get-shit-done-cc 1.4.21 → 1.4.23

package/README.md

@@ -251,7 +251,6 @@ GSD handles it for you:
 | `STATE.md` | Decisions, blockers, position — memory across sessions |
 | `PLAN.md` | Atomic task with XML structure, verification steps |
 | `SUMMARY.md` | What happened, what changed, committed to history |
-| `ISSUES.md` | Deferred enhancements tracked across sessions |
 | `todos/` | Captured ideas and tasks for later work |
 
 Size limits based on where Claude's quality degrades. Stay under, get consistent excellence.
@@ -342,7 +341,6 @@ You're never locked in. The system adapts.
 | `/gsd:list-phase-assumptions [N]` | See what Claude thinks before you correct it |
 | `/gsd:pause-work` | Create handoff file when stopping mid-phase |
 | `/gsd:resume-work` | Restore from last session |
-| `/gsd:consider-issues` | Review deferred issues, close resolved, identify urgent |
 | `/gsd:add-todo [desc]` | Capture idea or task from conversation for later |
 | `/gsd:check-todos [area]` | List pending todos, select one to work on |
 | `/gsd:debug [desc]` | Systematic debugging with persistent state across `/clear` |

package/commands/gsd/_archive/execute-phase.md

@@ -81,7 +81,6 @@ During execution, handle discoveries automatically:
 2. **Auto-add critical** - Security/correctness gaps, add and document
 3. **Auto-fix blockers** - Can't proceed without fix, do it and document
 4. **Ask about architectural** - Major structural changes, stop and ask user
-5. **Log enhancements** - Nice-to-haves, log to ISSUES.md, continue
 
 Only rule 4 requires user intervention.
 </deviation_rules>

package/commands/gsd/debug.md

@@ -9,19 +9,22 @@ allowed-tools:
   - Bash
   - Grep
   - Glob
+  - Task
   - AskUserQuestion
 ---
 
 <objective>
-Debug issues using scientific method with a persistent debug document that survives `/clear`.
+Debug issues using scientific method with subagent isolation for investigation.
 
-If resuming (no arguments and active session exists): pick up where you left off.
-If starting new: gather symptoms, then investigate autonomously.
+**Orchestrator role:** Gather symptoms interactively, spawn investigation subagent, handle checkpoints, spawn continuation agents as needed.
+
+**Why subagent:** Investigation burns context fast (reading files, forming hypotheses, testing). Fresh 200k context per investigation attempt. Main context stays lean for user interaction.
 </objective>
 
 <execution_context>
 @~/.claude/get-shit-done/workflows/debug.md
 @~/.claude/get-shit-done/templates/DEBUG.md
+@~/.claude/get-shit-done/templates/debug-subagent-prompt.md
 </execution_context>
 
 <context>
@@ -29,30 +32,170 @@ User's issue: $ARGUMENTS
 
 Check for active debug sessions:
 ```bash
-ls .planning/debug/*.md 2>/dev/null | head -5
+ls .planning/debug/*.md 2>/dev/null | grep -v resolved | head -5
 ```
 </context>
 
 <process>
-Follow the workflow in @~/.claude/get-shit-done/workflows/debug.md
 
-**Quick reference:**
+## 1. Check Active Sessions
+
+If active sessions exist AND no $ARGUMENTS:
+- List sessions with status, hypothesis, next action
+- User picks number to resume OR describes new issue
+
+If $ARGUMENTS provided OR user describes new issue:
+- Continue to symptom gathering
+
+## 2. Gather Symptoms (Main Context)
+
+Use AskUserQuestion for each:
+
+1. **Expected behavior** - What should happen?
+2. **Actual behavior** - What happens instead?
+3. **Error messages** - Any errors? (paste or describe)
+4. **Timeline** - When did this start? Ever worked?
+5. **Reproduction** - How do you trigger it?
+
+After each answer, note it. After all gathered, confirm ready to investigate.
+
+## 3. Create Debug File
+
+```bash
+mkdir -p .planning/debug
+```
+
+Create `.planning/debug/{slug}.md` with:
+- status: investigating
+- trigger: user's original description
+- Symptoms section filled from gathering
+- Empty Evidence, Eliminated, Resolution sections
+
+## 4. Spawn Investigation Subagent
 
-1. **Check for active sessions** - Offer to resume or start new
-2. **Gather symptoms** - What happened? What should happen? Errors? When?
-3. **Create DEBUG.md** - Document symptoms in `.planning/debug/[slug].md`
-4. **Investigate** - Evidence → Hypothesis → Test → Eliminate or Confirm
-5. **Fix and verify** - Minimal fix, verify against original symptoms
-6. **Archive** - Move to `.planning/debug/resolved/`
+Fill debug-subagent-prompt template with:
+- `{slug}`: Generated slug
+- `{trigger}`: Original issue description
+- `{expected}`: From symptom gathering
+- `{actual}`: From symptom gathering
+- `{errors}`: From symptom gathering
+- `{reproduction}`: From symptom gathering
+- `{timeline}`: From symptom gathering
+
+```
+Task(
+  prompt=filled_debug_subagent_prompt,
+  subagent_type="general-purpose",
+  description="Debug {slug}"
+)
+```
+
+## 5. Handle Subagent Return
+
+**If `## ROOT CAUSE FOUND`:**
+- Display root cause and evidence summary
+- Offer options:
+  - "Fix now" → spawn fix subagent
+  - "Plan fix" → suggest /gsd:plan-fix
+  - "Manual fix" → done
+
+**If `## CHECKPOINT REACHED`:**
+- Present checkpoint details to user
+- Get user response
+- Spawn continuation agent (see step 6)
+
+**If `## INVESTIGATION INCONCLUSIVE`:**
+- Show what was checked and eliminated
+- Offer options:
+  - "Continue investigating" → spawn new agent with additional context
+  - "Manual investigation" → done
+  - "Add more context" → gather more symptoms, spawn again
+
+## 6. Spawn Continuation Agent (After Checkpoint)
+
+When user responds to checkpoint, spawn fresh agent:
+
+```markdown
+<objective>
+Continue debugging {slug}.
+
+**DO NOT REDO** previous investigation. Evidence is in the debug file.
+</objective>
+
+<prior_state>
+Debug file: @.planning/debug/{slug}.md
+
+Read this file - it contains all evidence gathered so far.
+</prior_state>
+
+<checkpoint_response>
+**Checkpoint was:** {checkpoint_type}
+**User response:** {user_response}
+
+{interpretation based on checkpoint type}
+</checkpoint_response>
+
+<execution_context>
+@~/.claude/get-shit-done/workflows/debug.md
+@~/.claude/get-shit-done/templates/DEBUG.md
+</execution_context>
+
+<instructions>
+1. Read the debug file to understand current state
+2. Incorporate user's checkpoint response
+3. Continue investigation from Current Focus
+4. Update debug file continuously
+5. Return with ROOT CAUSE FOUND, CHECKPOINT REACHED, or INVESTIGATION INCONCLUSIVE
+</instructions>
+```
+
+## 7. Fix (Optional)
+
+If user chooses "Fix now" after root cause found:
+
+```markdown
+<objective>
+Fix the root cause identified in {slug} debug session.
+</objective>
+
+<context>
+Debug file: @.planning/debug/{slug}.md
+Root cause: {root_cause}
+Files involved: {files}
+</context>
+
+<instructions>
+1. Implement minimal fix addressing root cause
+2. Verify fix against original symptoms
+3. Update debug file Resolution section
+4. Commit with message referencing debug session
+5. Archive to .planning/debug/resolved/
+</instructions>
+```
 
-**Key principle:** The DEBUG.md is your memory. Update it constantly. It survives `/clear`.
 </process>
 
+<checkpoint_types>
+Subagent may return checkpoints for:
+
+**human-verify:** "Can you confirm you see X when you do Y?"
+- Present verification request
+- User responds with confirmation or what they see instead
+
+**human-action:** "I need you to run this command / check this thing"
+- Present action request
+- User responds "done" or with results
+
+**decision:** "Should I investigate path A or path B?"
+- Present options with context
+- User picks direction
+</checkpoint_types>
+
 <success_criteria>
-- [ ] Active sessions checked before starting new
-- [ ] Symptoms gathered through AskUserQuestion (not inline questions)
-- [ ] DEBUG.md tracks all investigation state
-- [ ] Scientific method followed (not random fixes)
+- [ ] Symptoms gathered interactively in main context
+- [ ] Investigation runs in subagent (fresh context)
+- [ ] Debug file tracks all state across agent boundaries
+- [ ] Checkpoints handled via continuation agents
 - [ ] Root cause confirmed with evidence before fixing
 - [ ] Fix verified and session archived
 </success_criteria>

package/commands/gsd/execute-phase.md

@@ -99,7 +99,6 @@ During execution, handle discoveries automatically:
 2. **Auto-add critical** - Security/correctness gaps, add and document
 3. **Auto-fix blockers** - Can't proceed without fix, do it and document
 4. **Ask about architectural** - Major structural changes, stop and ask user
-5. **Log enhancements** - Nice-to-haves, log to ISSUES.md, continue
 
 Only rule 4 requires user intervention.
 </deviation_rules>

package/commands/gsd/help.md

@@ -235,19 +235,6 @@ Create context handoff when pausing work mid-phase.
 
 Usage: `/gsd:pause-work`
 
-### Issue Management
-
-**`/gsd:consider-issues`**
-Review deferred issues with codebase context.
-
-- Analyzes all open issues against current codebase state
-- Identifies resolved issues (can close)
-- Identifies urgent issues (should address now)
-- Identifies natural fits for upcoming phases
-- Offers batch actions (close, insert phase, note for planning)
-
-Usage: `/gsd:consider-issues`
-
 ### Debugging
 
 **`/gsd:debug [issue description]`**
@@ -300,7 +287,6 @@ Show this command reference.
 ├── PROJECT.md            # Project vision
 ├── ROADMAP.md            # Current phase breakdown
 ├── STATE.md              # Project memory & context
-├── ISSUES.md             # Deferred enhancements (created when needed)
 ├── config.json           # Workflow mode & gates
 ├── todos/                # Captured ideas and tasks
 │   ├── pending/          # Todos waiting to be worked on

package/commands/gsd/progress.md

@@ -55,7 +55,7 @@ If missing STATE.md or ROADMAP.md: inform what's missing, suggest running `/gsd:
 
 - From STATE.md: current phase, plan number, status
 - Calculate: total plans, completed plans, remaining plans
-- Note any blockers, concerns, or deferred issues
+- Note any blockers or concerns
 - 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`
@@ -82,8 +82,8 @@ CONTEXT: [✓ if CONTEXT.md exists | - if not]
 - [decision 1 from STATE.md]
 - [decision 2]
 
-## Open Issues
-- [any deferred issues or blockers]
+## Blockers/Concerns
+- [any blockers or concerns from STATE.md]
 
 ## Pending Todos
 - [count] pending — /gsd:check-todos to review

package/get-shit-done/templates/UAT.md

@@ -243,15 +243,3 @@ skipped: 0
   root_cause: useEffect in CommentList.tsx missing commentCount dependency
 ```
 </good_example>
-
-<difference_from_issues_md>
-
-| UAT.md | ISSUES.md (global) |
-|--------|-------------------|
-| Created by /gsd:verify-work | Created by deviation rule 5 during execution |
-| Tracks test session state | Tracks deferred enhancements |
-| Phase-scoped, one per phase | Global, one per project |
-| Feeds into /gsd:plan-fix | Feeds into /gsd:consider-issues |
-| Contains pass/fail/skip results | Contains only deferred items |
-
-</difference_from_issues_md>