claude-cook 1.10.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +21 -0
- package/README.md +607 -0
- package/agents/gsd-codebase-mapper.md +738 -0
- package/agents/gsd-debugger.md +1203 -0
- package/agents/gsd-executor.md +784 -0
- package/agents/gsd-integration-checker.md +423 -0
- package/agents/gsd-phase-researcher.md +641 -0
- package/agents/gsd-plan-checker.md +745 -0
- package/agents/gsd-planner.md +1386 -0
- package/agents/gsd-pm.md +331 -0
- package/agents/gsd-project-researcher.md +865 -0
- package/agents/gsd-research-synthesizer.md +256 -0
- package/agents/gsd-roadmapper.md +605 -0
- package/agents/gsd-verifier.md +778 -0
- package/bin/install.js +1477 -0
- package/commands/gsd/add-phase.md +207 -0
- package/commands/gsd/add-todo.md +193 -0
- package/commands/gsd/audit-milestone.md +277 -0
- package/commands/gsd/check-todos.md +228 -0
- package/commands/gsd/complete-milestone.md +136 -0
- package/commands/gsd/debug.md +169 -0
- package/commands/gsd/discuss-phase.md +86 -0
- package/commands/gsd/execute-phase.md +339 -0
- package/commands/gsd/help.md +545 -0
- package/commands/gsd/insert-phase.md +227 -0
- package/commands/gsd/join-discord.md +18 -0
- package/commands/gsd/list-phase-assumptions.md +50 -0
- package/commands/gsd/map-codebase.md +71 -0
- package/commands/gsd/new-milestone.md +721 -0
- package/commands/gsd/new-project.md +1008 -0
- package/commands/gsd/pause-work.md +134 -0
- package/commands/gsd/plan-milestone-gaps.md +295 -0
- package/commands/gsd/plan-phase.md +525 -0
- package/commands/gsd/pm-check.md +115 -0
- package/commands/gsd/pm-replan.md +102 -0
- package/commands/gsd/pm-start.md +218 -0
- package/commands/gsd/pm-status.md +116 -0
- package/commands/gsd/pm-stop.md +72 -0
- package/commands/gsd/progress.md +415 -0
- package/commands/gsd/quick.md +309 -0
- package/commands/gsd/remove-phase.md +349 -0
- package/commands/gsd/research-phase.md +200 -0
- package/commands/gsd/resume-work.md +40 -0
- package/commands/gsd/set-profile.md +106 -0
- package/commands/gsd/settings.md +151 -0
- package/commands/gsd/update.md +172 -0
- package/commands/gsd/verify-work.md +219 -0
- package/get-shit-done/references/checkpoints.md +1078 -0
- package/get-shit-done/references/continuation-format.md +249 -0
- package/get-shit-done/references/git-integration.md +254 -0
- package/get-shit-done/references/model-profiles.md +73 -0
- package/get-shit-done/references/planning-config.md +189 -0
- package/get-shit-done/references/questioning.md +141 -0
- package/get-shit-done/references/tdd.md +263 -0
- package/get-shit-done/references/ui-brand.md +172 -0
- package/get-shit-done/references/verification-patterns.md +612 -0
- package/get-shit-done/references/vibe-kanban.md +142 -0
- package/get-shit-done/templates/DEBUG.md +159 -0
- package/get-shit-done/templates/UAT.md +247 -0
- package/get-shit-done/templates/codebase/architecture.md +255 -0
- package/get-shit-done/templates/codebase/concerns.md +310 -0
- package/get-shit-done/templates/codebase/conventions.md +307 -0
- package/get-shit-done/templates/codebase/integrations.md +280 -0
- package/get-shit-done/templates/codebase/stack.md +186 -0
- package/get-shit-done/templates/codebase/structure.md +285 -0
- package/get-shit-done/templates/codebase/testing.md +480 -0
- package/get-shit-done/templates/config.json +35 -0
- package/get-shit-done/templates/context.md +283 -0
- package/get-shit-done/templates/continue-here.md +78 -0
- package/get-shit-done/templates/debug-subagent-prompt.md +91 -0
- package/get-shit-done/templates/discovery.md +146 -0
- package/get-shit-done/templates/milestone-archive.md +123 -0
- package/get-shit-done/templates/milestone.md +115 -0
- package/get-shit-done/templates/phase-prompt.md +567 -0
- package/get-shit-done/templates/planner-subagent-prompt.md +117 -0
- package/get-shit-done/templates/pm-config.md +55 -0
- package/get-shit-done/templates/pm-log.md +27 -0
- package/get-shit-done/templates/project.md +184 -0
- package/get-shit-done/templates/requirements.md +231 -0
- package/get-shit-done/templates/research-project/ARCHITECTURE.md +204 -0
- package/get-shit-done/templates/research-project/FEATURES.md +147 -0
- package/get-shit-done/templates/research-project/PITFALLS.md +200 -0
- package/get-shit-done/templates/research-project/STACK.md +120 -0
- package/get-shit-done/templates/research-project/SUMMARY.md +170 -0
- package/get-shit-done/templates/research.md +529 -0
- package/get-shit-done/templates/roadmap.md +202 -0
- package/get-shit-done/templates/state.md +205 -0
- package/get-shit-done/templates/summary.md +246 -0
- package/get-shit-done/templates/ticket-map.md +28 -0
- package/get-shit-done/templates/user-setup.md +311 -0
- package/get-shit-done/templates/verification-report.md +322 -0
- package/get-shit-done/workflows/complete-milestone.md +903 -0
- package/get-shit-done/workflows/diagnose-issues.md +231 -0
- package/get-shit-done/workflows/discovery-phase.md +289 -0
- package/get-shit-done/workflows/discuss-phase.md +433 -0
- package/get-shit-done/workflows/execute-phase.md +671 -0
- package/get-shit-done/workflows/execute-plan.md +1844 -0
- package/get-shit-done/workflows/list-phase-assumptions.md +178 -0
- package/get-shit-done/workflows/map-codebase.md +322 -0
- package/get-shit-done/workflows/pm-check.md +210 -0
- package/get-shit-done/workflows/pm-dispatch.md +104 -0
- package/get-shit-done/workflows/pm-replan.md +203 -0
- package/get-shit-done/workflows/pm-sync.md +130 -0
- package/get-shit-done/workflows/resume-project.md +307 -0
- package/get-shit-done/workflows/transition.md +556 -0
- package/get-shit-done/workflows/verify-phase.md +628 -0
- package/get-shit-done/workflows/verify-work.md +596 -0
- package/hooks/dist/gsd-check-update.js +61 -0
- package/hooks/dist/gsd-statusline.js +87 -0
- package/package.json +47 -0
- package/scripts/build-hooks.js +42 -0
- package/scripts/pm-loop.sh +155 -0
|
@@ -0,0 +1,228 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: gsd:check-todos
|
|
3
|
+
description: List pending todos and select one to work on
|
|
4
|
+
argument-hint: [area filter]
|
|
5
|
+
allowed-tools:
|
|
6
|
+
- Read
|
|
7
|
+
- Write
|
|
8
|
+
- Bash
|
|
9
|
+
- Glob
|
|
10
|
+
- AskUserQuestion
|
|
11
|
+
---
|
|
12
|
+
|
|
13
|
+
<objective>
|
|
14
|
+
List all pending todos, allow selection, load full context for the selected todo, and route to appropriate action.
|
|
15
|
+
|
|
16
|
+
Enables reviewing captured ideas and deciding what to work on next.
|
|
17
|
+
</objective>
|
|
18
|
+
|
|
19
|
+
<context>
|
|
20
|
+
@.planning/STATE.md
|
|
21
|
+
@.planning/ROADMAP.md
|
|
22
|
+
</context>
|
|
23
|
+
|
|
24
|
+
<process>
|
|
25
|
+
|
|
26
|
+
<step name="check_exist">
|
|
27
|
+
```bash
|
|
28
|
+
TODO_COUNT=$(ls .planning/todos/pending/*.md 2>/dev/null | wc -l | tr -d ' ')
|
|
29
|
+
echo "Pending todos: $TODO_COUNT"
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
If count is 0:
|
|
33
|
+
```
|
|
34
|
+
No pending todos.
|
|
35
|
+
|
|
36
|
+
Todos are captured during work sessions with /gsd:add-todo.
|
|
37
|
+
|
|
38
|
+
---
|
|
39
|
+
|
|
40
|
+
Would you like to:
|
|
41
|
+
|
|
42
|
+
1. Continue with current phase (/gsd:progress)
|
|
43
|
+
2. Add a todo now (/gsd:add-todo)
|
|
44
|
+
```
|
|
45
|
+
|
|
46
|
+
Exit.
|
|
47
|
+
</step>
|
|
48
|
+
|
|
49
|
+
<step name="parse_filter">
|
|
50
|
+
Check for area filter in arguments:
|
|
51
|
+
- `/gsd:check-todos` → show all
|
|
52
|
+
- `/gsd:check-todos api` → filter to area:api only
|
|
53
|
+
</step>
|
|
54
|
+
|
|
55
|
+
<step name="list_todos">
|
|
56
|
+
```bash
|
|
57
|
+
for file in .planning/todos/pending/*.md; do
|
|
58
|
+
created=$(grep "^created:" "$file" | cut -d' ' -f2)
|
|
59
|
+
title=$(grep "^title:" "$file" | cut -d':' -f2- | xargs)
|
|
60
|
+
area=$(grep "^area:" "$file" | cut -d' ' -f2)
|
|
61
|
+
echo "$created|$title|$area|$file"
|
|
62
|
+
done | sort
|
|
63
|
+
```
|
|
64
|
+
|
|
65
|
+
Apply area filter if specified. Display as numbered list:
|
|
66
|
+
|
|
67
|
+
```
|
|
68
|
+
Pending Todos:
|
|
69
|
+
|
|
70
|
+
1. Add auth token refresh (api, 2d ago)
|
|
71
|
+
2. Fix modal z-index issue (ui, 1d ago)
|
|
72
|
+
3. Refactor database connection pool (database, 5h ago)
|
|
73
|
+
|
|
74
|
+
---
|
|
75
|
+
|
|
76
|
+
Reply with a number to view details, or:
|
|
77
|
+
- `/gsd:check-todos [area]` to filter by area
|
|
78
|
+
- `q` to exit
|
|
79
|
+
```
|
|
80
|
+
|
|
81
|
+
Format age as relative time.
|
|
82
|
+
</step>
|
|
83
|
+
|
|
84
|
+
<step name="handle_selection">
|
|
85
|
+
Wait for user to reply with a number.
|
|
86
|
+
|
|
87
|
+
If valid: load selected todo, proceed.
|
|
88
|
+
If invalid: "Invalid selection. Reply with a number (1-[N]) or `q` to exit."
|
|
89
|
+
</step>
|
|
90
|
+
|
|
91
|
+
<step name="load_context">
|
|
92
|
+
Read the todo file completely. Display:
|
|
93
|
+
|
|
94
|
+
```
|
|
95
|
+
## [title]
|
|
96
|
+
|
|
97
|
+
**Area:** [area]
|
|
98
|
+
**Created:** [date] ([relative time] ago)
|
|
99
|
+
**Files:** [list or "None"]
|
|
100
|
+
|
|
101
|
+
### Problem
|
|
102
|
+
[problem section content]
|
|
103
|
+
|
|
104
|
+
### Solution
|
|
105
|
+
[solution section content]
|
|
106
|
+
```
|
|
107
|
+
|
|
108
|
+
If `files` field has entries, read and briefly summarize each.
|
|
109
|
+
</step>
|
|
110
|
+
|
|
111
|
+
<step name="check_roadmap">
|
|
112
|
+
```bash
|
|
113
|
+
ls .planning/ROADMAP.md 2>/dev/null && echo "Roadmap exists"
|
|
114
|
+
```
|
|
115
|
+
|
|
116
|
+
If roadmap exists:
|
|
117
|
+
1. Check if todo's area matches an upcoming phase
|
|
118
|
+
2. Check if todo's files overlap with a phase's scope
|
|
119
|
+
3. Note any match for action options
|
|
120
|
+
</step>
|
|
121
|
+
|
|
122
|
+
<step name="offer_actions">
|
|
123
|
+
**If todo maps to a roadmap phase:**
|
|
124
|
+
|
|
125
|
+
Use AskUserQuestion:
|
|
126
|
+
- header: "Action"
|
|
127
|
+
- question: "This todo relates to Phase [N]: [name]. What would you like to do?"
|
|
128
|
+
- options:
|
|
129
|
+
- "Work on it now" — move to done, start working
|
|
130
|
+
- "Add to phase plan" — include when planning Phase [N]
|
|
131
|
+
- "Brainstorm approach" — think through before deciding
|
|
132
|
+
- "Put it back" — return to list
|
|
133
|
+
|
|
134
|
+
**If no roadmap match:**
|
|
135
|
+
|
|
136
|
+
Use AskUserQuestion:
|
|
137
|
+
- header: "Action"
|
|
138
|
+
- question: "What would you like to do with this todo?"
|
|
139
|
+
- options:
|
|
140
|
+
- "Work on it now" — move to done, start working
|
|
141
|
+
- "Create a phase" — /gsd:add-phase with this scope
|
|
142
|
+
- "Brainstorm approach" — think through before deciding
|
|
143
|
+
- "Put it back" — return to list
|
|
144
|
+
</step>
|
|
145
|
+
|
|
146
|
+
<step name="execute_action">
|
|
147
|
+
**Work on it now:**
|
|
148
|
+
```bash
|
|
149
|
+
mv ".planning/todos/pending/[filename]" ".planning/todos/done/"
|
|
150
|
+
```
|
|
151
|
+
Update STATE.md todo count. Present problem/solution context. Begin work or ask how to proceed.
|
|
152
|
+
|
|
153
|
+
**Add to phase plan:**
|
|
154
|
+
Note todo reference in phase planning notes. Keep in pending. Return to list or exit.
|
|
155
|
+
|
|
156
|
+
**Create a phase:**
|
|
157
|
+
Display: `/gsd:add-phase [description from todo]`
|
|
158
|
+
Keep in pending. User runs command in fresh context.
|
|
159
|
+
|
|
160
|
+
**Brainstorm approach:**
|
|
161
|
+
Keep in pending. Start discussion about problem and approaches.
|
|
162
|
+
|
|
163
|
+
**Put it back:**
|
|
164
|
+
Return to list_todos step.
|
|
165
|
+
</step>
|
|
166
|
+
|
|
167
|
+
<step name="update_state">
|
|
168
|
+
After any action that changes todo count:
|
|
169
|
+
|
|
170
|
+
```bash
|
|
171
|
+
ls .planning/todos/pending/*.md 2>/dev/null | wc -l
|
|
172
|
+
```
|
|
173
|
+
|
|
174
|
+
Update STATE.md "### Pending Todos" section if exists.
|
|
175
|
+
</step>
|
|
176
|
+
|
|
177
|
+
<step name="git_commit">
|
|
178
|
+
If todo was moved to done/, commit the change:
|
|
179
|
+
|
|
180
|
+
**Check planning config:**
|
|
181
|
+
|
|
182
|
+
```bash
|
|
183
|
+
COMMIT_PLANNING_DOCS=$(cat .planning/config.json 2>/dev/null | grep -o '"commit_docs"[[:space:]]*:[[:space:]]*[^,}]*' | grep -o 'true\|false' || echo "true")
|
|
184
|
+
git check-ignore -q .planning 2>/dev/null && COMMIT_PLANNING_DOCS=false
|
|
185
|
+
```
|
|
186
|
+
|
|
187
|
+
**If `COMMIT_PLANNING_DOCS=false`:** Skip git operations, log "Todo moved (not committed - commit_docs: false)"
|
|
188
|
+
|
|
189
|
+
**If `COMMIT_PLANNING_DOCS=true` (default):**
|
|
190
|
+
|
|
191
|
+
```bash
|
|
192
|
+
git add .planning/todos/done/[filename]
|
|
193
|
+
git rm --cached .planning/todos/pending/[filename] 2>/dev/null || true
|
|
194
|
+
[ -f .planning/STATE.md ] && git add .planning/STATE.md
|
|
195
|
+
git commit -m "$(cat <<'EOF'
|
|
196
|
+
docs: start work on todo - [title]
|
|
197
|
+
|
|
198
|
+
Moved to done/, beginning implementation.
|
|
199
|
+
EOF
|
|
200
|
+
)"
|
|
201
|
+
```
|
|
202
|
+
|
|
203
|
+
Confirm: "Committed: docs: start work on todo - [title]"
|
|
204
|
+
</step>
|
|
205
|
+
|
|
206
|
+
</process>
|
|
207
|
+
|
|
208
|
+
<output>
|
|
209
|
+
- Moved todo to `.planning/todos/done/` (if "Work on it now")
|
|
210
|
+
- Updated `.planning/STATE.md` (if todo count changed)
|
|
211
|
+
</output>
|
|
212
|
+
|
|
213
|
+
<anti_patterns>
|
|
214
|
+
- Don't delete todos — move to done/ when work begins
|
|
215
|
+
- Don't start work without moving to done/ first
|
|
216
|
+
- Don't create plans from this command — route to /gsd:plan-phase or /gsd:add-phase
|
|
217
|
+
</anti_patterns>
|
|
218
|
+
|
|
219
|
+
<success_criteria>
|
|
220
|
+
- [ ] All pending todos listed with title, area, age
|
|
221
|
+
- [ ] Area filter applied if specified
|
|
222
|
+
- [ ] Selected todo's full context loaded
|
|
223
|
+
- [ ] Roadmap context checked for phase match
|
|
224
|
+
- [ ] Appropriate actions offered
|
|
225
|
+
- [ ] Selected action executed
|
|
226
|
+
- [ ] STATE.md updated if todo count changed
|
|
227
|
+
- [ ] Changes committed to git (if todo moved to done/)
|
|
228
|
+
</success_criteria>
|
|
@@ -0,0 +1,136 @@
|
|
|
1
|
+
---
|
|
2
|
+
type: prompt
|
|
3
|
+
name: gsd:complete-milestone
|
|
4
|
+
description: Archive completed milestone and prepare for next version
|
|
5
|
+
argument-hint: <version>
|
|
6
|
+
allowed-tools:
|
|
7
|
+
- Read
|
|
8
|
+
- Write
|
|
9
|
+
- Bash
|
|
10
|
+
---
|
|
11
|
+
|
|
12
|
+
<objective>
|
|
13
|
+
Mark milestone {{version}} complete, archive to milestones/, and update ROADMAP.md and REQUIREMENTS.md.
|
|
14
|
+
|
|
15
|
+
Purpose: Create historical record of shipped version, archive milestone artifacts (roadmap + requirements), and prepare for next milestone.
|
|
16
|
+
Output: Milestone archived (roadmap + requirements), PROJECT.md evolved, git tagged.
|
|
17
|
+
</objective>
|
|
18
|
+
|
|
19
|
+
<execution_context>
|
|
20
|
+
**Load these files NOW (before proceeding):**
|
|
21
|
+
|
|
22
|
+
- @~/.claude/get-shit-done/workflows/complete-milestone.md (main workflow)
|
|
23
|
+
- @~/.claude/get-shit-done/templates/milestone-archive.md (archive template)
|
|
24
|
+
</execution_context>
|
|
25
|
+
|
|
26
|
+
<context>
|
|
27
|
+
**Project files:**
|
|
28
|
+
- `.planning/ROADMAP.md`
|
|
29
|
+
- `.planning/REQUIREMENTS.md`
|
|
30
|
+
- `.planning/STATE.md`
|
|
31
|
+
- `.planning/PROJECT.md`
|
|
32
|
+
|
|
33
|
+
**User input:**
|
|
34
|
+
|
|
35
|
+
- Version: {{version}} (e.g., "1.0", "1.1", "2.0")
|
|
36
|
+
</context>
|
|
37
|
+
|
|
38
|
+
<process>
|
|
39
|
+
|
|
40
|
+
**Follow complete-milestone.md workflow:**
|
|
41
|
+
|
|
42
|
+
0. **Check for audit:**
|
|
43
|
+
|
|
44
|
+
- Look for `.planning/v{{version}}-MILESTONE-AUDIT.md`
|
|
45
|
+
- If missing or stale: recommend `/gsd:audit-milestone` first
|
|
46
|
+
- If audit status is `gaps_found`: recommend `/gsd:plan-milestone-gaps` first
|
|
47
|
+
- If audit status is `passed`: proceed to step 1
|
|
48
|
+
|
|
49
|
+
```markdown
|
|
50
|
+
## Pre-flight Check
|
|
51
|
+
|
|
52
|
+
{If no v{{version}}-MILESTONE-AUDIT.md:}
|
|
53
|
+
⚠ No milestone audit found. Run `/gsd:audit-milestone` first to verify
|
|
54
|
+
requirements coverage, cross-phase integration, and E2E flows.
|
|
55
|
+
|
|
56
|
+
{If audit has gaps:}
|
|
57
|
+
⚠ Milestone audit found gaps. Run `/gsd:plan-milestone-gaps` to create
|
|
58
|
+
phases that close the gaps, or proceed anyway to accept as tech debt.
|
|
59
|
+
|
|
60
|
+
{If audit passed:}
|
|
61
|
+
✓ Milestone audit passed. Proceeding with completion.
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
1. **Verify readiness:**
|
|
65
|
+
|
|
66
|
+
- Check all phases in milestone have completed plans (SUMMARY.md exists)
|
|
67
|
+
- Present milestone scope and stats
|
|
68
|
+
- Wait for confirmation
|
|
69
|
+
|
|
70
|
+
2. **Gather stats:**
|
|
71
|
+
|
|
72
|
+
- Count phases, plans, tasks
|
|
73
|
+
- Calculate git range, file changes, LOC
|
|
74
|
+
- Extract timeline from git log
|
|
75
|
+
- Present summary, confirm
|
|
76
|
+
|
|
77
|
+
3. **Extract accomplishments:**
|
|
78
|
+
|
|
79
|
+
- Read all phase SUMMARY.md files in milestone range
|
|
80
|
+
- Extract 4-6 key accomplishments
|
|
81
|
+
- Present for approval
|
|
82
|
+
|
|
83
|
+
4. **Archive milestone:**
|
|
84
|
+
|
|
85
|
+
- Create `.planning/milestones/v{{version}}-ROADMAP.md`
|
|
86
|
+
- Extract full phase details from ROADMAP.md
|
|
87
|
+
- Fill milestone-archive.md template
|
|
88
|
+
- Update ROADMAP.md to one-line summary with link
|
|
89
|
+
|
|
90
|
+
5. **Archive requirements:**
|
|
91
|
+
|
|
92
|
+
- Create `.planning/milestones/v{{version}}-REQUIREMENTS.md`
|
|
93
|
+
- Mark all v1 requirements as complete (checkboxes checked)
|
|
94
|
+
- Note requirement outcomes (validated, adjusted, dropped)
|
|
95
|
+
- Delete `.planning/REQUIREMENTS.md` (fresh one created for next milestone)
|
|
96
|
+
|
|
97
|
+
6. **Update PROJECT.md:**
|
|
98
|
+
|
|
99
|
+
- Add "Current State" section with shipped version
|
|
100
|
+
- Add "Next Milestone Goals" section
|
|
101
|
+
- Archive previous content in `<details>` (if v1.1+)
|
|
102
|
+
|
|
103
|
+
7. **Commit and tag:**
|
|
104
|
+
|
|
105
|
+
- Stage: MILESTONES.md, PROJECT.md, ROADMAP.md, STATE.md, archive files
|
|
106
|
+
- Commit: `chore: archive v{{version}} milestone`
|
|
107
|
+
- Tag: `git tag -a v{{version}} -m "[milestone summary]"`
|
|
108
|
+
- Ask about pushing tag
|
|
109
|
+
|
|
110
|
+
8. **Offer next steps:**
|
|
111
|
+
- `/gsd:new-milestone` — start next milestone (questioning → research → requirements → roadmap)
|
|
112
|
+
|
|
113
|
+
</process>
|
|
114
|
+
|
|
115
|
+
<success_criteria>
|
|
116
|
+
|
|
117
|
+
- Milestone archived to `.planning/milestones/v{{version}}-ROADMAP.md`
|
|
118
|
+
- Requirements archived to `.planning/milestones/v{{version}}-REQUIREMENTS.md`
|
|
119
|
+
- `.planning/REQUIREMENTS.md` deleted (fresh for next milestone)
|
|
120
|
+
- ROADMAP.md collapsed to one-line entry
|
|
121
|
+
- PROJECT.md updated with current state
|
|
122
|
+
- Git tag v{{version}} created
|
|
123
|
+
- Commit successful
|
|
124
|
+
- User knows next steps (including need for fresh requirements)
|
|
125
|
+
</success_criteria>
|
|
126
|
+
|
|
127
|
+
<critical_rules>
|
|
128
|
+
|
|
129
|
+
- **Load workflow first:** Read complete-milestone.md before executing
|
|
130
|
+
- **Verify completion:** All phases must have SUMMARY.md files
|
|
131
|
+
- **User confirmation:** Wait for approval at verification gates
|
|
132
|
+
- **Archive before deleting:** Always create archive files before updating/deleting originals
|
|
133
|
+
- **One-line summary:** Collapsed milestone in ROADMAP.md should be single line with link
|
|
134
|
+
- **Context efficiency:** Archive keeps ROADMAP.md and REQUIREMENTS.md constant size per milestone
|
|
135
|
+
- **Fresh requirements:** Next milestone starts with `/gsd:new-milestone` which includes requirements definition
|
|
136
|
+
</critical_rules>
|
|
@@ -0,0 +1,169 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: gsd:debug
|
|
3
|
+
description: Systematic debugging with persistent state across context resets
|
|
4
|
+
argument-hint: [issue description]
|
|
5
|
+
allowed-tools:
|
|
6
|
+
- Read
|
|
7
|
+
- Bash
|
|
8
|
+
- Task
|
|
9
|
+
- AskUserQuestion
|
|
10
|
+
---
|
|
11
|
+
|
|
12
|
+
<objective>
|
|
13
|
+
Debug issues using scientific method with subagent isolation.
|
|
14
|
+
|
|
15
|
+
**Orchestrator role:** Gather symptoms, spawn gsd-debugger agent, handle checkpoints, spawn continuations.
|
|
16
|
+
|
|
17
|
+
**Why subagent:** Investigation burns context fast (reading files, forming hypotheses, testing). Fresh 200k context per investigation. Main context stays lean for user interaction.
|
|
18
|
+
</objective>
|
|
19
|
+
|
|
20
|
+
<context>
|
|
21
|
+
User's issue: $ARGUMENTS
|
|
22
|
+
|
|
23
|
+
Check for active sessions:
|
|
24
|
+
```bash
|
|
25
|
+
ls .planning/debug/*.md 2>/dev/null | grep -v resolved | head -5
|
|
26
|
+
```
|
|
27
|
+
</context>
|
|
28
|
+
|
|
29
|
+
<process>
|
|
30
|
+
|
|
31
|
+
## 0. Resolve Model Profile
|
|
32
|
+
|
|
33
|
+
Read model profile for agent spawning:
|
|
34
|
+
|
|
35
|
+
```bash
|
|
36
|
+
MODEL_PROFILE=$(cat .planning/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
|
|
37
|
+
```
|
|
38
|
+
|
|
39
|
+
Default to "balanced" if not set.
|
|
40
|
+
|
|
41
|
+
**Model lookup table:**
|
|
42
|
+
|
|
43
|
+
| Agent | quality | balanced | budget |
|
|
44
|
+
|-------|---------|----------|--------|
|
|
45
|
+
| gsd-debugger | opus | sonnet | sonnet |
|
|
46
|
+
|
|
47
|
+
Store resolved model for use in Task calls below.
|
|
48
|
+
|
|
49
|
+
## 1. Check Active Sessions
|
|
50
|
+
|
|
51
|
+
If active sessions exist AND no $ARGUMENTS:
|
|
52
|
+
- List sessions with status, hypothesis, next action
|
|
53
|
+
- User picks number to resume OR describes new issue
|
|
54
|
+
|
|
55
|
+
If $ARGUMENTS provided OR user describes new issue:
|
|
56
|
+
- Continue to symptom gathering
|
|
57
|
+
|
|
58
|
+
## 2. Gather Symptoms (if new issue)
|
|
59
|
+
|
|
60
|
+
Use AskUserQuestion for each:
|
|
61
|
+
|
|
62
|
+
1. **Expected behavior** - What should happen?
|
|
63
|
+
2. **Actual behavior** - What happens instead?
|
|
64
|
+
3. **Error messages** - Any errors? (paste or describe)
|
|
65
|
+
4. **Timeline** - When did this start? Ever worked?
|
|
66
|
+
5. **Reproduction** - How do you trigger it?
|
|
67
|
+
|
|
68
|
+
After all gathered, confirm ready to investigate.
|
|
69
|
+
|
|
70
|
+
## 3. Spawn gsd-debugger Agent
|
|
71
|
+
|
|
72
|
+
Fill prompt and spawn:
|
|
73
|
+
|
|
74
|
+
```markdown
|
|
75
|
+
<objective>
|
|
76
|
+
Investigate issue: {slug}
|
|
77
|
+
|
|
78
|
+
**Summary:** {trigger}
|
|
79
|
+
</objective>
|
|
80
|
+
|
|
81
|
+
<symptoms>
|
|
82
|
+
expected: {expected}
|
|
83
|
+
actual: {actual}
|
|
84
|
+
errors: {errors}
|
|
85
|
+
reproduction: {reproduction}
|
|
86
|
+
timeline: {timeline}
|
|
87
|
+
</symptoms>
|
|
88
|
+
|
|
89
|
+
<mode>
|
|
90
|
+
symptoms_prefilled: true
|
|
91
|
+
goal: find_and_fix
|
|
92
|
+
</mode>
|
|
93
|
+
|
|
94
|
+
<debug_file>
|
|
95
|
+
Create: .planning/debug/{slug}.md
|
|
96
|
+
</debug_file>
|
|
97
|
+
```
|
|
98
|
+
|
|
99
|
+
```
|
|
100
|
+
Task(
|
|
101
|
+
prompt=filled_prompt,
|
|
102
|
+
subagent_type="gsd-debugger",
|
|
103
|
+
model="{debugger_model}",
|
|
104
|
+
description="Debug {slug}"
|
|
105
|
+
)
|
|
106
|
+
```
|
|
107
|
+
|
|
108
|
+
## 4. Handle Agent Return
|
|
109
|
+
|
|
110
|
+
**If `## ROOT CAUSE FOUND`:**
|
|
111
|
+
- Display root cause and evidence summary
|
|
112
|
+
- Offer options:
|
|
113
|
+
- "Fix now" - spawn fix subagent
|
|
114
|
+
- "Plan fix" - suggest /gsd:plan-phase --gaps
|
|
115
|
+
- "Manual fix" - done
|
|
116
|
+
|
|
117
|
+
**If `## CHECKPOINT REACHED`:**
|
|
118
|
+
- Present checkpoint details to user
|
|
119
|
+
- Get user response
|
|
120
|
+
- Spawn continuation agent (see step 5)
|
|
121
|
+
|
|
122
|
+
**If `## INVESTIGATION INCONCLUSIVE`:**
|
|
123
|
+
- Show what was checked and eliminated
|
|
124
|
+
- Offer options:
|
|
125
|
+
- "Continue investigating" - spawn new agent with additional context
|
|
126
|
+
- "Manual investigation" - done
|
|
127
|
+
- "Add more context" - gather more symptoms, spawn again
|
|
128
|
+
|
|
129
|
+
## 5. Spawn Continuation Agent (After Checkpoint)
|
|
130
|
+
|
|
131
|
+
When user responds to checkpoint, spawn fresh agent:
|
|
132
|
+
|
|
133
|
+
```markdown
|
|
134
|
+
<objective>
|
|
135
|
+
Continue debugging {slug}. Evidence is in the debug file.
|
|
136
|
+
</objective>
|
|
137
|
+
|
|
138
|
+
<prior_state>
|
|
139
|
+
Debug file: @.planning/debug/{slug}.md
|
|
140
|
+
</prior_state>
|
|
141
|
+
|
|
142
|
+
<checkpoint_response>
|
|
143
|
+
**Type:** {checkpoint_type}
|
|
144
|
+
**Response:** {user_response}
|
|
145
|
+
</checkpoint_response>
|
|
146
|
+
|
|
147
|
+
<mode>
|
|
148
|
+
goal: find_and_fix
|
|
149
|
+
</mode>
|
|
150
|
+
```
|
|
151
|
+
|
|
152
|
+
```
|
|
153
|
+
Task(
|
|
154
|
+
prompt=continuation_prompt,
|
|
155
|
+
subagent_type="gsd-debugger",
|
|
156
|
+
model="{debugger_model}",
|
|
157
|
+
description="Continue debug {slug}"
|
|
158
|
+
)
|
|
159
|
+
```
|
|
160
|
+
|
|
161
|
+
</process>
|
|
162
|
+
|
|
163
|
+
<success_criteria>
|
|
164
|
+
- [ ] Active sessions checked
|
|
165
|
+
- [ ] Symptoms gathered (if new)
|
|
166
|
+
- [ ] gsd-debugger spawned with context
|
|
167
|
+
- [ ] Checkpoints handled correctly
|
|
168
|
+
- [ ] Root cause confirmed before fixing
|
|
169
|
+
</success_criteria>
|
|
@@ -0,0 +1,86 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: gsd:discuss-phase
|
|
3
|
+
description: Gather phase context through adaptive questioning before planning
|
|
4
|
+
argument-hint: "<phase>"
|
|
5
|
+
allowed-tools:
|
|
6
|
+
- Read
|
|
7
|
+
- Write
|
|
8
|
+
- Bash
|
|
9
|
+
- Glob
|
|
10
|
+
- Grep
|
|
11
|
+
- AskUserQuestion
|
|
12
|
+
---
|
|
13
|
+
|
|
14
|
+
<objective>
|
|
15
|
+
Extract implementation decisions that downstream agents need — researcher and planner will use CONTEXT.md to know what to investigate and what choices are locked.
|
|
16
|
+
|
|
17
|
+
**How it works:**
|
|
18
|
+
1. Analyze the phase to identify gray areas (UI, UX, behavior, etc.)
|
|
19
|
+
2. Present gray areas — user selects which to discuss
|
|
20
|
+
3. Deep-dive each selected area until satisfied
|
|
21
|
+
4. Create CONTEXT.md with decisions that guide research and planning
|
|
22
|
+
|
|
23
|
+
**Output:** `{phase}-CONTEXT.md` — decisions clear enough that downstream agents can act without asking the user again
|
|
24
|
+
</objective>
|
|
25
|
+
|
|
26
|
+
<execution_context>
|
|
27
|
+
@~/.claude/get-shit-done/workflows/discuss-phase.md
|
|
28
|
+
@~/.claude/get-shit-done/templates/context.md
|
|
29
|
+
</execution_context>
|
|
30
|
+
|
|
31
|
+
<context>
|
|
32
|
+
Phase number: $ARGUMENTS (required)
|
|
33
|
+
|
|
34
|
+
**Load project state:**
|
|
35
|
+
@.planning/STATE.md
|
|
36
|
+
|
|
37
|
+
**Load roadmap:**
|
|
38
|
+
@.planning/ROADMAP.md
|
|
39
|
+
</context>
|
|
40
|
+
|
|
41
|
+
<process>
|
|
42
|
+
1. Validate phase number (error if missing or not in roadmap)
|
|
43
|
+
2. Check if CONTEXT.md exists (offer update/view/skip if yes)
|
|
44
|
+
3. **Analyze phase** — Identify domain and generate phase-specific gray areas
|
|
45
|
+
4. **Present gray areas** — Multi-select: which to discuss? (NO skip option)
|
|
46
|
+
5. **Deep-dive each area** — 4 questions per area, then offer more/next
|
|
47
|
+
6. **Write CONTEXT.md** — Sections match areas discussed
|
|
48
|
+
7. Offer next steps (research or plan)
|
|
49
|
+
|
|
50
|
+
**CRITICAL: Scope guardrail**
|
|
51
|
+
- Phase boundary from ROADMAP.md is FIXED
|
|
52
|
+
- Discussion clarifies HOW to implement, not WHETHER to add more
|
|
53
|
+
- If user suggests new capabilities: "That's its own phase. I'll note it for later."
|
|
54
|
+
- Capture deferred ideas — don't lose them, don't act on them
|
|
55
|
+
|
|
56
|
+
**Domain-aware gray areas:**
|
|
57
|
+
Gray areas depend on what's being built. Analyze the phase goal:
|
|
58
|
+
- Something users SEE → layout, density, interactions, states
|
|
59
|
+
- Something users CALL → responses, errors, auth, versioning
|
|
60
|
+
- Something users RUN → output format, flags, modes, error handling
|
|
61
|
+
- Something users READ → structure, tone, depth, flow
|
|
62
|
+
- Something being ORGANIZED → criteria, grouping, naming, exceptions
|
|
63
|
+
|
|
64
|
+
Generate 3-4 **phase-specific** gray areas, not generic categories.
|
|
65
|
+
|
|
66
|
+
**Probing depth:**
|
|
67
|
+
- Ask 4 questions per area before checking
|
|
68
|
+
- "More questions about [area], or move to next?"
|
|
69
|
+
- If more → ask 4 more, check again
|
|
70
|
+
- After all areas → "Ready to create context?"
|
|
71
|
+
|
|
72
|
+
**Do NOT ask about (Claude handles these):**
|
|
73
|
+
- Technical implementation
|
|
74
|
+
- Architecture choices
|
|
75
|
+
- Performance concerns
|
|
76
|
+
- Scope expansion
|
|
77
|
+
</process>
|
|
78
|
+
|
|
79
|
+
<success_criteria>
|
|
80
|
+
- Gray areas identified through intelligent analysis
|
|
81
|
+
- User chose which areas to discuss
|
|
82
|
+
- Each selected area explored until satisfied
|
|
83
|
+
- Scope creep redirected to deferred ideas
|
|
84
|
+
- CONTEXT.md captures decisions, not vague vision
|
|
85
|
+
- User knows next steps
|
|
86
|
+
</success_criteria>
|