Remove agent: field from all 20 commands — same root cause as subtask fix

The agent: field on a command makes OpenCode delegate the entire command
to a specific subagent. The subagent receives only the command body
(skill file reference + arguments) with ZERO conversation context.

This caused the /prototype failure: the prototyper subagent received
the skill file but had no idea what game to prototype, which mechanic
to validate, or where the concept doc lived — because subagents don't
inherit conversation history.

Root cause: upstream Claude Code's agent: field was metadata/hint only.
Skills ran inline in the main conversation. OpenCode's agent: field is
a delegation mechanism that bypasses the main agent's context.

Fix: removed agent: from all 20 affected commands (adopt,
architecture-review, balance-check, code-review, content-audit,
create-architecture, create-control-manifest, create-epics,
create-stories, localize, patch-notes, perf-profile,
propagate-design-change, prototype, qa-plan, security-audit, team-qa,
ux-design, ux-review, vertical-slice).

After fix: all 77 commands run inline with zero agent: or subtask:
fields. The main agent loads the skill, gathers context interactively,
and spawns specific subagents via the task tool WITH full context in
the prompt — exactly matching upstream behavior.

All 77 commands: 0 with agent:, 0 with subtask:.

Author: Cipher-85

.opencode/commands/adopt.md

@@ -1,6 +1,5 @@
 ---
 description: Brownfield onboarding — audits existing project artifacts for template format compliance (not just existence), classifies gaps by impact, and produces a numbered migration plan. Run this when joining an in-progress project or upgrading from an older template version. Distinct from /project-stage-detect (which checks what exists) — this checks whether what exists will actually work with the template's skills.
-agent: technical-director
 ---
 @.opencode/skills/adopt/SKILL.md
 

.opencode/commands/architecture-review.md

@@ -1,6 +1,5 @@
 ---
 description: Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL verdict. The architecture equivalent of /design-review.
-agent: technical-director
 ---
 @.opencode/skills/architecture-review/SKILL.md
 

.opencode/commands/balance-check.md

@@ -1,6 +1,5 @@
 ---
 description: Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design. Use when user says 'balance report', 'check game balance', 'run a balance check'.
-agent: economy-designer
 ---
 @.opencode/skills/balance-check/SKILL.md
 

.opencode/commands/code-review.md

@@ -1,6 +1,5 @@
 ---
 description: Performs an architectural and quality code review on a specified file or set of files. Checks for coding standard compliance, architectural pattern adherence, SOLID principles, testability, and performance concerns.
-agent: lead-programmer
 ---
 @.opencode/skills/code-review/SKILL.md
 

.opencode/commands/content-audit.md

@@ -1,6 +1,5 @@
 ---
 description: Audit GDD-specified content counts against implemented content. Identifies what's planned vs built.
-agent: producer
 ---
 @.opencode/skills/content-audit/SKILL.md
 

.opencode/commands/create-architecture.md

@@ -1,6 +1,5 @@
 ---
 description: 'Guided, section-by-section authoring of the master architecture document for the game. Reads all GDDs, the systems index, existing ADRs, and the engine reference library to produce a complete architecture blueprint before any code is written. Engine-version-aware: flags knowledge gaps and validates decisions against the pinned engine version.'
-agent: technical-director
 ---
 @.opencode/skills/create-architecture/SKILL.md
 

.opencode/commands/create-control-manifest.md

@@ -1,6 +1,5 @@
 ---
 description: After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).
-agent: technical-director
 ---
 @.opencode/skills/create-control-manifest/SKILL.md
 

.opencode/commands/create-epics.md

@@ -1,6 +1,5 @@
 ---
 description: Translate approved GDDs + architecture into epics — one epic per architectural module. Defines scope, governing ADRs, engine risk, and untraced requirements. Does NOT break into stories — run /create-stories [epic-slug] after each epic is created.
-agent: technical-director
 ---
 @.opencode/skills/create-epics/SKILL.md
 

.opencode/commands/create-stories.md

@@ -1,6 +1,5 @@
 ---
 description: Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.
-agent: lead-programmer
 ---
 @.opencode/skills/create-stories/SKILL.md
 

.opencode/commands/localize.md

@@ -1,6 +1,5 @@
 ---
 description: 'Full localization pipeline: scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage.'
-agent: localization-lead
 ---
 @.opencode/skills/localize/SKILL.md