focus.md` | Focused single-concern variant |
 
-**Examples**: `/cook:hard`, `/fix:fast`, `/review:team`, `/plan:focus`
+**Examples**: `/cook:hard`, `/fix:fast`, `/review:team`, `/plan:team`
 
 **Team variant baseline**: `:team` is supported only where `commands/{cmd}/team.md` exists. Deploy uses specialized variants (`check`, `preview`, `production`, `rollback`).
 

package/commands/ask/hard.md

@@ -23,7 +23,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/brainstorm/hard.md

@@ -23,7 +23,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/code/hard.md

@@ -23,7 +23,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/code.md

@@ -29,7 +29,7 @@ execution-mode: router
 
 ```
 IF user references an existing plan (@plan, @PLAN-..., path to PLAN-*.md, or "according to plan" / "follow the plan"):
-  → Route to /code:hard or /code:focus (workflow will SKIP research, scout, brainstorm and go straight to implementation)
+  → Route to /code:hard (workflow will SKIP research, scout, brainstorm and go straight to implementation)
 
 IF task is simple (clear requirements, single file):
   → Route to /code:fast
@@ -37,9 +37,6 @@ IF task is simple (clear requirements, single file):
 IF task is complex (multi-file, research needed):
   → Route to /code:hard
 
-IF task is complex AND context optimization is critical:
-  → Route to /code:focus
-
 IF task is complex AND maximum quality with team collaboration needed:
   → Route to /code:team
 
@@ -55,7 +52,6 @@ IF unsure:
 | ------------- | ------------------------------------------------------- |
 | `/code:fast`  | Quick implementation, clear requirements                |
 | `/code:hard`  | Complex features, multi-file changes                    |
-| `/code:focus` | Complex features with **enforced context optimization** |
 | `/code:team`  | Maximum quality with parallel agent team collaboration |
 
 ---
@@ -71,8 +67,7 @@ IF unsure:
 
 1. ⚡ **Fast** → `/code:fast` — Quick implementation
 2. ⚡⚡⚡ **Hard** → `/code:hard` — Full development cycle
-3. 🎯 **Focus** → `/code:focus` — Full cycle with **automatic context clearing** (prevents hallucination)
-4. 👥 **Team** → `/code:team` — Full team collaboration (parallel agents, maximum quality)
+3. 👥 **Team** → `/code:team` — Full team collaboration (parallel agents, maximum quality)
 
 ⏳ Awaiting selection...
 ```

package/commands/cook/hard.md

@@ -23,7 +23,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/cook.md

@@ -34,9 +34,6 @@ IF feature is simple (clear spec, low complexity):
 IF feature is complex (multi-component, research needed):
   → Route to /cook:hard
 
-IF feature is complex AND context optimization is critical:
-  → Route to /cook:focus
-
 IF feature is complex AND maximum quality with team collaboration needed:
   → Route to /cook:team
 
@@ -52,7 +49,6 @@ IF unsure:
 | ------------- | ------------------------------------------------------- |
 | `/cook:fast`  | Quick features, clear specifications                    |
 | `/cook:hard`  | Complex features, full workflow                         |
-| `/cook:focus` | Complex features with **enforced context optimization** |
 | `/cook:team`  | Maximum quality with parallel agent team collaboration |
 
 ---
@@ -68,8 +64,7 @@ IF unsure:
 
 1. ⚡ **Fast** → `/cook:fast` — Quick implementation
 2. ⚡⚡⚡ **Hard** → `/cook:hard` — Full feature development
-3. 🎯 **Focus** → `/cook:focus` — Full development with **automatic context clearing** (prevents hallucination)
-4. 👥 **Team** → `/cook:team` — Full team collaboration (parallel agents, maximum quality)
+3. 👥 **Team** → `/cook:team` — Full team collaboration (parallel agents, maximum quality)
 
 ⏳ Awaiting selection...
 ```

package/commands/debug/hard.md

@@ -23,7 +23,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/debug.md

@@ -33,9 +33,6 @@ IF issue is simple (clear error, reproducible):
 IF issue is complex (intermittent, unclear cause):
   → Route to /debug:hard
 
-IF issue is complex AND clean fix handoff is critical:
-  → Route to /debug:focus
-
 IF issue is complex AND maximum quality with team collaboration needed:
   → Route to /debug:team
 
@@ -51,7 +48,6 @@ IF unsure:
 | --------------- | ---------------------------------------------------- |
 | `/debug:fast`   | Quick diagnosis for simple bugs                      |
 | `/debug:hard`   | Deep investigation for complex issues                |
-| `/debug:focus` | Deep investigation with **enforced context optimization** |
 | `/debug:team`  | Maximum quality with parallel agent team collaboration |
 
 ---
@@ -67,8 +63,7 @@ IF unsure:
 
 1. ⚡ **Fast** → `/debug:fast` — Quick diagnosis
 2. ⚡⚡⚡ **Hard** → `/debug:hard` — Deep investigation
-3. 🔒 **Focus** → `/debug:focus` — Deep investigation with **automatic context clearing** (clean fix handoff)
-4. 👥 **Team** → `/debug:team` — Full team collaboration (parallel agents, maximum quality)
+3. 👥 **Team** → `/debug:team` — Full team collaboration (parallel agents, maximum quality)
 
 ⏳ Awaiting selection...
 ```

package/commands/design/hard.md

@@ -23,7 +23,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/design.md

@@ -34,9 +34,6 @@ IF design is simple (component, quick mockup):
 IF design is complex (full feature, system):
   → Route to /design:hard
 
-IF design is complex AND clean implementation handoff is critical:
-  → Route to /design:focus
-
 IF design is complex AND maximum quality with team collaboration needed:
   → Route to /design:team
 
@@ -52,7 +49,6 @@ IF unsure:
 | --------------- | -------------------------------------------------- |
 | `/design:fast`  | Quick component design, simple UI                  |
 | `/design:hard`  | Full feature design, system design                 |
-| `/design:focus` | Full design with **enforced context optimization** |
 | `/design:team`  | Maximum quality with parallel agent team collaboration |
 
 ---
@@ -68,8 +64,7 @@ IF unsure:
 
 1. ⚡ **Fast** → `/design:fast` — Quick design
 2. ⚡⚡⚡ **Hard** → `/design:hard` — Full design process
-3. 🎯 **Focus** → `/design:focus` — Full design with **automatic context clearing** (clean implementation handoff)
-4. 👥 **Team** → `/design:team` — Full team collaboration (parallel agents, maximum quality)
+3. 👥 **Team** → `/design:team` — Full team collaboration (parallel agents, maximum quality)
 
 ⏳ Awaiting selection...
 ```

package/commands/fix/hard.md

@@ -22,7 +22,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/fix.md

@@ -34,9 +34,6 @@ IF issue is simple (clear cause, quick fix):
 IF issue is complex (research needed, multi-file):
   → Route to /fix:hard
 
-IF issue is complex AND context optimization is critical:
-  → Route to /fix:focus
-
 IF issue is complex AND maximum quality with team collaboration needed:
   → Route to /fix:team
 
@@ -52,7 +49,6 @@ IF unsure:
 | ------------ | ----------------------------------------------------- |
 | `/fix:fast`  | Quick fixes, clear issues                             |
 | `/fix:hard`  | Complex issues, research needed                       |
-| `/fix:focus` | Complex issues with **enforced context optimization** |
 | `/fix:team`  | Maximum quality with parallel agent team collaboration |
 
 ---
@@ -68,8 +64,7 @@ IF unsure:
 
 1. ⚡ **Fast** → `/fix:fast` — Quick fix
 2. ⚡⚡⚡ **Hard** → `/fix:hard` — Full resolution
-3. 🎯 **Focus** → `/fix:focus` — Full resolution with **automatic context clearing** (prevents hallucination)
-4. 👥 **Team** → `/fix:team` — Full team collaboration (parallel agents, maximum quality)
+3. 👥 **Team** → `/fix:team` — Full team collaboration (parallel agents, maximum quality)
 
 ⏳ Awaiting selection...
 ```

package/commands/plan/hard.md

@@ -23,7 +23,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/plan.md

@@ -34,9 +34,6 @@ IF task is clear (known approach, codebase-only):
 IF task is complex (research needed, architectural):
   → Route to /plan:hard
 
-IF task is complex AND clean implementation handoff is critical:
-  → Route to /plan:focus
-
 IF task is complex AND maximum quality with team collaboration needed:
   → Route to /plan:team
 
@@ -52,7 +49,6 @@ IF unsure:
 | ------------- | ---------------------------------------------------- |
 | `/plan:fast`  | Quick planning without research                      |
 | `/plan:hard`  | Full planning with research                          |
-| `/plan:focus` | Full planning with **enforced context optimization** |
 | `/plan:team`  | Maximum quality with parallel agent team collaboration |
 
 ---
@@ -68,8 +64,7 @@ IF unsure:
 
 1. ⚡ **Fast** → `/plan:fast` — Quick plan
 2. ⚡⚡⚡ **Hard** → `/plan:hard` — Full research-backed plan
-3. 🎯 **Focus** → `/plan:focus` — Full plan with **automatic context clearing** (clean implementation handoff)
-4. 👥 **Team** → `/plan:team` — Full team collaboration (parallel agents, maximum quality)
+3. 👥 **Team** → `/plan:team` — Full team collaboration (parallel agents, maximum quality)
 
 ⏳ Awaiting selection...
 ```

package/commands/report/fast.md

@@ -10,7 +10,7 @@ execution-mode: execute
 > **MISSION**: Generate concise, actionable status reports and summaries.
 >
 > Use for daily standups, progress checks, and high-level overviews.
-> For **update existing files** or **generate from template**, use `/report:hard` or `/report:focus`.
+> For **update existing files** or **generate from template**, use `/report:hard` or `/report:team`.
 
 <task>$ARGUMENTS</task>
 
@@ -61,7 +61,7 @@ One phase at a time, each phase independent: Phase 1 → then Phase 2 → … in
 | Agent | `reporter`                                                                 |
 | ----- | -------------------------------------------------------------------------- |
 | Goal  | Infer intent; if **create report** → generate concise status report        |
-| Exit  | Report with Summary, Key Changes, Next Steps — or recommend `/report:hard`/`/report:focus` if user intent is update/template |
+| Exit  | Report with Summary, Key Changes, Next Steps — or recommend `/report:hard`/`/report:team` if user intent is update/template |
 
 ---
 

package/commands/report/hard.md

@@ -25,7 +25,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/report.md

@@ -50,11 +50,8 @@ IF task is simple status update OR summary:
 IF task is comprehensive analysis OR deep dive OR any non-trivial topic (infer from request):
   → Route to /report:hard
 
-IF task requires absolute context clarity OR "clean slate" analysis:
-  → Route to /report:focus
-
 IF user explicitly asks to UPDATE existing files (not create report):
-  → Still use /report:hard or /report:focus; reporter OUTPUT MODE = update existing files
+  → Use /report:hard or /report:team; reporter OUTPUT MODE = update existing files
 
 IF task is complex AND maximum quality with team collaboration needed:
   → Route to /report:team
@@ -71,7 +68,6 @@ IF unsure:
 | --------------- | --------------------------------------------------------------------------- |
 | `/report:fast`  | Quick status updates, daily summaries                                       |
 | `/report:hard`  | Detailed analysis, any topic (algorithms, docs, changes), template-based  |
-| `/report:focus` | Deep analysis with **enforced context optimization**; update or create      |
 | `/report:team`  | Maximum quality with parallel agent team collaboration |
 
 ---
@@ -87,8 +83,7 @@ IF unsure:
 
 1. ⚡ **Fast** → `/report:fast` — Quick summary
 2. ⚡⚡⚡ **Hard** → `/report:hard` — Full analysis, any topic; create report **or** update existing files / use template
-3. 🎯 **Focus** → `/report:focus` — Deep analysis with **automatic context clearing**; create or update per task
-4. 👥 **Team** → `/report:team` — Full team collaboration (parallel agents, maximum quality)
+3. 👥 **Team** → `/report:team` — Full team collaboration (parallel agents, maximum quality)
 
 ⏳ Awaiting selection...
 ```

package/commands/review/hard.md

@@ -22,7 +22,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/test/hard.md

@@ -23,7 +23,7 @@ execution-mode: execute
 
 **⛔ Do not run Phase 1 until all are loaded.** Follow **all** rules in those files; they override any conflicting instructions in this file.
 
-**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/focus variants enable find-skills).
+**Skills Resolution**: When delegating, load `SKILLS.md` on-demand for fitness calculation and dynamic discovery (hard/team variants enable find-skills).
 
 ---
 

package/commands/test.md

@@ -33,9 +33,6 @@ IF scope is limited (unit tests, quick check):
 IF scope is comprehensive (full suite, E2E):
   → Route to /test:hard
 
-IF scope is comprehensive AND clean execution focus is critical:
-  → Route to /test:focus
-
 IF scope is comprehensive AND maximum quality with team collaboration needed:
   → Route to /test:team
 
@@ -51,7 +48,6 @@ IF unsure:
 | -------------- | -------------------------------------------------- |
 | `/test:fast`   | Quick tests, unit tests                            |
 | `/test:hard`   | Full test suite, E2E                               |
-| `/test:focus` | Full testing with **enforced context optimization** |
 | `/test:team`  | Maximum quality with parallel agent team collaboration |
 
 ---
@@ -67,8 +63,7 @@ IF unsure:
 
 1. ⚡ **Fast** → `/test:fast` — Quick tests
 2. ⚡⚡⚡ **Hard** → `/test:hard` — Comprehensive testing
-3. 🔒 **Focus** → `/test:focus` — Comprehensive testing with **automatic context clearing** (focused execution)
-4. 👥 **Team** → `/test:team` — Full team collaboration (parallel agents, maximum quality)
+3. 👥 **Team** → `/test:team` — Full team collaboration (parallel agents, maximum quality)
 
 ⏳ Awaiting selection...
 ```

package/documents/HSOL-ASSESSMENT.md

@@ -11,7 +11,7 @@
 | Dimension | Rating | Notes |
 |-----------|--------|--------|
 | **Completeness** | Strong | Resolution algorithm, decision gate, blocking/async, variant/fitness, trust, conflict, edge cases are defined. |
-| **Consistency** | Strong | Thresholds (0.75, 0.8), variant (fast/hard/focus), and flow align across Discovery, Orchestration, _index.yaml, Blueprint. |
+| **Consistency** | Strong | Thresholds (0.75, 0.8), variant (fast/hard/team), and flow align across Discovery, Orchestration, _index.yaml, Blueprint. |
 | **Production readiness** | Good | Clear rules for tool scope, install commands, fallbacks; a few operational gaps (see below). |
 | **Agent intelligence** | Strong | Matrix-first + dynamic enhancement, blocking when matrix insufficient so current task uses new skill; async when matrix adequate. |
 
@@ -28,9 +28,9 @@
 
 2. **Variant + fitness logic**
    - Fast → no discovery (keeps fast path low-latency).
-   - Hard/Focus + fitness ≥ 0.8 → skip discovery.
-   - Hard/Focus + 0.75 ≤ fitness < 0.8 → async (recommend for next time).
-   - Hard/Focus + fitness < 0.75 → blocking (current task uses new skill). Aligns with “skill for current work” goal.
+   - Hard/Team + fitness ≥ 0.8 → skip discovery.
+   - Hard/Team + 0.75 ≤ fitness < 0.8 → async (recommend for next time).
+   - Hard/Team + fitness < 0.75 → blocking (current task uses new skill). Aligns with “skill for current work” goal.
 
 3. **Tool-scoped behavior**
    - All install/verify actions are for the **current tool only**; `-g -y` and no cross-tool install unless user asks. Reduces confusion and errors.
@@ -78,7 +78,7 @@
 
 ### 5. Default variant (optional)
 
-**Issue**: When user says `/cook` without `:fast` or `:hard`, the router picks a default. Discovery runs only for hard/focus. If the default is “hard”, discovery applies; if “fast”, it does not. Not ambiguous but could be explicit.
+**Issue**: When user says `/cook` without `:fast` or `:hard`, the router picks a default. Discovery runs only for hard/team. If the default is “hard”, discovery applies; if “fast”, it does not. Not ambiguous but could be explicit.
 
 **Suggestion**: In SKILL-DISCOVERY or SKILL-ORCHESTRATION, one line: “When command has no variant, use the router’s default (e.g. hard for full workflows); discovery eligibility follows that variant.” Optional.
 
@@ -96,7 +96,7 @@
 - **Install flow**: Commands, scope (current tool), and confirm rules are clear.
 - **Fallbacks**: Timeout, no skills, install failure are handled.
 - **Config**: _index.yaml has discovery on/off, thresholds, variants, promotion; per-agent overrides exist.
-- **Cross-doc alignment**: Thresholds (0.75, 0.8), variant list (hard, focus), and flow (blocking vs async) match across docs and config.
+- **Cross-doc alignment**: Thresholds (0.75, 0.8), variant list (hard, team), and flow (blocking vs async) match across docs and config.
 
 ---
 

package/documents/SMART-SKILL-ORCHESTRATION-BLUEPRINT.md

@@ -263,7 +263,7 @@ ROOT CAUSE: No automated feedback loop between:
 > **Blocking** (matrix fitness < 0.75): Wait for discovery → install → re-inject → **then** execute. Purpose: new skill is **used for the current task** — best completion for this request. **Async** (fitness 0.75–0.8): Do not wait; execute with matrix; when discovery returns only surface recommendation for **next time**. Async does not improve accuracy for the current task.
 
 **Principle 2b: Conditional Discovery (Variant + Fitness)**
-> Dynamic discovery (find-skills, steps 8–10) runs **only** when: (1) command variant is **`hard`** or **`focus`** — **`fast`** skips discovery so fast stays fast; (2) best matrix fitness **< 0.8** — if matrix already has a highly suitable skill (e.g. 9–10), skip discovery. So: fast flow → steps 1–7 + execute; hard/focus + matrix sufficient → same; hard/focus + matrix < 0.8 → full flow including discovery.
+> Dynamic discovery (find-skills, steps 8–10) runs **only** when: (1) command variant is **`hard`** or **`team`** — **`fast`** skips discovery so fast stays fast; (2) best matrix fitness **< 0.8** — if matrix already has a highly suitable skill (e.g. 9–10), skip discovery. So: fast flow → steps 1–7 + execute; hard/team + matrix sufficient → same; hard/team + matrix < 0.8 → full flow including discovery.
 
 **Principle 3: Graduated Trust**
 > Newly discovered skills start in "evaluation mode" with limited scope. Trust increases with successful executions.

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

@@ -82,15 +82,15 @@
 
 ---
 
-### BF-006 — 4 Variant Strategies
+### BF-006 — 3 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).
+**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/focus.md`, `commands/cook/team.md` (pattern repeated per command)
+**Key Files**: `commands/cook/fast.md`, `commands/cook/hard.md`, `commands/cook/team.md`, `commands/cook/team.md` (pattern repeated per command)
 
 ---
 
@@ -170,7 +170,7 @@
 
 ### 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`.
+**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.
 
@@ -286,7 +286,7 @@
 
 **Goal Mapping**: BG-003 (Speed)
 
-**Key Files**: `commands/code.md` (routing), `commands/code/hard.md`, `commands/code/focus.md` (skip logic)
+**Key Files**: `commands/code.md` (routing), `commands/code/hard.md`, `commands/code/team.md` (skip logic)
 
 ---
 

package/documents/business/business-features/03-feature-specifications.md

@@ -124,9 +124,9 @@ Each feature specification includes:
 
 ---
 
-### BF-006 — 4 Variant Strategies
+### BF-006 — 3 Variant Strategies
 
-**Description**: `:fast` (2–3 agents), `:hard` (5–8 agents + gates), `:focus` (clean execution), `:team` (adversarial Golden Triangle).
+**Description**: `:fast` (2–3 agents), `:hard` (5–8 agents + gates), `:team` (adversarial Golden Triangle).
 
 **Acceptance Criteria**:
 
@@ -134,11 +134,10 @@ Each feature specification includes:
 |---|-------|------|------|
 | AC-1 | `/cook` command issued | User specifies `:fast` | 2–3 agents execute with basic quality gates |
 | AC-2 | `/cook` command issued | User specifies `:hard` | 5–8 agents execute with test, review, and security gates |
-| AC-3 | `/cook` command issued | User specifies `:focus` | Context optimization runs; clean focused output produced |
-| AC-4 | `/cook` command issued | User specifies `:team` | Golden Triangle team (Tech Lead + Executor + Reviewer) with debate |
+| AC-3 | `/cook` command issued | User specifies `:team` | Golden Triangle team (Tech Lead + Executor + Reviewer) with debate |
 
 **Technical Surface**:
-- `commands/cook/fast.md`, `commands/cook/hard.md`, `commands/cook/focus.md`, `commands/cook/team.md`
+- `commands/cook/fast.md`, `commands/cook/hard.md`, `commands/cook/team.md`
 - Pattern replicated for each command supporting variants
 
 **Dependencies**: BF-005 (command router)
@@ -156,7 +155,7 @@ Each feature specification includes:
 | AC-1 | Agent has profile with backend domain | HSOL resolves skills | Backend-relevant skills from `matrix-skills/backend.yaml` are injected |
 | AC-2 | 19 domain YAML files exist | HSOL resolution runs | All domains are searchable; `_index.yaml` is the entry point |
 | AC-3 | Fitness score computed | Score >= 0.8 | Skill is included in the resolved set |
-| AC-4 | Fitness score computed | Score < 0.8 in `:hard`/`:focus` | Dynamic discovery (BF-013) may trigger |
+| AC-4 | Fitness score computed | Score < 0.8 in `:hard`/`:team` | Dynamic discovery (BF-013) may trigger |
 
 **Technical Surface**:
 - `rules/SKILLS.md` — Resolution algorithm, fitness scoring, thresholds
@@ -274,7 +273,7 @@ Each feature specification includes:
 
 ### BF-013 — Dynamic Skill Discovery
 
-**Description**: When fitness < 0.8 in `:hard`/`:focus`, `find-skills` discovers community skills. Tracked in `_dynamic.yaml`.
+**Description**: When fitness < 0.8 in `:hard`/`:team`, `find-skills` discovers community skills. Tracked in `_dynamic.yaml`.
 
 **Acceptance Criteria**:
 
@@ -470,7 +469,7 @@ Each feature specification includes:
 
 **Technical Surface**:
 - `commands/code.md` — Detection routing
-- `commands/code/hard.md`, `commands/code/focus.md` — Skip logic section
+- `commands/code/hard.md`, `commands/code/team.md` — Skip logic section
 
 **Dependencies**: BF-005 (`/code` command)
 

package/documents/business/business-features/04-dependencies-and-release-sequencing.md

@@ -129,11 +129,11 @@ All features on this chain must ship in order. Parallel branches (BF-005→BF-00
 
 ---
 
-### v1.0.2 (2026-01-28) — Focus Variants
+### v1.0.2 (2026-01-28) — Variant Expansion
 
 | Feature | Description |
 |---------|-------------|
-| BF-006 | `:focus` variant added (cook:focus, fix:focus) |
+| BF-006 | Team variant capability expanded for build and fix workflows |
 
 ---
 
@@ -217,7 +217,7 @@ gantt
     BF-010 Cognitive Anchoring     :done, 2026-01-26, 1d
     
     section Must Have (enhanced)
-    BF-006 +focus Variant          :done, 2026-01-28, 1d
+    BF-006 Variant Refinement      :done, 2026-01-28, 1d
     BF-007 HSOL v2 Rewrite         :done, 2026-02-03, 1d
     BF-002 +Codex Platform         :done, 2026-03-09, 1d
     BF-006 +team Variant           :done, 2026-03-09, 1d

package/documents/business/business-features/05-success-metrics.md

@@ -75,7 +75,7 @@
 
 | KPI | Baseline | Target | Measurement | Status |
 |-----|----------|--------|-------------|--------|
-| Variants per command | 1 (no variants) | Up to 4 (fast, hard, focus, team) | Count variant files per command directory | ✅ VALIDATED |
+| Variants per command | 1 (no variants) | Up to 4 (fast, hard, team) | Count variant files per command directory | ✅ VALIDATED |
 | Agent scaling | Fixed | `:fast` 2–3, `:hard` 5–8, `:team` 3 per team | Verify agent count in variant file phase definitions | 📐 STRUCTURAL |
 | Quality gate presence | None | `:hard` includes test + review + security gates | Parse `:hard` variant files for gate definitions | 📐 STRUCTURAL |
 
@@ -225,7 +225,7 @@
 
 | KPI | Baseline | Target | Measurement | Status |
 |-----|----------|--------|-------------|--------|
-| Report variants | 0 | 4 (auto, fast, hard, focus) | Count variant files | ✅ VALIDATED |
+| Report variants | 0 | 3 (fast, hard, team) | Count variant files | ✅ VALIDATED |
 | Report accuracy | Manual reports | Grounded in project state | Compare report assertions to actual codebase state | ❌ UNVALIDATED |
 
 ---