gsd-opencode 1.33.0 → 1.33.2

package/commands/gsd/gsd-set-profile.md

@@ -2,7 +2,6 @@
 name: gsd-set-profile
 description: Switch model profile for GSD agents (simple/smart/genius/inherit)
 argument-hint: <profile (simple|smart|genius|inherit)>
-model: haiku
 permissions:
    bash: true
 ---

package/get-shit-done/workflows/autonomous.md

@@ -319,11 +319,7 @@ UI_SPEC_FILE=$(ls "${PHASE_DIR}"/*-UI-SPEC.md 2>/dev/null | head -1)
 **If `INTERACTIVE` is set:** Dispatch plan as a background agent to keep the main context lean. While plan runs, the workflow can immediately start discussing the next phase (see step 4).
 
 ```
-Agent(
-  description="Plan phase ${PHASE_NUM}: ${PHASE_NAME}",
-  run_in_background=true,
-  prompt="Run plan-phase for phase ${PHASE_NUM}: skill(skill=\"gsd:plan-phase\", args=\"${PHASE_NUM}\")"
-)
+@gsd-plan-phase "Run plan-phase for phase ${PHASE_NUM}: skill(skill=\"gsd-plan-phase\", args=\"${PHASE_NUM}\")"
 ```
 
 Store the agent task_id. After discuss for the next phase completes (or if no next phase), wait for the plan agent to finish before proceeding to execute.
@@ -341,11 +337,7 @@ Verify plan produced output — re-run `init phase-op` and check `has_plans`. If
 **If `INTERACTIVE` is set:** Wait for the plan agent to complete (if not already), verify plans exist, then dispatch execute as a background agent:
 
 ```
-Agent(
-  description="Execute phase ${PHASE_NUM}: ${PHASE_NAME}",
-  run_in_background=true,
-  prompt="Run execute-phase for phase ${PHASE_NUM}: skill(skill=\"gsd:execute-phase\", args=\"${PHASE_NUM} --no-transition\")"
-)
+@gsd-execute-phase "Run execute-phase for phase ${PHASE_NUM}: skill(skill=\"gsd-execute-phase\", args=\"${PHASE_NUM} --no-transition\")"
 ```
 
 Store the agent task_id. The workflow can now start discussing the next phase while this phase executes in the background. Before starting post-execution routing for this phase, wait for the execute agent to complete.

package/get-shit-done/workflows/discovery-phase.md

@@ -93,7 +93,7 @@ For: Choosing between options, new external integration.
 
    ```
    For each library/framework:
-   - mcp__context7__resolve-library-id  
+   - mcp__context7__resolve-library-id   
    - mcp__context7__get-library-docs (mode: "code" for API, "info" for concepts)
    ```
 

package/get-shit-done/workflows/discuss-phase-assumptions.md

@@ -310,7 +310,7 @@ Parse the subagent's response. Extract:
 If research topics were flagged, spawn a general research agent:
 
 ```
-task(subagent_type="general", prompt="""
+@general """
 Research the following topics for Phase {PHASE}: {phase_name}.
 
 Topics needing research:
@@ -323,7 +323,7 @@ For each topic, return:
 
 Use Context7 (resolve-library-id then query-docs) for library-specific questions.
 Use websearch for ecosystem/best-practice questions.
-""")
+"""
 ```
 
 Merge findings back into assumptions:

package/get-shit-done/workflows/discuss-phase.md

@@ -551,10 +551,9 @@ After user selects gray areas in present_gray_areas, spawn parallel research age
 
 1. Display brief status: "Researching {N} areas..."
 
-2. For EACH user-selected gray area, spawn a task() in parallel:
+2. For EACH user-selected gray area, spawn a relevant subagent using `@subagent prompt` syntax in parallel:
 
-   task(
-     prompt="First, read @$HOME/.config/opencode/agents/gsd-advisor-researcher.md for your role and instructions.
+   @gsd-advisor-researcher "First, read @$HOME/.config/opencode/agents/gsd-advisor-researcher.md for your role and instructions.
 
      <gray_area>{area_name}: {area_description from gray area identification}</gray_area>
      <phase_context>{phase_goal and description from ROADMAP.md}</phase_context>
@@ -562,13 +561,9 @@ After user selects gray areas in present_gray_areas, spawn parallel research age
      <calibration_tier>{resolved calibration tier: full_maturity | standard | minimal_decisive}</calibration_tier>
 
      Research this gray area and return a structured comparison table with rationale.
-     ${AGENT_SKILLS_ADVISOR}",
-     subagent_type="general",
-     model="{ADVISOR_MODEL}",
-     description="Research: {area_name}"
-   )
+     ${AGENT_SKILLS_ADVISOR}"
 
-   All task() calls spawn simultaneously — do NOT wait for one before starting the next.
+   All subagents spawn simultaneously — do NOT wait for one before starting the next.
 
 3. After ALL agents return, SYNTHESIZE results before presenting:
    For each agent's return:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gsd-opencode",
-  "version": "1.33.0",
+  "version": "1.33.2",
   "description": "GSD-OpenCode distribution manager - install, verify, and maintain your GSD-OpenCode installation",
   "type": "module",
   "main": "bin/gsd.js",