gsd-opencode 1.3.33 → 1.4.2

package/command/gsd/new-project.md

@@ -2,9 +2,9 @@
 name: gsd:new-project
 description: Initialize a new project with deep context gathering and PROJECT.md
 allowed-tools:
-  - Read
-  - Bash
-  - Write
+  - read
+  - bash
+  - write
   - question
 ---
 
@@ -228,8 +228,8 @@ Use question:
 - header: "Mode"
 - question: "How do you want to work?"
 - options:
+  - "YOLO" — Auto-approve, just execute (Recommended)
   - "Interactive" — Confirm at each step
-  - "YOLO" — Auto-approve, just execute
 
 </step>
 
@@ -248,7 +248,27 @@ Use question:
 
 **Depth controls compression tolerance, not artificial inflation.** All depths use 2-3 tasks per plan. Comprehensive means "don't compress complex work"—it doesn't mean "pad simple work to hit a number."
 
-Create `.planning/config.json` with chosen mode and depth using `templates/config.json` structure.
+</step>
+
+<step name="parallelization">
+
+Ask parallel execution preference:
+
+Use question:
+
+- header: "Parallelization"
+- question: "Enable parallel phase execution?"
+- options:
+  - "Enabled" — Run independent plans in parallel (Recommended)
+  - "Disabled" — Execute plans sequentially
+
+**Parallelization** spawns multiple agents for independent plans within a phase. Wave-based execution handles dependencies automatically. Can be changed later in config.json.
+
+</step>
+
+<step name="config">
+
+Create `.planning/config.json` with chosen mode, depth, and parallelization using `templates/config.json` structure.
 
 </step>
 
@@ -290,7 +310,6 @@ Project initialized:
 *`/clear` first → fresh context window*
 
 ---
-
 ```
 
 </step>
@@ -310,7 +329,7 @@ Project initialized:
 - [ ] PROJECT.md captures full context with evolutionary structure
 - [ ] Requirements initialized as hypotheses (greenfield) or with inferred Validated (brownfield)
 - [ ] Key Decisions table initialized
-- [ ] config.json has workflow mode
+- [ ] config.json has workflow mode, depth, and parallelization
 - [ ] All committed to git
 
 </success_criteria>

package/command/gsd/pause-work.md

@@ -2,9 +2,9 @@
 name: gsd:pause-work
 description: Create context handoff when pausing work mid-phase
 allowed-tools:
-  - Read
-  - Write
-  - Bash
+  - read
+  - write
+  - bash
 ---
 
 <objective>
@@ -120,3 +120,4 @@ To resume: /gsd:resume-work
 - [ ] Committed as WIP
 - [ ] User knows location and how to resume
 </success_criteria>
+```

package/command/gsd/plan-fix.md

@@ -3,11 +3,11 @@ name: gsd:plan-fix
 description: Plan fixes for UAT issues from verify-work
 argument-hint: "[plan, e.g., '04-02']"
 allowed-tools:
-  - Read
-  - Bash
-  - Write
-  - Glob
-  - Grep
+  - read
+  - bash
+  - write
+  - glob
+  - grep
   - question
 ---
 
@@ -24,7 +24,7 @@ Output: {plan}-FIX.md in the phase directory, ready for execution.
 </execution_context>
 
 <context>
-Plan number: $ARGUMENTS (required - e.g., "04-02" or "09-01")
+Plan number: ($ARGUMENTS) (required - e.g., "04-02" or "09-01")
 
 **Load project state:**
 @.planning/STATE.md
@@ -36,7 +36,7 @@ Plan number: $ARGUMENTS (required - e.g., "04-02" or "09-01")
 <step name="parse">
 **Parse plan argument:**
 
-$ARGUMENTS should be a plan number like "04-02" or "09-01".
+($ARGUMENTS) should be a plan number like "04-02" or "09-01".
 Extract phase number (XX) and plan number (NN).
 
 If no argument provided:
@@ -126,7 +126,7 @@ Priority: {critical count} critical, {major count} major, {minor count} minor
 </objective>
 
 <execution_context>
-@~/.config/opencode/get-shit-done/workflows/execute-phase.md
+@~/.config/opencode/get-shit-done/workflows/execute-plan.md
 @~/.config/opencode/get-shit-done/templates/summary.md
 </execution_context>
 

package/command/gsd/plan-phase.md

@@ -3,11 +3,11 @@ name: gsd:plan-phase
 description: Create detailed execution plan for a phase (PLAN.md)
 argument-hint: "[phase]"
 allowed-tools:
-  - Read
-  - Bash
-  - Write
-  - Glob
-  - Grep
+  - read
+  - bash
+  - write
+  - glob
+  - grep
   - question
   - webfetch
   - mcp__context7__*
@@ -16,7 +16,7 @@ allowed-tools:
 <objective>
 Create executable phase prompt with discovery, context injection, and task breakdown.
 
-Purpose: Break down roadmap phases into concrete, executable PLAN.md files that Claude can execute.
+Purpose: Break down roadmap phases into concrete, executable PLAN.md files that OpenCode can execute.
 Output: One or more PLAN.md files in the phase directory (.planning/phases/XX-name/{phase}-{plan}-PLAN.md)
 </objective>
 
@@ -30,7 +30,7 @@ Output: One or more PLAN.md files in the phase directory (.planning/phases/XX-na
 </execution_context>
 
 <context>
-Phase number: $ARGUMENTS (optional - auto-detects next unplanned phase if not provided)
+Phase number: ($ARGUMENTS) (optional - auto-detects next unplanned phase if not provided)
 
 **Load project state first:**
 @.planning/STATE.md
@@ -47,7 +47,7 @@ Check for `.planning/codebase/` and load relevant documents based on phase type.
 
 <process>
 1. Check .planning/ directory exists (error if not - user should run /gsd:new-project)
-2. If phase number provided via $ARGUMENTS, validate it exists in roadmap
+2. If phase number provided via ($ARGUMENTS), validate it exists in roadmap
 3. If no phase number, detect next unplanned phase from roadmap
 4. Follow plan-phase.md workflow:
    - Load project state and accumulated decisions
@@ -62,6 +62,6 @@ Check for `.planning/codebase/` and load relevant documents based on phase type.
 
 - One or more PLAN.md files created in .planning/phases/XX-name/
 - Each plan has: objective, execution_context, context, tasks, verification, success_criteria, output
-- Tasks are specific enough for Claude to execute
+- Tasks are specific enough for OpenCode to execute
 - User knows next steps (execute plan or review/adjust)
   </success_criteria>

package/command/gsd/progress.md

@@ -2,10 +2,10 @@
 name: gsd:progress
 description: Check project progress, show context, and route to next action (execute or plan)
 allowed-tools:
-  - Read
-  - Bash
-  - Grep
-  - Glob
+  - read
+  - bash
+  - grep
+  - glob
 ---
 
 <objective>
@@ -44,7 +44,7 @@ If missing STATE.md or ROADMAP.md: inform what's missing, suggest running `/gsd:
 <step name="recent">
 **Gather recent work context:**
 
-- Find 2-3 most recent SUMMARY.md files
+- Find the 2-3 most recent SUMMARY.md files
 - Extract from each: what was accomplished, key decisions, any issues logged
 - This shows "what we've been working on"
   </step>
@@ -56,6 +56,8 @@ If missing STATE.md or ROADMAP.md: inform what's missing, suggest running `/gsd:
 - Calculate: total plans, completed plans, remaining plans
 - Note any blockers, concerns, or deferred issues
 - Check for CONTEXT.md: For phases without PLAN.md files, check if `{phase}-CONTEXT.md` exists in phase directory
+- Count pending todos: `ls .planning/todos/pending/*.md 2>/dev/null | wc -l`
+- Check for active debug sessions: `ls .planning/debug/*.md 2>/dev/null | grep -v resolved | wc -l`
   </step>
 
 <step name="report">
@@ -82,6 +84,13 @@ CONTEXT: [✓ if CONTEXT.md exists | - if not]
 ## Open Issues
 - [any deferred issues or blockers]
 
+## Pending Todos
+- [count] pending — /gsd:check-todos to review
+
+## Active Debug Sessions
+- [count] active — /gsd:debug to continue
+(Only show this section if count > 0)
+
 ## What's Next
 [Next phase/plan objective from ROADMAP]
 ```
@@ -93,7 +102,7 @@ CONTEXT: [✓ if CONTEXT.md exists | - if not]
 
 **Step 1: Count plans, summaries, and issues in current phase**
 
-List files in current phase directory:
+List files in the current phase directory:
 
 ```bash
 ls -1 .planning/phases/[current-phase-dir]/*-PLAN.md 2>/dev/null | wc -l
@@ -128,7 +137,7 @@ Track:
 
 **Route A: Unexecuted plan exists**
 
-Find first PLAN.md without matching SUMMARY.md.
+Find the first PLAN.md without matching SUMMARY.md.
 Read its `<objective>` section.
 
 ```
@@ -186,7 +195,7 @@ Check if `{phase}-CONTEXT.md` exists in phase directory.
 **Also available:**
 - `/gsd:discuss-phase {phase}` — gather context first
 - `/gsd:research-phase {phase}` — investigate unknowns
-- `/gsd:list-phase-assumptions {phase}` — see Claude's assumptions
+- `/gsd:list-phase-assumptions {phase}` — see OpenCode's assumptions
 
 ---
 ```
@@ -223,9 +232,9 @@ ISSUES.md exists without matching FIX.md. User needs to plan fixes.
 
 Read ROADMAP.md and identify:
 1. Current phase number
-2. All phase numbers in current milestone section
+2. All phase numbers in the current milestone section
 
-Count total phases and identify highest phase number.
+Count total phases and identify the highest phase number.
 
 State: "Current phase is {X}. Milestone has {N} phases (highest: {Y})."
 
@@ -240,7 +249,7 @@ State: "Current phase is {X}. Milestone has {N} phases (highest: {Y})."
 
 **Route C: Phase complete, more phases remain**
 
-Read ROADMAP.md to get next phase's name and goal.
+Read ROADMAP.md to get the next phase's name and goal.
 
 ```
 ---

package/command/gsd/remove-phase.md

@@ -3,16 +3,16 @@ name: gsd:remove-phase
 description: Remove a future phase from roadmap and renumber subsequent phases
 argument-hint: <phase-number>
 allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - Glob
+  - read
+  - write
+  - bash
+  - glob
 ---
 
 <objective>
-Remove an unstarted future phase from roadmap and renumber all subsequent phases to maintain a clean, linear sequence.
+Remove an unstarted future phase from the roadmap and renumber all subsequent phases to maintain a clean, linear sequence.
 
-Purpose: Clean removal of work you've decided not to do, without poluting context with cancelled/deferred markers.
+Purpose: Clean removal of work you've decided not to do, without polluting context with cancelled/deferred markers.
 Output: Phase deleted, all subsequent phases renumbered, git commit as historical record.
 </objective>
 
@@ -24,8 +24,8 @@ Output: Phase deleted, all subsequent phases renumbered, git commit as historica
 <process>
 
 <step name="parse_arguments">
-Parse command arguments:
-- Argument ($ARGUMENTS) is phase number to remove (integer or decimal)
+Parse the command arguments:
+- Argument is the phase number to remove (integer or decimal)
 - Example: `/gsd:remove-phase 17` → phase = 17
 - Example: `/gsd:remove-phase 16.1` → phase = 16.1
 
@@ -66,7 +66,7 @@ Verify that target phase exists in ROADMAP.md:
 </step>
 
 <step name="validate_future_phase">
-Verify that phase is a future phase (not started):
+Verify that the phase is a future phase (not started):
 
 1. Compare target phase to current phase from STATE.md
 2. Target must be > current phase number
@@ -151,8 +151,8 @@ Delete target phase directory if it exists:
 
 ```bash
 if [ -d ".planning/phases/{target}-{slug}" ]; then
-  rm -rf ".planning/phases/{target}-${slug}"
-  echo "Deleted: .planning/phases/{target}-${slug}/"
+  rm -rf ".planning/phases/{target}-{slug}"
+  echo "Deleted: .planning/phases/{target}-{slug}/"
 fi
 ```
 
@@ -195,14 +195,14 @@ Also handle CONTEXT.md and DISCOVERY.md (these don't have phase prefixes, so no
 <step name="update_roadmap">
 Update ROADMAP.md:
 
-1. **Remove** phase section entirely:
+1. **Remove phase section entirely:**
    - Delete from `### Phase {target}:` to next phase heading (or section end)
 
 2. **Remove from phase list:**
    - Delete line `- [ ] **Phase {target}: {Name}**` or similar
 
 3. **Remove from Progress table:**
-   - Delete of row for Phase {target}
+   - Delete row for Phase {target}
 
 4. **Renumber all subsequent phases:**
    - `### Phase 18:` → `### Phase 17:`
@@ -231,7 +231,7 @@ Update STATE.md:
 2. **Recalculate progress percentage:**
    - New percentage based on completed plans / new total plans
 
-Do NOT add a "Roadmap Evolution" note - git commit is the record.
+Do NOT add a "Roadmap Evolution" note - git commit is record.
 
 Write updated STATE.md.
 </step>
@@ -295,7 +295,7 @@ Would you like to:
 - Don't remove completed phases (have SUMMARY.md files)
 - Don't remove current or past phases
 - Don't leave gaps in numbering - always renumber
-- Don't add "removed phase" notes to STATE.md - git commit is the record
+- Don't add "removed phase" notes to STATE.md - git commit is record
 - Don't ask about each decimal phase - just renumber them
 - Don't modify completed phase directories
 </anti_patterns>

package/command/gsd/research-phase.md

@@ -3,20 +3,20 @@ name: gsd:research-phase
 description: Research how to implement a phase before planning
 argument-hint: "[phase]"
 allowed-tools:
-  - Read
-  - Bash
-  - Glob
-  - Grep
-  - Write
+  - read
+  - bash
+  - glob
+  - grep
+  - write
   - webfetch
-  - WebSearch
+  - websearch
   - mcp__context7__*
 ---
 
 <objective>
 Comprehensive research on HOW to implement a phase before planning.
 
-This is for niche/complex domains where Claude's training data is sparse or outdated. Research discovers:
+This is for niche/complex domains where OpenCode's training data is sparse or outdated. Research discovers:
 - What libraries exist for this problem
 - What architecture patterns experts use
 - What standard stack looks like
@@ -33,7 +33,7 @@ Output: RESEARCH.md with ecosystem knowledge that informs quality planning.
 </execution_context>
 
 <context>
-Phase number: $ARGUMENTS (required)
+Phase number: ($ARGUMENTS) (required)
 
 **Load project state:**
 @.planning/STATE.md
@@ -74,7 +74,7 @@ Check for `.planning/phases/XX-name/{phase}-CONTEXT.md` - bonus context from dis
 - Standard web dev (auth, CRUD, REST APIs)
 - Well-known patterns (forms, validation, testing)
 - Simple integrations (Stripe, SendGrid with clear docs)
-- Commodity features Claude handles well
+- Commodity features OpenCode handles well
 </when_to_use>
 
 <success_criteria>
@@ -85,7 +85,7 @@ Check for `.planning/phases/XX-name/{phase}-CONTEXT.md` - bonus context from dis
 - [ ] RESEARCH.md created with ecosystem knowledge
 - [ ] Standard stack/libraries identified
 - [ ] Architecture patterns documented
-- [ ] Common pitfalls catalogueed
+- [ ] Common pitfalls catalogued
 - [ ] What NOT to hand-roll is clear
 - [ ] User knows next steps (plan phase)
 </success_criteria>

package/command/gsd/resume-work.md

@@ -2,17 +2,16 @@
 name: gsd:resume-work
 description: Resume work from previous session with full context restoration
 allowed-tools:
-  - Read
-  - Bash
-  - Write
+  - read
+  - bash
+  - write
   - question
 ---
 
 <objective>
 Restore complete project context and resume work seamlessly from previous session.
 
-Routes to:
-- resume-project workflow which handles:
+Routes to resume-project workflow which handles:
 
 - STATE.md loading (or reconstruction if missing)
 - Checkpoint detection (.continue-here files)

package/command/gsd/status.md

@@ -0,0 +1,127 @@
+---
+name: gsd:status
+description: Check status of background agents from parallel execution
+argument-hint: "[--wait]"
+allowed-tools:
+  - read
+  - write
+  - bash
+---
+
+<objective>
+Monitor background agent status from /gsd:execute-phase parallel execution.
+
+Shows running/completed agents from agent-history.json.
+With --wait flag, blocks until all agents complete.
+</objective>
+
+<context>
+Arguments: ($ARGUMENTS)
+</context>
+
+<process>
+
+<step name="load_history">
+**Load agent history:**
+
+```bash
+cat .planning/agent-history.json 2>/dev/null || echo '{"entries":[]}'
+```
+
+If file doesn't exist or has no entries:
+```
+No background agents tracked.
+
+Run /gsd:execute-phase to spawn parallel agents.
+```
+Exit.
+</step>
+
+<step name="filter_agents">
+**Find background agents:**
+
+Filter entries where:
+- `execution_mode` is "parallel" or "background"
+- `status` is "spawned" (still running) or recently completed
+
+Group by `parallel_group` if present.
+</step>
+
+<step name="display">
+**Show status table:**
+
+```
+Background Agents
+════════════════════════════════════════
+
+| Plan   | Status      | Elapsed  | Agent ID      |
+|--------|-------------|----------|---------------|
+| 10-01  | ✓ Complete  | 2m 15s   | agent_01H...  |
+| 10-02  | ⏳ Running   | 1m 30s   | agent_01H...  |
+| 10-04  | ✓ Complete  | 1m 45s   | agent_01H...  |
+
+Progress: 2/3 complete
+
+════════════════════════════════════════
+Wait for all: /gsd:status --wait
+```
+
+**Status icons:**
+- ✓ Complete
+- ⏳ Running
+- ✗ Failed
+- ⏸ Queued (waiting for dependency)
+</step>
+
+<step name="wait_mode">
+**If --wait flag provided:**
+
+For each agent with status "spawned", monitor until complete:
+
+Report as each completes:
+```
+⏳ Waiting for 3 agents...
+
+✓ [1/3] 10-01 complete (2m 15s)
+✓ [2/3] 10-04 complete (1m 45s)
+✓ [3/3] 10-02 complete (3m 30s)
+
+════════════════════════════════════════
+All agents complete!
+
+Total time: 3m 30s (parallel)
+Sequential estimate: 7m 30s
+Time saved: ~4m (53%)
+════════════════════════════════════════
+```
+
+Update agent-history.json with completion status for each.
+</step>
+
+<step name="next_steps">
+**After all complete (or if already complete):**
+
+```
+---
+
+## ▶ Next Up
+
+All parallel agents finished. Review results:
+
+`/gsd:progress`
+
+*`/clear` first → fresh context window*
+
+---
+```
+</step>
+
+</process>
+
+<success_criteria>
+- [ ] Reads agent-history.json for background agents
+- [ ] Updates history with current status
+- [ ] Shows simple status table
+- [ ] --wait flag blocks until all complete
+- [ ] Reports time savings vs sequential
+</success_criteria>

package/command/gsd/verify-work.md

@@ -3,19 +3,19 @@ name: gsd:verify-work
 description: Guide manual user acceptance testing of recently built features
 argument-hint: "[optional: phase or plan number, e.g., '4' or '04-02']"
 allowed-tools:
-  - Read
-  - Bash
-  - Glob
-  - Grep
-  - Edit
-  - Write
+  - read
+  - bash
+  - glob
+  - grep
+  - edit
+  - write
   - question
 ---
 
 <objective>
 Guide user through manual acceptance testing of recently built features.
 
-Purpose: Validate that what Claude thinks was built actually works from user's perspective. The USER performs all testing — Claude generates test checklist, guides process, and captures issues.
+Purpose: Validate that what OpenCode thinks was built actually works from user's perspective. The USER performs all testing — OpenCode generates a test checklist, guides process, and captures issues.
 
 Output: Validation of features, any issues logged to phase-scoped ISSUES.md
 </objective>
@@ -26,7 +26,7 @@ Output: Validation of features, any issues logged to phase-scoped ISSUES.md
 </execution_context>
 
 <context>
-Scope: $ARGUMENTS (optional)
+Scope: ($ARGUMENTS) (optional)
 - If provided: Test specific phase or plan (e.g., "4" or "04-02")
 - If not provided: Test most recently completed plan
 

package/get-shit-done/references/continuation-format.md

@@ -13,7 +13,7 @@ Standard format for presenting next steps after completing a command or workflow
 
 `{command to copy-paste}`
 
-<sub>`/clear` first → fresh context window</sub>
+*`/clear` first → fresh context window*
 
 ---
 
@@ -46,7 +46,7 @@ Standard format for presenting next steps after completing a command or workflow
 
 `/gsd:execute-plan .planning/phases/02-auth/02-03-PLAN.md`
 
-<sub>`/clear` first → fresh context window</sub>
+*`/clear` first → fresh context window*
 
 ---
 
@@ -67,11 +67,11 @@ Add note that this is the last plan and what comes after:
 ## ▶ Next Up
 
 **02-03: Refresh Token Rotation** — Add /api/auth/refresh with sliding expiry
-<sub>Final plan in Phase 2</sub>
+*Final plan in Phase 2*
 
 `/gsd:execute-plan .planning/phases/02-auth/02-03-PLAN.md`
 
-<sub>`/clear` first → fresh context window</sub>
+*`/clear` first → fresh context window*
 
 ---
 
@@ -93,7 +93,7 @@ Add note that this is the last plan and what comes after:
 
 `/gsd:plan-phase 2`
 
-<sub>`/clear` first → fresh context window</sub>
+*`/clear` first → fresh context window*
 
 ---
 
@@ -122,7 +122,7 @@ Show completion status before next action:
 
 `/gsd:plan-phase 3`
 
-<sub>`/clear` first → fresh context window</sub>
+*`/clear` first → fresh context window*
 
 ---
 
@@ -151,7 +151,7 @@ When there's no clear primary action:
 
 **To research unknowns:** `/gsd:research-phase 3`
 
-<sub>`/clear` first → fresh context window</sub>
+*`/clear` first → fresh context window*
 
 ---
 ```
@@ -171,7 +171,7 @@ All 4 phases shipped
 
 `/gsd:discuss-milestone`
 
-<sub>`/clear` first → fresh context window</sub>
+*`/clear` first → fresh context window*
 
 ---