striderZA · Nov 3, 2026 · Nov 3, 2026 · Nov 3, 2026 · Nov 3, 2026 · Nov 3, 2026
diff --git a/.agents/modules/architecture/skills/architecture-review/SKILL.md b/.agents/modules/architecture/skills/architecture-review/SKILL.md
@@ -5,7 +5,6 @@ argument-hint: "[focus: full | coverage | consistency | engine | single-gdd path
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write, Task, question
 agent: technical-director
-model: opencode-go/kimi-k2.6
 ---
 
 # Architecture Review

diff --git a/.agents/modules/core/docs/coordination-rules.md b/.agents/modules/core/docs/coordination-rules.md
@@ -12,25 +12,6 @@
 5. **No Unilateral Cross-Domain Changes**: An agent must never modify files
    outside its designated directories without explicit delegation.
 
-## Model Tier Assignment
-
-Skills and agents are assigned to model tiers based on task complexity:
-
-| Tier | Model | When to use |
-|------|-------|-------------|
-| **Haiku** | `opencode-go/deepseek-v4-flash` | Read-only status checks, formatting, simple lookups — no creative judgment needed |
-| **Sonnet** | `opencode-go/qwen3.6-plus` | Implementation, design authoring, analysis of individual systems — default for most work |
-| **Opus** | `opencode-go/kimi-k2.6` | Multi-document synthesis, high-stakes phase gate verdicts, cross-system holistic review |
-
-Skills with `model: haiku`: `/help`, `/sprint-status`, `/story-readiness`, `/scope-check`,
-`/project-stage-detect`, `/generate-changelog`, `/patch-notes`, `/onboard`
-
-Skills with `model: opus`: `/review-all-gdds`, `/architecture-review`, `/gate-check`
-
-All other skills default to Sonnet. When creating new skills, assign Haiku if the
-skill only reads and formats; assign Opus if it must synthesize 5+ documents with
-high-stakes output; otherwise leave unset (Sonnet).
-
 ## Subagents vs Agent Teams
 
 This project uses two distinct multi-agent patterns:

diff --git a/.agents/modules/core/docs/director-gates.md b/.agents/modules/core/docs/director-gates.md
@@ -124,7 +124,7 @@ For phase gates, record in `docs/architecture/architecture.md` or
 
 ## Tier 1 — Creative Director Gates
 
-Agent: `creative-director` | Model tier: Opus | Domain: Vision, pillars, player experience
+Agent: `creative-director` | Domain: Vision, pillars, player experience
 
 ---
 
@@ -266,7 +266,7 @@ any session that produces player feedback
 
 ## Tier 1 — Technical Director Gates
 
-Agent: `technical-director` | Model tier: Opus | Domain: Architecture, engine risk, performance
+Agent: `technical-director` | Domain: Architecture, engine risk, performance
 
 ---
 
@@ -412,7 +412,7 @@ or before finalizing any engine-specific implementation approach
 
 ## Tier 1 — Producer Gates
 
-Agent: `producer` | Model tier: Opus | Domain: Scope, timeline, dependencies, production risk
+Agent: `producer` | Domain: Scope, timeline, dependencies, production risk
 
 ---
 
@@ -538,7 +538,7 @@ is invoked
 
 ## Tier 1 — Art Director Gates
 
-Agent: `art-director` | Model tier: Sonnet | Domain: Visual identity, art bible, visual production readiness
+Agent: `art-director` | Domain: Visual identity, art bible, visual production readiness
 
 ---
 

diff --git a/.agents/modules/core/skills/gate-check/SKILL.md b/.agents/modules/core/skills/gate-check/SKILL.md
@@ -4,7 +4,6 @@ description: "Validate readiness to advance between development phases. Produces
 argument-hint: "[target-phase: workflow-selection | systems-design | technical-setup | pre-production | production | polish | release] [--review full|lean|solo]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Bash, Write, Task, question
-model: opencode-go/kimi-k2.6
 ---
 
 # Phase Gate Validation

diff --git a/.agents/modules/core/skills/help/SKILL.md b/.agents/modules/core/skills/help/SKILL.md
@@ -6,7 +6,6 @@ user-invocable: true
 allowed-tools: Read, Glob, Grep
 context: |
   Static help skill — reads production artifacts directly to determine project state and next steps.
-model: opencode-go/deepseek-v4-flash
 ---
 
 # Studio Help — What Do I Do Next?

diff --git a/.agents/modules/core/skills/init-template/SKILL.md b/.agents/modules/core/skills/init-template/SKILL.md
@@ -30,7 +30,6 @@ Otherwise, use `question` to gather missing details:
 
 ### Tab 3: Team
 - **Team size** (solo / small 2-5 / medium 6-15 / large 16+)
-- **Preferred model tier** (default / workhorse / lightweight) — refer to the README's Model Mapping section for options
 
 ## Phase 2: Replace README.md
 
@@ -73,7 +72,6 @@ Replace `[Game Name]`, `[One-line description]`, and `[Engine]` with the user's
 
 Read AGENTS.md and update:
 - Set the engine to the user's choice by changing the `## Technology Stack` section
-- Update the model assignment: replace the model table with the user's preference (default/workhorse/lightweight), mapping to their engine's specialist agents
 - Remove or update any project-specific settings
 - If AGENTS.md is missing or malformed, warn and skip this phase
 

diff --git a/.agents/modules/core/skills/project-stage-detect/SKILL.md b/.agents/modules/core/skills/project-stage-detect/SKILL.md
@@ -4,7 +4,6 @@ description: "Automatically analyze project state, detect stage, identify gaps,
 argument-hint: "[optional: role filter like 'programmer' or 'designer']"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Bash, Write
-model: opencode-go/deepseek-v4-flash
 # Read-only diagnostic skill — no specialist agent delegation needed
 ---
 

diff --git a/.agents/modules/design/skills/review-all-gdds/SKILL.md b/.agents/modules/design/skills/review-all-gdds/SKILL.md
@@ -4,7 +4,6 @@ description: "Holistic cross-GDD consistency and game design review. Reads all s
 argument-hint: "[focus: full | consistency | design-theory | since-last-review]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write, Bash, question, Task
-model: opencode-go/kimi-k2.6
 ---
 
 # Review All GDDs

diff --git a/.agents/modules/design/skills/scope-check/SKILL.md b/.agents/modules/design/skills/scope-check/SKILL.md
@@ -4,7 +4,6 @@ description: "Analyze a feature or sprint for scope creep by comparing current s
 argument-hint: "[feature-name or sprint-N]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Bash
-model: opencode-go/deepseek-v4-flash
 ---
 
 # Scope Check

diff --git a/.agents/modules/release/skills/changelog/SKILL.md b/.agents/modules/release/skills/changelog/SKILL.md
@@ -7,7 +7,6 @@ allowed-tools: Read, Glob, Grep, Bash, Write
 context: |
   !git log --oneline -30 2>/dev/null
   !git tag --list --sort=-v:refname 2>/dev/null | head -5
-model: opencode-go/deepseek-v4-flash
 ---
 
 ## Phase 1: Parse Arguments

diff --git a/.agents/modules/release/skills/patch-notes/SKILL.md b/.agents/modules/release/skills/patch-notes/SKILL.md
@@ -4,7 +4,6 @@ description: "Generate player-facing patch notes from git history, sprint data,
 argument-hint: "[version] [--style brief|detailed|full]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write, Bash
-model: opencode-go/deepseek-v4-flash
 agent: community-manager
 ---
 

diff --git a/.agents/modules/release/skills/sprint-status/SKILL.md b/.agents/modules/release/skills/sprint-status/SKILL.md
@@ -4,7 +4,6 @@ description: "Fast sprint status check. Reads the current sprint plan, scans sto
 argument-hint: "[sprint-number or blank for current]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep
-model: opencode-go/deepseek-v4-flash
 ---
 
 # Sprint Status

diff --git a/.agents/modules/stories/skills/onboard/SKILL.md b/.agents/modules/stories/skills/onboard/SKILL.md
@@ -4,7 +4,6 @@ description: "Generates a contextual onboarding document for a new contributor o
 argument-hint: "[role|area]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write
-model: opencode-go/deepseek-v4-flash
 ---
 
 ## Phase 1: Load Project Context

diff --git a/.agents/modules/stories/skills/story-readiness/SKILL.md b/.agents/modules/stories/skills/story-readiness/SKILL.md
@@ -4,7 +4,6 @@ description: "Validate that a story file is implementation-ready. Checks for emb
 argument-hint: "[story-file-path or 'all' or 'sprint']"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, question, Task
-model: opencode-go/deepseek-v4-flash
 ---
 
 # Story Readiness

diff --git a/.agents/skills/architecture-review/SKILL.md b/.agents/skills/architecture-review/SKILL.md
@@ -5,7 +5,6 @@ argument-hint: "[focus: full | coverage | consistency | engine | single-gdd path
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write, Task, question
 agent: technical-director
-model: opencode-go/kimi-k2.6
 ---
 
 # Architecture Review

diff --git a/.agents/skills/changelog/SKILL.md b/.agents/skills/changelog/SKILL.md
@@ -7,7 +7,6 @@ allowed-tools: Read, Glob, Grep, Bash, Write
 context: |
   !git log --oneline -30 2>/dev/null
   !git tag --list --sort=-v:refname 2>/dev/null | head -5
-model: opencode-go/deepseek-v4-flash
 ---
 
 ## Phase 1: Parse Arguments

diff --git a/.agents/skills/gate-check/SKILL.md b/.agents/skills/gate-check/SKILL.md
@@ -4,7 +4,6 @@ description: "Validate readiness to advance between development phases. Produces
 argument-hint: "[target-phase: workflow-selection | systems-design | technical-setup | pre-production | production | polish | release] [--review full|lean|solo]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Bash, Write, Task, question
-model: opencode-go/kimi-k2.6
 ---
 
 # Phase Gate Validation

diff --git a/.agents/skills/help/SKILL.md b/.agents/skills/help/SKILL.md
@@ -6,7 +6,6 @@ user-invocable: true
 allowed-tools: Read, Glob, Grep
 context: |
   Static help skill — reads production artifacts directly to determine project state and next steps.
-model: opencode-go/deepseek-v4-flash
 ---
 
 # Studio Help — What Do I Do Next?

diff --git a/.agents/skills/init-template/SKILL.md b/.agents/skills/init-template/SKILL.md
@@ -30,7 +30,6 @@ Otherwise, use `question` to gather missing details:
 
 ### Tab 3: Team
 - **Team size** (solo / small 2-5 / medium 6-15 / large 16+)
-- **Preferred model tier** (default / workhorse / lightweight) — refer to the README's Model Mapping section for options
 
 ### Modular Installation
 
@@ -108,7 +107,6 @@ Replace `[Game Name]`, `[One-line description]`, and `[Engine]` with the user's
 
 Read AGENTS.md and update:
 - Set the engine to the user's choice by changing the `## Technology Stack` section
-- Update the model assignment: replace the model table with the user's preference (default/workhorse/lightweight), mapping to their engine's specialist agents
 - Remove or update any project-specific settings
 - If AGENTS.md is missing or malformed, warn and skip this phase
 

diff --git a/.agents/skills/onboard/SKILL.md b/.agents/skills/onboard/SKILL.md
@@ -4,7 +4,6 @@ description: "Generates a contextual onboarding document for a new contributor o
 argument-hint: "[role|area]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write, question
-model: opencode-go/deepseek-v4-flash
 ---
 
 ## Overview

diff --git a/.agents/skills/patch-notes/SKILL.md b/.agents/skills/patch-notes/SKILL.md
@@ -4,7 +4,6 @@ description: "Generate player-facing patch notes from git history, sprint data,
 argument-hint: "[version] [--style brief|detailed|full]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write, Bash
-model: opencode-go/deepseek-v4-flash
 agent: community-manager
 ---
 

diff --git a/.agents/skills/project-stage-detect/SKILL.md b/.agents/skills/project-stage-detect/SKILL.md
@@ -4,7 +4,6 @@ description: "Automatically analyze project state, detect stage, identify gaps,
 argument-hint: "[optional: role filter like 'programmer' or 'designer']"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Bash, Write
-model: opencode-go/deepseek-v4-flash
 # Read-only diagnostic skill — no specialist agent delegation needed
 ---
 

diff --git a/.agents/skills/review-all-gdds/SKILL.md b/.agents/skills/review-all-gdds/SKILL.md
@@ -4,7 +4,6 @@ description: "Holistic cross-GDD consistency and game design review. Reads all s
 argument-hint: "[focus: full | consistency | design-theory | since-last-review]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write, Bash, question, Task
-model: opencode-go/kimi-k2.6
 ---
 
 # Review All GDDs

diff --git a/.agents/skills/scope-check/SKILL.md b/.agents/skills/scope-check/SKILL.md
@@ -4,7 +4,6 @@ description: "Analyze a feature or sprint for scope creep by comparing current s
 argument-hint: "[feature-name or sprint-N]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Bash
-model: opencode-go/deepseek-v4-flash
 ---
 
 # Scope Check

diff --git a/.agents/skills/sprint-status/SKILL.md b/.agents/skills/sprint-status/SKILL.md
@@ -4,7 +4,6 @@ description: "Fast sprint status check. Reads the current sprint plan, scans sto
 argument-hint: "[sprint-number or blank for current]"
 user-invocable: true
 allowed-tools: Read, Glob, Grep
-model: opencode-go/deepseek-v4-flash
 ---
 
 # Sprint Status

diff --git a/.agents/skills/story-readiness/SKILL.md b/.agents/skills/story-readiness/SKILL.md
@@ -4,7 +4,6 @@ description: "Validate that a story file is implementation-ready. Checks for emb
 argument-hint: "[story-file-path or 'all' or 'sprint']"
 user-invocable: true
 allowed-tools: Read, Glob, Grep, question, Task
-model: opencode-go/deepseek-v4-flash
 ---
 
 # Story Readiness

diff --git a/.github/workflows/opencode.yml b/.github/workflows/opencode.yml
diff --git a/.opencode/modules/architecture/agents/lead-programmer.md b/.opencode/modules/architecture/agents/lead-programmer.md
@@ -1,7 +1,6 @@
 ---
 description: "The Lead Programmer owns code-level architecture, coding standards, code review, and the assignment of programming work to specialist programmers. Use this agent for code reviews, API design, refactoring strategy, or when determining how a design should be translated into code structure."
 mode: subagent
-model: opencode-go/qwen3.6-plus
 maxTurns: 20
 ---
 

diff --git a/.opencode/modules/architecture/skills/architecture-review/SKILL.md b/.opencode/modules/architecture/skills/architecture-review/SKILL.md
@@ -5,7 +5,6 @@ argument-hint: "[focus: full | coverage | consistency | engine | single-gdd path
 user-invocable: true
 allowed-tools: Read, Glob, Grep, Write, Task, question
 agent: technical-director
-model: opencode-go/kimi-k2.6
 ---
 
 # Architecture Review

diff --git a/.opencode/modules/art/agents/art-director.md b/.opencode/modules/art/agents/art-director.md
@@ -1,7 +1,6 @@
 ---
 description: "The Art Director owns the visual identity of the game: style guides, art bible, asset standards, color palettes, UI/UX visual design, and the art production pipeline. Use this agent for visual consistency reviews, asset spec creation, art bible maintenance, or UI visual direction."
 mode: subagent
-model: opencode-go/qwen3.6-plus
 maxTurns: 20
 permission:
   bash: deny

diff --git a/.opencode/modules/art/agents/technical-artist.md b/.opencode/modules/art/agents/technical-artist.md
@@ -1,7 +1,6 @@
 ---
 description: "The Technical Artist bridges art and engineering: shaders, VFX, rendering optimization, art pipeline tools, and performance profiling for visual systems. Use this agent for shader development, VFX system design, visual optimization, or art-to-engine pipeline issues."
 mode: subagent
-model: opencode-go/qwen3.6-plus
 maxTurns: 20
 ---
 

diff --git a/.opencode/modules/audio/agents/audio-director.md b/.opencode/modules/audio/agents/audio-director.md
@@ -1,7 +1,6 @@
 ---
 description: "The Audio Director owns the sonic identity of the game: music direction, sound design philosophy, audio implementation strategy, and mix balance. Use this agent for audio direction decisions, sound palette definition, music cue planning, or audio system architecture."
 mode: subagent
-model: opencode-go/qwen3.6-plus
 maxTurns: 20
 permission:
   bash: deny

diff --git a/.opencode/modules/audio/agents/sound-designer.md b/.opencode/modules/audio/agents/sound-designer.md
@@ -1,7 +1,6 @@
 ---
 description: "The Sound Designer creates detailed specifications for sound effects, documents audio events, and defines mixing parameters. Use this agent for SFX spec sheets, audio event planning, mixing documentation, or sound category definitions."
 mode: subagent
-model: opencode-go/deepseek-v4-flash
 maxTurns: 10
 permission:
   bash: deny

diff --git a/.opencode/modules/core/agents/creative-director.md b/.opencode/modules/core/agents/creative-director.md
@@ -1,7 +1,6 @@
 ---
 description: "The Creative Director is the highest-level creative authority for the project. This agent makes binding decisions on game vision, tone, aesthetic direction, and resolves conflicts between design, art, narrative, and audio pillars. Use this agent when a decision affects the fundamental identity of the game or when department leads cannot reach consensus."
 mode: primary
-model: opencode-go/kimi-k2.6
 maxTurns: 30
 permission:
   bash: deny

diff --git a/.opencode/modules/core/agents/producer.md b/.opencode/modules/core/agents/producer.md
@@ -1,7 +1,6 @@
 ---
 description: "The Producer manages all production concerns: sprint planning, milestone tracking, risk management, scope negotiation, and cross-department coordination. This is the primary coordination agent. Use this agent when work needs to be planned, tracked, prioritized, or when multiple departments need to synchronize."
 mode: primary
-model: opencode-go/kimi-k2.6
 maxTurns: 30
 ---
 

diff --git a/.opencode/modules/core/agents/technical-director.md b/.opencode/modules/core/agents/technical-director.md
@@ -1,7 +1,6 @@
 ---
 description: "The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or enable design possibilities."
 mode: primary
-model: opencode-go/kimi-k2.6
 maxTurns: 30
 ---