gsd-codex-cli 1.20.0
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/.codex/prompts/gsd-add-phase.md +44 -0
- package/.codex/prompts/gsd-add-todo.md +43 -0
- package/.codex/prompts/gsd-audit-milestone.md +43 -0
- package/.codex/prompts/gsd-check-todos.md +43 -0
- package/.codex/prompts/gsd-complete-milestone.md +43 -0
- package/.codex/prompts/gsd-debug.md +46 -0
- package/.codex/prompts/gsd-discuss-phase.md +43 -0
- package/.codex/prompts/gsd-execute-phase.md +43 -0
- package/.codex/prompts/gsd-help.md +43 -0
- package/.codex/prompts/gsd-insert-phase.md +43 -0
- package/.codex/prompts/gsd-list-phase-assumptions.md +43 -0
- package/.codex/prompts/gsd-map-codebase.md +43 -0
- package/.codex/prompts/gsd-new-milestone.md +43 -0
- package/.codex/prompts/gsd-new-project.md +43 -0
- package/.codex/prompts/gsd-pause-work.md +43 -0
- package/.codex/prompts/gsd-plan-milestone-gaps.md +43 -0
- package/.codex/prompts/gsd-plan-phase.md +43 -0
- package/.codex/prompts/gsd-progress.md +43 -0
- package/.codex/prompts/gsd-quick.md +43 -0
- package/.codex/prompts/gsd-remove-phase.md +43 -0
- package/.codex/prompts/gsd-research-phase.md +43 -0
- package/.codex/prompts/gsd-resume-work.md +43 -0
- package/.codex/prompts/gsd-set-profile.md +43 -0
- package/.codex/prompts/gsd-settings.md +43 -0
- package/.codex/prompts/gsd-update.md +43 -0
- package/.codex/prompts/gsd-verify-work.md +43 -0
- package/.codex/skills/get-shit-done-codex/SKILL.md +65 -0
- package/.codex/skills/get-shit-done-codex/references/compat.md +32 -0
- package/.codex/skills/get-shit-done-codex/references/windows.md +23 -0
- package/CHANGELOG.md +1434 -0
- package/LICENSE +21 -0
- package/README.md +690 -0
- package/agents/gsd-codebase-mapper.md +761 -0
- package/agents/gsd-debugger.md +1198 -0
- package/agents/gsd-executor.md +419 -0
- package/agents/gsd-integration-checker.md +423 -0
- package/agents/gsd-phase-researcher.md +469 -0
- package/agents/gsd-plan-checker.md +622 -0
- package/agents/gsd-planner.md +1159 -0
- package/agents/gsd-project-researcher.md +618 -0
- package/agents/gsd-research-synthesizer.md +236 -0
- package/agents/gsd-roadmapper.md +639 -0
- package/agents/gsd-verifier.md +541 -0
- package/bin/install-codex.js +100 -0
- package/bin/install.js +1806 -0
- package/commands/gsd/add-phase.md +39 -0
- package/commands/gsd/add-todo.md +42 -0
- package/commands/gsd/audit-milestone.md +42 -0
- package/commands/gsd/check-todos.md +41 -0
- package/commands/gsd/cleanup.md +18 -0
- package/commands/gsd/complete-milestone.md +136 -0
- package/commands/gsd/debug.md +162 -0
- package/commands/gsd/discuss-phase.md +87 -0
- package/commands/gsd/execute-phase.md +42 -0
- package/commands/gsd/health.md +22 -0
- package/commands/gsd/help.md +22 -0
- package/commands/gsd/insert-phase.md +33 -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 +51 -0
- package/commands/gsd/new-project.md +42 -0
- package/commands/gsd/pause-work.md +35 -0
- package/commands/gsd/plan-milestone-gaps.md +40 -0
- package/commands/gsd/plan-phase.md +44 -0
- package/commands/gsd/progress.md +24 -0
- package/commands/gsd/quick.md +40 -0
- package/commands/gsd/reapply-patches.md +110 -0
- package/commands/gsd/remove-phase.md +32 -0
- package/commands/gsd/research-phase.md +187 -0
- package/commands/gsd/resume-work.md +40 -0
- package/commands/gsd/set-profile.md +34 -0
- package/commands/gsd/settings.md +36 -0
- package/commands/gsd/update.md +37 -0
- package/commands/gsd/verify-work.md +39 -0
- package/get-shit-done/bin/gsd-tools.cjs +5243 -0
- package/get-shit-done/bin/gsd-tools.test.cjs +2273 -0
- package/get-shit-done/references/checkpoints.md +775 -0
- package/get-shit-done/references/continuation-format.md +249 -0
- package/get-shit-done/references/decimal-phase-calculation.md +65 -0
- package/get-shit-done/references/git-integration.md +248 -0
- package/get-shit-done/references/git-planning-commit.md +38 -0
- package/get-shit-done/references/model-profile-resolution.md +34 -0
- package/get-shit-done/references/model-profiles.md +92 -0
- package/get-shit-done/references/phase-argument-parsing.md +61 -0
- package/get-shit-done/references/planning-config.md +196 -0
- package/get-shit-done/references/questioning.md +145 -0
- package/get-shit-done/references/tdd.md +263 -0
- package/get-shit-done/references/ui-brand.md +160 -0
- package/get-shit-done/references/verification-patterns.md +612 -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 +36 -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/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 +552 -0
- package/get-shit-done/templates/roadmap.md +202 -0
- package/get-shit-done/templates/state.md +176 -0
- package/get-shit-done/templates/summary-complex.md +59 -0
- package/get-shit-done/templates/summary-minimal.md +41 -0
- package/get-shit-done/templates/summary-standard.md +48 -0
- package/get-shit-done/templates/summary.md +246 -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/add-phase.md +111 -0
- package/get-shit-done/workflows/add-todo.md +157 -0
- package/get-shit-done/workflows/audit-milestone.md +242 -0
- package/get-shit-done/workflows/check-todos.md +176 -0
- package/get-shit-done/workflows/cleanup.md +152 -0
- package/get-shit-done/workflows/complete-milestone.md +674 -0
- package/get-shit-done/workflows/diagnose-issues.md +219 -0
- package/get-shit-done/workflows/discovery-phase.md +289 -0
- package/get-shit-done/workflows/discuss-phase.md +485 -0
- package/get-shit-done/workflows/execute-phase.md +408 -0
- package/get-shit-done/workflows/execute-plan.md +441 -0
- package/get-shit-done/workflows/health.md +156 -0
- package/get-shit-done/workflows/help.md +486 -0
- package/get-shit-done/workflows/insert-phase.md +129 -0
- package/get-shit-done/workflows/list-phase-assumptions.md +178 -0
- package/get-shit-done/workflows/map-codebase.md +327 -0
- package/get-shit-done/workflows/new-milestone.md +373 -0
- package/get-shit-done/workflows/new-project.md +1113 -0
- package/get-shit-done/workflows/pause-work.md +122 -0
- package/get-shit-done/workflows/plan-milestone-gaps.md +256 -0
- package/get-shit-done/workflows/plan-phase.md +448 -0
- package/get-shit-done/workflows/progress.md +393 -0
- package/get-shit-done/workflows/quick.md +444 -0
- package/get-shit-done/workflows/remove-phase.md +154 -0
- package/get-shit-done/workflows/research-phase.md +74 -0
- package/get-shit-done/workflows/resume-project.md +306 -0
- package/get-shit-done/workflows/set-profile.md +80 -0
- package/get-shit-done/workflows/settings.md +200 -0
- package/get-shit-done/workflows/transition.md +539 -0
- package/get-shit-done/workflows/update.md +214 -0
- package/get-shit-done/workflows/verify-phase.md +242 -0
- package/get-shit-done/workflows/verify-work.md +570 -0
- package/hooks/dist/gsd-check-update.js +62 -0
- package/hooks/dist/gsd-statusline.js +91 -0
- package/package.json +54 -0
- package/scripts/build-hooks.js +42 -0
|
@@ -0,0 +1,441 @@
|
|
|
1
|
+
<purpose>
|
|
2
|
+
Execute a phase prompt (PLAN.md) and create the outcome summary (SUMMARY.md).
|
|
3
|
+
</purpose>
|
|
4
|
+
|
|
5
|
+
<required_reading>
|
|
6
|
+
Read STATE.md before any operation to load project context.
|
|
7
|
+
Read config.json for planning behavior settings.
|
|
8
|
+
|
|
9
|
+
@~/.claude/get-shit-done/references/git-integration.md
|
|
10
|
+
</required_reading>
|
|
11
|
+
|
|
12
|
+
<process>
|
|
13
|
+
|
|
14
|
+
<step name="init_context" priority="first">
|
|
15
|
+
Load execution context (uses `init execute-phase` for full context, including file contents):
|
|
16
|
+
|
|
17
|
+
```bash
|
|
18
|
+
INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs init execute-phase "${PHASE}" --include state,config)
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
Extract from init JSON: `executor_model`, `commit_docs`, `phase_dir`, `phase_number`, `plans`, `summaries`, `incomplete_plans`.
|
|
22
|
+
|
|
23
|
+
**File contents (from --include):** `state_content`, `config_content`. Access with:
|
|
24
|
+
```bash
|
|
25
|
+
STATE_CONTENT=$(echo "$INIT" | jq -r '.state_content // empty')
|
|
26
|
+
CONFIG_CONTENT=$(echo "$INIT" | jq -r '.config_content // empty')
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
If `.planning/` missing: error.
|
|
30
|
+
</step>
|
|
31
|
+
|
|
32
|
+
<step name="identify_plan">
|
|
33
|
+
```bash
|
|
34
|
+
# Use plans/summaries from INIT JSON, or list files
|
|
35
|
+
ls .planning/phases/XX-name/*-PLAN.md 2>/dev/null | sort
|
|
36
|
+
ls .planning/phases/XX-name/*-SUMMARY.md 2>/dev/null | sort
|
|
37
|
+
```
|
|
38
|
+
|
|
39
|
+
Find first PLAN without matching SUMMARY. Decimal phases supported (`01.1-hotfix/`):
|
|
40
|
+
|
|
41
|
+
```bash
|
|
42
|
+
PHASE=$(echo "$PLAN_PATH" | grep -oE '[0-9]+(\.[0-9]+)?-[0-9]+')
|
|
43
|
+
# config_content already loaded via --include config in init_context
|
|
44
|
+
```
|
|
45
|
+
|
|
46
|
+
<if mode="yolo">
|
|
47
|
+
Auto-approve: `⚡ Execute {phase}-{plan}-PLAN.md [Plan X of Y for Phase Z]` → parse_segments.
|
|
48
|
+
</if>
|
|
49
|
+
|
|
50
|
+
<if mode="interactive" OR="custom with gates.execute_next_plan true">
|
|
51
|
+
Present plan identification, wait for confirmation.
|
|
52
|
+
</if>
|
|
53
|
+
</step>
|
|
54
|
+
|
|
55
|
+
<step name="record_start_time">
|
|
56
|
+
```bash
|
|
57
|
+
PLAN_START_TIME=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
|
|
58
|
+
PLAN_START_EPOCH=$(date +%s)
|
|
59
|
+
```
|
|
60
|
+
</step>
|
|
61
|
+
|
|
62
|
+
<step name="parse_segments">
|
|
63
|
+
```bash
|
|
64
|
+
grep -n "type=\"checkpoint" .planning/phases/XX-name/{phase}-{plan}-PLAN.md
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
**Routing by checkpoint type:**
|
|
68
|
+
|
|
69
|
+
| Checkpoints | Pattern | Execution |
|
|
70
|
+
|-------------|---------|-----------|
|
|
71
|
+
| None | A (autonomous) | Single subagent: full plan + SUMMARY + commit |
|
|
72
|
+
| Verify-only | B (segmented) | Segments between checkpoints. After none/human-verify → SUBAGENT. After decision/human-action → MAIN |
|
|
73
|
+
| Decision | C (main) | Execute entirely in main context |
|
|
74
|
+
|
|
75
|
+
**Pattern A:** init_agent_tracking → spawn Task(subagent_type="gsd-executor", model=executor_model) with prompt: execute plan at [path], autonomous, all tasks + SUMMARY + commit, follow deviation/auth rules, report: plan name, tasks, SUMMARY path, commit hash → track agent_id → wait → update tracking → report.
|
|
76
|
+
|
|
77
|
+
**Pattern B:** Execute segment-by-segment. Autonomous segments: spawn subagent for assigned tasks only (no SUMMARY/commit). Checkpoints: main context. After all segments: aggregate, create SUMMARY, commit. See segment_execution.
|
|
78
|
+
|
|
79
|
+
**Pattern C:** Execute in main using standard flow (step name="execute").
|
|
80
|
+
|
|
81
|
+
Fresh context per subagent preserves peak quality. Main context stays lean.
|
|
82
|
+
</step>
|
|
83
|
+
|
|
84
|
+
<step name="init_agent_tracking">
|
|
85
|
+
```bash
|
|
86
|
+
if [ ! -f .planning/agent-history.json ]; then
|
|
87
|
+
echo '{"version":"1.0","max_entries":50,"entries":[]}' > .planning/agent-history.json
|
|
88
|
+
fi
|
|
89
|
+
rm -f .planning/current-agent-id.txt
|
|
90
|
+
if [ -f .planning/current-agent-id.txt ]; then
|
|
91
|
+
INTERRUPTED_ID=$(cat .planning/current-agent-id.txt)
|
|
92
|
+
echo "Found interrupted agent: $INTERRUPTED_ID"
|
|
93
|
+
fi
|
|
94
|
+
```
|
|
95
|
+
|
|
96
|
+
If interrupted: ask user to resume (Task `resume` parameter) or start fresh.
|
|
97
|
+
|
|
98
|
+
**Tracking protocol:** On spawn: write agent_id to `current-agent-id.txt`, append to agent-history.json: `{"agent_id":"[id]","task_description":"[desc]","phase":"[phase]","plan":"[plan]","segment":[num|null],"timestamp":"[ISO]","status":"spawned","completion_timestamp":null}`. On completion: status → "completed", set completion_timestamp, delete current-agent-id.txt. Prune: if entries > max_entries, remove oldest "completed" (never "spawned").
|
|
99
|
+
|
|
100
|
+
Run for Pattern A/B before spawning. Pattern C: skip.
|
|
101
|
+
</step>
|
|
102
|
+
|
|
103
|
+
<step name="segment_execution">
|
|
104
|
+
Pattern B only (verify-only checkpoints). Skip for A/C.
|
|
105
|
+
|
|
106
|
+
1. Parse segment map: checkpoint locations and types
|
|
107
|
+
2. Per segment:
|
|
108
|
+
- Subagent route: spawn gsd-executor for assigned tasks only. Prompt: task range, plan path, read full plan for context, execute assigned tasks, track deviations, NO SUMMARY/commit. Track via agent protocol.
|
|
109
|
+
- Main route: execute tasks using standard flow (step name="execute")
|
|
110
|
+
3. After ALL segments: aggregate files/deviations/decisions → create SUMMARY.md → commit → self-check:
|
|
111
|
+
- Verify key-files.created exist on disk with `[ -f ]`
|
|
112
|
+
- Check `git log --oneline --all --grep="{phase}-{plan}"` returns ≥1 commit
|
|
113
|
+
- Append `## Self-Check: PASSED` or `## Self-Check: FAILED` to SUMMARY
|
|
114
|
+
|
|
115
|
+
**Known Claude Code bug (classifyHandoffIfNeeded):** If any segment agent reports "failed" with `classifyHandoffIfNeeded is not defined`, this is a Claude Code runtime bug — not a real failure. Run spot-checks; if they pass, treat as successful.
|
|
116
|
+
|
|
117
|
+
|
|
118
|
+
|
|
119
|
+
|
|
120
|
+
</step>
|
|
121
|
+
|
|
122
|
+
<step name="load_prompt">
|
|
123
|
+
```bash
|
|
124
|
+
cat .planning/phases/XX-name/{phase}-{plan}-PLAN.md
|
|
125
|
+
```
|
|
126
|
+
This IS the execution instructions. Follow exactly. If plan references CONTEXT.md: honor user's vision throughout.
|
|
127
|
+
</step>
|
|
128
|
+
|
|
129
|
+
<step name="previous_phase_check">
|
|
130
|
+
```bash
|
|
131
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs phases list --type summaries --raw
|
|
132
|
+
# Extract the second-to-last summary from the JSON result
|
|
133
|
+
```
|
|
134
|
+
If previous SUMMARY has unresolved "Issues Encountered" or "Next Phase Readiness" blockers: AskUserQuestion(header="Previous Issues", options: "Proceed anyway" | "Address first" | "Review previous").
|
|
135
|
+
</step>
|
|
136
|
+
|
|
137
|
+
<step name="execute">
|
|
138
|
+
Deviations are normal — handle via rules below.
|
|
139
|
+
|
|
140
|
+
1. Read @context files from prompt
|
|
141
|
+
2. Per task:
|
|
142
|
+
- `type="auto"`: if `tdd="true"` → TDD execution. Implement with deviation rules + auth gates. Verify done criteria. Commit (see task_commit). Track hash for Summary.
|
|
143
|
+
- `type="checkpoint:*"`: STOP → checkpoint_protocol → wait for user → continue only after confirmation.
|
|
144
|
+
3. Run `<verification>` checks
|
|
145
|
+
4. Confirm `<success_criteria>` met
|
|
146
|
+
5. Document deviations in Summary
|
|
147
|
+
</step>
|
|
148
|
+
|
|
149
|
+
<authentication_gates>
|
|
150
|
+
|
|
151
|
+
## Authentication Gates
|
|
152
|
+
|
|
153
|
+
Auth errors during execution are NOT failures — they're expected interaction points.
|
|
154
|
+
|
|
155
|
+
**Indicators:** "Not authenticated", "Unauthorized", 401/403, "Please run {tool} login", "Set {ENV_VAR}"
|
|
156
|
+
|
|
157
|
+
**Protocol:**
|
|
158
|
+
1. Recognize auth gate (not a bug)
|
|
159
|
+
2. STOP task execution
|
|
160
|
+
3. Create dynamic checkpoint:human-action with exact auth steps
|
|
161
|
+
4. Wait for user to authenticate
|
|
162
|
+
5. Verify credentials work
|
|
163
|
+
6. Retry original task
|
|
164
|
+
7. Continue normally
|
|
165
|
+
|
|
166
|
+
**Example:** `vercel --yes` → "Not authenticated" → checkpoint asking user to `vercel login` → verify with `vercel whoami` → retry deploy → continue
|
|
167
|
+
|
|
168
|
+
**In Summary:** Document as normal flow under "## Authentication Gates", not as deviations.
|
|
169
|
+
|
|
170
|
+
</authentication_gates>
|
|
171
|
+
|
|
172
|
+
<deviation_rules>
|
|
173
|
+
|
|
174
|
+
## Deviation Rules
|
|
175
|
+
|
|
176
|
+
You WILL discover unplanned work. Apply automatically, track all for Summary.
|
|
177
|
+
|
|
178
|
+
| Rule | Trigger | Action | Permission |
|
|
179
|
+
|------|---------|--------|------------|
|
|
180
|
+
| **1: Bug** | Broken behavior, errors, wrong queries, type errors, security vulns, race conditions, leaks | Fix → test → verify → track `[Rule 1 - Bug]` | Auto |
|
|
181
|
+
| **2: Missing Critical** | Missing essentials: error handling, validation, auth, CSRF/CORS, rate limiting, indexes, logging | Add → test → verify → track `[Rule 2 - Missing Critical]` | Auto |
|
|
182
|
+
| **3: Blocking** | Prevents completion: missing deps, wrong types, broken imports, missing env/config/files, circular deps | Fix blocker → verify proceeds → track `[Rule 3 - Blocking]` | Auto |
|
|
183
|
+
| **4: Architectural** | Structural change: new DB table, schema change, new service, switching libs, breaking API, new infra | STOP → present decision (below) → track `[Rule 4 - Architectural]` | Ask user |
|
|
184
|
+
|
|
185
|
+
**Rule 4 format:**
|
|
186
|
+
```
|
|
187
|
+
⚠️ Architectural Decision Needed
|
|
188
|
+
|
|
189
|
+
Current task: [task name]
|
|
190
|
+
Discovery: [what prompted this]
|
|
191
|
+
Proposed change: [modification]
|
|
192
|
+
Why needed: [rationale]
|
|
193
|
+
Impact: [what this affects]
|
|
194
|
+
Alternatives: [other approaches]
|
|
195
|
+
|
|
196
|
+
Proceed with proposed change? (yes / different approach / defer)
|
|
197
|
+
```
|
|
198
|
+
|
|
199
|
+
**Priority:** Rule 4 (STOP) > Rules 1-3 (auto) > unsure → Rule 4
|
|
200
|
+
**Edge cases:** missing validation → R2 | null crash → R1 | new table → R4 | new column → R1/2
|
|
201
|
+
**Heuristic:** Affects correctness/security/completion? → R1-3. Maybe? → R4.
|
|
202
|
+
|
|
203
|
+
</deviation_rules>
|
|
204
|
+
|
|
205
|
+
<deviation_documentation>
|
|
206
|
+
|
|
207
|
+
## Documenting Deviations
|
|
208
|
+
|
|
209
|
+
Summary MUST include deviations section. None? → `## Deviations from Plan\n\nNone - plan executed exactly as written.`
|
|
210
|
+
|
|
211
|
+
Per deviation: **[Rule N - Category] Title** — Found during: Task X | Issue | Fix | Files modified | Verification | Commit hash
|
|
212
|
+
|
|
213
|
+
End with: **Total deviations:** N auto-fixed (breakdown). **Impact:** assessment.
|
|
214
|
+
|
|
215
|
+
</deviation_documentation>
|
|
216
|
+
|
|
217
|
+
<tdd_plan_execution>
|
|
218
|
+
## TDD Execution
|
|
219
|
+
|
|
220
|
+
For `type: tdd` plans — RED-GREEN-REFACTOR:
|
|
221
|
+
|
|
222
|
+
1. **Infrastructure** (first TDD plan only): detect project, install framework, config, verify empty suite
|
|
223
|
+
2. **RED:** Read `<behavior>` → failing test(s) → run (MUST fail) → commit: `test({phase}-{plan}): add failing test for [feature]`
|
|
224
|
+
3. **GREEN:** Read `<implementation>` → minimal code → run (MUST pass) → commit: `feat({phase}-{plan}): implement [feature]`
|
|
225
|
+
4. **REFACTOR:** Clean up → tests MUST pass → commit: `refactor({phase}-{plan}): clean up [feature]`
|
|
226
|
+
|
|
227
|
+
Errors: RED doesn't fail → investigate test/existing feature. GREEN doesn't pass → debug, iterate. REFACTOR breaks → undo.
|
|
228
|
+
|
|
229
|
+
See `~/.claude/get-shit-done/references/tdd.md` for structure.
|
|
230
|
+
</tdd_plan_execution>
|
|
231
|
+
|
|
232
|
+
<task_commit>
|
|
233
|
+
## Task Commit Protocol
|
|
234
|
+
|
|
235
|
+
After each task (verification passed, done criteria met), commit immediately.
|
|
236
|
+
|
|
237
|
+
**1. Check:** `git status --short`
|
|
238
|
+
|
|
239
|
+
**2. Stage individually** (NEVER `git add .` or `git add -A`):
|
|
240
|
+
```bash
|
|
241
|
+
git add src/api/auth.ts
|
|
242
|
+
git add src/types/user.ts
|
|
243
|
+
```
|
|
244
|
+
|
|
245
|
+
**3. Commit type:**
|
|
246
|
+
|
|
247
|
+
| Type | When | Example |
|
|
248
|
+
|------|------|---------|
|
|
249
|
+
| `feat` | New functionality | feat(08-02): create user registration endpoint |
|
|
250
|
+
| `fix` | Bug fix | fix(08-02): correct email validation regex |
|
|
251
|
+
| `test` | Test-only (TDD RED) | test(08-02): add failing test for password hashing |
|
|
252
|
+
| `refactor` | No behavior change (TDD REFACTOR) | refactor(08-02): extract validation to helper |
|
|
253
|
+
| `perf` | Performance | perf(08-02): add database index |
|
|
254
|
+
| `docs` | Documentation | docs(08-02): add API docs |
|
|
255
|
+
| `style` | Formatting | style(08-02): format auth module |
|
|
256
|
+
| `chore` | Config/deps | chore(08-02): add bcrypt dependency |
|
|
257
|
+
|
|
258
|
+
**4. Format:** `{type}({phase}-{plan}): {description}` with bullet points for key changes.
|
|
259
|
+
|
|
260
|
+
**5. Record hash:**
|
|
261
|
+
```bash
|
|
262
|
+
TASK_COMMIT=$(git rev-parse --short HEAD)
|
|
263
|
+
TASK_COMMITS+=("Task ${TASK_NUM}: ${TASK_COMMIT}")
|
|
264
|
+
```
|
|
265
|
+
|
|
266
|
+
</task_commit>
|
|
267
|
+
|
|
268
|
+
<step name="checkpoint_protocol">
|
|
269
|
+
On `type="checkpoint:*"`: automate everything possible first. Checkpoints are for verification/decisions only.
|
|
270
|
+
|
|
271
|
+
Display: `CHECKPOINT: [Type]` box → Progress {X}/{Y} → Task name → type-specific content → `YOUR ACTION: [signal]`
|
|
272
|
+
|
|
273
|
+
| Type | Content | Resume signal |
|
|
274
|
+
|------|---------|---------------|
|
|
275
|
+
| human-verify (90%) | What was built + verification steps (commands/URLs) | "approved" or describe issues |
|
|
276
|
+
| decision (9%) | Decision needed + context + options with pros/cons | "Select: option-id" |
|
|
277
|
+
| human-action (1%) | What was automated + ONE manual step + verification plan | "done" |
|
|
278
|
+
|
|
279
|
+
After response: verify if specified. Pass → continue. Fail → inform, wait. WAIT for user — do NOT hallucinate completion.
|
|
280
|
+
|
|
281
|
+
See ~/.claude/get-shit-done/references/checkpoints.md for details.
|
|
282
|
+
</step>
|
|
283
|
+
|
|
284
|
+
<step name="checkpoint_return_for_orchestrator">
|
|
285
|
+
When spawned via Task and hitting checkpoint: return structured state (cannot interact with user directly).
|
|
286
|
+
|
|
287
|
+
**Required return:** 1) Completed Tasks table (hashes + files) 2) Current Task (what's blocking) 3) Checkpoint Details (user-facing content) 4) Awaiting (what's needed from user)
|
|
288
|
+
|
|
289
|
+
Orchestrator parses → presents to user → spawns fresh continuation with your completed tasks state. You will NOT be resumed. In main context: use checkpoint_protocol above.
|
|
290
|
+
</step>
|
|
291
|
+
|
|
292
|
+
<step name="verification_failure_gate">
|
|
293
|
+
If verification fails: STOP. Present: "Verification failed for Task [X]: [name]. Expected: [criteria]. Actual: [result]." Options: Retry | Skip (mark incomplete) | Stop (investigate). If skipped → SUMMARY "Issues Encountered".
|
|
294
|
+
</step>
|
|
295
|
+
|
|
296
|
+
<step name="record_completion_time">
|
|
297
|
+
```bash
|
|
298
|
+
PLAN_END_TIME=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
|
|
299
|
+
PLAN_END_EPOCH=$(date +%s)
|
|
300
|
+
|
|
301
|
+
DURATION_SEC=$(( PLAN_END_EPOCH - PLAN_START_EPOCH ))
|
|
302
|
+
DURATION_MIN=$(( DURATION_SEC / 60 ))
|
|
303
|
+
|
|
304
|
+
if [[ $DURATION_MIN -ge 60 ]]; then
|
|
305
|
+
HRS=$(( DURATION_MIN / 60 ))
|
|
306
|
+
MIN=$(( DURATION_MIN % 60 ))
|
|
307
|
+
DURATION="${HRS}h ${MIN}m"
|
|
308
|
+
else
|
|
309
|
+
DURATION="${DURATION_MIN} min"
|
|
310
|
+
fi
|
|
311
|
+
```
|
|
312
|
+
</step>
|
|
313
|
+
|
|
314
|
+
<step name="generate_user_setup">
|
|
315
|
+
```bash
|
|
316
|
+
grep -A 50 "^user_setup:" .planning/phases/XX-name/{phase}-{plan}-PLAN.md | head -50
|
|
317
|
+
```
|
|
318
|
+
|
|
319
|
+
If user_setup exists: create `{phase}-USER-SETUP.md` using template `~/.claude/get-shit-done/templates/user-setup.md`. Per service: env vars table, account setup checklist, dashboard config, local dev notes, verification commands. Status "Incomplete". Set `USER_SETUP_CREATED=true`. If empty/missing: skip.
|
|
320
|
+
</step>
|
|
321
|
+
|
|
322
|
+
<step name="create_summary">
|
|
323
|
+
Create `{phase}-{plan}-SUMMARY.md` at `.planning/phases/XX-name/`. Use `~/.claude/get-shit-done/templates/summary.md`.
|
|
324
|
+
|
|
325
|
+
**Frontmatter:** phase, plan, subsystem, tags | requires/provides/affects | tech-stack.added/patterns | key-files.created/modified | key-decisions | duration ($DURATION), completed ($PLAN_END_TIME date).
|
|
326
|
+
|
|
327
|
+
Title: `# Phase [X] Plan [Y]: [Name] Summary`
|
|
328
|
+
|
|
329
|
+
One-liner SUBSTANTIVE: "JWT auth with refresh rotation using jose library" not "Authentication implemented"
|
|
330
|
+
|
|
331
|
+
Include: duration, start/end times, task count, file count.
|
|
332
|
+
|
|
333
|
+
Next: more plans → "Ready for {next-plan}" | last → "Phase complete, ready for transition".
|
|
334
|
+
</step>
|
|
335
|
+
|
|
336
|
+
<step name="update_current_position">
|
|
337
|
+
Update STATE.md using gsd-tools:
|
|
338
|
+
|
|
339
|
+
```bash
|
|
340
|
+
# Advance plan counter (handles last-plan edge case)
|
|
341
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs state advance-plan
|
|
342
|
+
|
|
343
|
+
# Recalculate progress bar from disk state
|
|
344
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs state update-progress
|
|
345
|
+
|
|
346
|
+
# Record execution metrics
|
|
347
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs state record-metric \
|
|
348
|
+
--phase "${PHASE}" --plan "${PLAN}" --duration "${DURATION}" \
|
|
349
|
+
--tasks "${TASK_COUNT}" --files "${FILE_COUNT}"
|
|
350
|
+
```
|
|
351
|
+
</step>
|
|
352
|
+
|
|
353
|
+
<step name="extract_decisions_and_issues">
|
|
354
|
+
From SUMMARY: Extract decisions and add to STATE.md:
|
|
355
|
+
|
|
356
|
+
```bash
|
|
357
|
+
# Add each decision from SUMMARY key-decisions
|
|
358
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs state add-decision \
|
|
359
|
+
--phase "${PHASE}" --summary "${DECISION_TEXT}" --rationale "${RATIONALE}"
|
|
360
|
+
|
|
361
|
+
# Add blockers if any found
|
|
362
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs state add-blocker "Blocker description"
|
|
363
|
+
```
|
|
364
|
+
</step>
|
|
365
|
+
|
|
366
|
+
<step name="update_session_continuity">
|
|
367
|
+
Update session info using gsd-tools:
|
|
368
|
+
|
|
369
|
+
```bash
|
|
370
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs state record-session \
|
|
371
|
+
--stopped-at "Completed ${PHASE}-${PLAN}-PLAN.md" \
|
|
372
|
+
--resume-file "None"
|
|
373
|
+
```
|
|
374
|
+
|
|
375
|
+
Keep STATE.md under 150 lines.
|
|
376
|
+
</step>
|
|
377
|
+
|
|
378
|
+
<step name="issues_review_gate">
|
|
379
|
+
If SUMMARY "Issues Encountered" ≠ "None": yolo → log and continue. Interactive → present issues, wait for acknowledgment.
|
|
380
|
+
</step>
|
|
381
|
+
|
|
382
|
+
<step name="update_roadmap">
|
|
383
|
+
```bash
|
|
384
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs roadmap update-plan-progress "${PHASE}"
|
|
385
|
+
```
|
|
386
|
+
Counts PLAN vs SUMMARY files on disk. Updates progress table row with correct count and status (`In Progress` or `Complete` with date).
|
|
387
|
+
</step>
|
|
388
|
+
|
|
389
|
+
<step name="git_commit_metadata">
|
|
390
|
+
Task code already committed per-task. Commit plan metadata:
|
|
391
|
+
|
|
392
|
+
```bash
|
|
393
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "docs({phase}-{plan}): complete [plan-name] plan" --files .planning/phases/XX-name/{phase}-{plan}-SUMMARY.md .planning/STATE.md .planning/ROADMAP.md
|
|
394
|
+
```
|
|
395
|
+
</step>
|
|
396
|
+
|
|
397
|
+
<step name="update_codebase_map">
|
|
398
|
+
If .planning/codebase/ doesn't exist: skip.
|
|
399
|
+
|
|
400
|
+
```bash
|
|
401
|
+
FIRST_TASK=$(git log --oneline --grep="feat({phase}-{plan}):" --grep="fix({phase}-{plan}):" --grep="test({phase}-{plan}):" --reverse | head -1 | cut -d' ' -f1)
|
|
402
|
+
git diff --name-only ${FIRST_TASK}^..HEAD 2>/dev/null
|
|
403
|
+
```
|
|
404
|
+
|
|
405
|
+
Update only structural changes: new src/ dir → STRUCTURE.md | deps → STACK.md | file pattern → CONVENTIONS.md | API client → INTEGRATIONS.md | config → STACK.md | renamed → update paths. Skip code-only/bugfix/content changes.
|
|
406
|
+
|
|
407
|
+
```bash
|
|
408
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs commit "" --files .planning/codebase/*.md --amend
|
|
409
|
+
```
|
|
410
|
+
</step>
|
|
411
|
+
|
|
412
|
+
<step name="offer_next">
|
|
413
|
+
If `USER_SETUP_CREATED=true`: display `⚠️ USER SETUP REQUIRED` with path + env/config tasks at TOP.
|
|
414
|
+
|
|
415
|
+
```bash
|
|
416
|
+
ls -1 .planning/phases/[current-phase-dir]/*-PLAN.md 2>/dev/null | wc -l
|
|
417
|
+
ls -1 .planning/phases/[current-phase-dir]/*-SUMMARY.md 2>/dev/null | wc -l
|
|
418
|
+
```
|
|
419
|
+
|
|
420
|
+
| Condition | Route | Action |
|
|
421
|
+
|-----------|-------|--------|
|
|
422
|
+
| summaries < plans | **A: More plans** | Find next PLAN without SUMMARY. Yolo: auto-continue. Interactive: show next plan, suggest `/gsd:execute-phase {phase}` + `/gsd:verify-work`. STOP here. |
|
|
423
|
+
| summaries = plans, current < highest phase | **B: Phase done** | Show completion, suggest `/gsd:plan-phase {Z+1}` + `/gsd:verify-work {Z}` + `/gsd:discuss-phase {Z+1}` |
|
|
424
|
+
| summaries = plans, current = highest phase | **C: Milestone done** | Show banner, suggest `/gsd:complete-milestone` + `/gsd:verify-work` + `/gsd:add-phase` |
|
|
425
|
+
|
|
426
|
+
All routes: `/clear` first for fresh context.
|
|
427
|
+
</step>
|
|
428
|
+
|
|
429
|
+
</process>
|
|
430
|
+
|
|
431
|
+
<success_criteria>
|
|
432
|
+
|
|
433
|
+
- All tasks from PLAN.md completed
|
|
434
|
+
- All verifications pass
|
|
435
|
+
- USER-SETUP.md generated if user_setup in frontmatter
|
|
436
|
+
- SUMMARY.md created with substantive content
|
|
437
|
+
- STATE.md updated (position, decisions, issues, session)
|
|
438
|
+
- ROADMAP.md updated
|
|
439
|
+
- If codebase map exists: map updated with execution changes (or skipped if no significant changes)
|
|
440
|
+
- If USER-SETUP.md created: prominently surfaced in completion output
|
|
441
|
+
</success_criteria>
|
|
@@ -0,0 +1,156 @@
|
|
|
1
|
+
<purpose>
|
|
2
|
+
Validate `.planning/` directory integrity and report actionable issues. Checks for missing files, invalid configurations, inconsistent state, and orphaned plans. Optionally repairs auto-fixable issues.
|
|
3
|
+
</purpose>
|
|
4
|
+
|
|
5
|
+
<required_reading>
|
|
6
|
+
Read all files referenced by the invoking prompt's execution_context before starting.
|
|
7
|
+
</required_reading>
|
|
8
|
+
|
|
9
|
+
<process>
|
|
10
|
+
|
|
11
|
+
<step name="parse_args">
|
|
12
|
+
**Parse arguments:**
|
|
13
|
+
|
|
14
|
+
Check if `--repair` flag is present in the command arguments.
|
|
15
|
+
|
|
16
|
+
```
|
|
17
|
+
REPAIR_FLAG=""
|
|
18
|
+
if arguments contain "--repair"; then
|
|
19
|
+
REPAIR_FLAG="--repair"
|
|
20
|
+
fi
|
|
21
|
+
```
|
|
22
|
+
</step>
|
|
23
|
+
|
|
24
|
+
<step name="run_health_check">
|
|
25
|
+
**Run health validation:**
|
|
26
|
+
|
|
27
|
+
```bash
|
|
28
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs validate health $REPAIR_FLAG
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
Parse JSON output:
|
|
32
|
+
- `status`: "healthy" | "degraded" | "broken"
|
|
33
|
+
- `errors[]`: Critical issues (code, message, fix, repairable)
|
|
34
|
+
- `warnings[]`: Non-critical issues
|
|
35
|
+
- `info[]`: Informational notes
|
|
36
|
+
- `repairable_count`: Number of auto-fixable issues
|
|
37
|
+
- `repairs_performed[]`: Actions taken if --repair was used
|
|
38
|
+
</step>
|
|
39
|
+
|
|
40
|
+
<step name="format_output">
|
|
41
|
+
**Format and display results:**
|
|
42
|
+
|
|
43
|
+
```
|
|
44
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
45
|
+
GSD Health Check
|
|
46
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
47
|
+
|
|
48
|
+
Status: HEALTHY | DEGRADED | BROKEN
|
|
49
|
+
Errors: N | Warnings: N | Info: N
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
**If repairs were performed:**
|
|
53
|
+
```
|
|
54
|
+
## Repairs Performed
|
|
55
|
+
|
|
56
|
+
- ✓ config.json: Created with defaults
|
|
57
|
+
- ✓ STATE.md: Regenerated from roadmap
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
**If errors exist:**
|
|
61
|
+
```
|
|
62
|
+
## Errors
|
|
63
|
+
|
|
64
|
+
- [E001] config.json: JSON parse error at line 5
|
|
65
|
+
Fix: Run /gsd:health --repair to reset to defaults
|
|
66
|
+
|
|
67
|
+
- [E002] PROJECT.md not found
|
|
68
|
+
Fix: Run /gsd:new-project to create
|
|
69
|
+
```
|
|
70
|
+
|
|
71
|
+
**If warnings exist:**
|
|
72
|
+
```
|
|
73
|
+
## Warnings
|
|
74
|
+
|
|
75
|
+
- [W001] STATE.md references phase 5, but only phases 1-3 exist
|
|
76
|
+
Fix: Run /gsd:health --repair to regenerate
|
|
77
|
+
|
|
78
|
+
- [W005] Phase directory "1-setup" doesn't follow NN-name format
|
|
79
|
+
Fix: Rename to match pattern (e.g., 01-setup)
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
**If info exists:**
|
|
83
|
+
```
|
|
84
|
+
## Info
|
|
85
|
+
|
|
86
|
+
- [I001] 02-implementation/02-01-PLAN.md has no SUMMARY.md
|
|
87
|
+
Note: May be in progress
|
|
88
|
+
```
|
|
89
|
+
|
|
90
|
+
**Footer (if repairable issues exist and --repair was NOT used):**
|
|
91
|
+
```
|
|
92
|
+
---
|
|
93
|
+
N issues can be auto-repaired. Run: /gsd:health --repair
|
|
94
|
+
```
|
|
95
|
+
</step>
|
|
96
|
+
|
|
97
|
+
<step name="offer_repair">
|
|
98
|
+
**If repairable issues exist and --repair was NOT used:**
|
|
99
|
+
|
|
100
|
+
Ask user if they want to run repairs:
|
|
101
|
+
|
|
102
|
+
```
|
|
103
|
+
Would you like to run /gsd:health --repair to fix N issues automatically?
|
|
104
|
+
```
|
|
105
|
+
|
|
106
|
+
If yes, re-run with --repair flag and display results.
|
|
107
|
+
</step>
|
|
108
|
+
|
|
109
|
+
<step name="verify_repairs">
|
|
110
|
+
**If repairs were performed:**
|
|
111
|
+
|
|
112
|
+
Re-run health check without --repair to confirm issues are resolved:
|
|
113
|
+
|
|
114
|
+
```bash
|
|
115
|
+
node ~/.claude/get-shit-done/bin/gsd-tools.cjs validate health
|
|
116
|
+
```
|
|
117
|
+
|
|
118
|
+
Report final status.
|
|
119
|
+
</step>
|
|
120
|
+
|
|
121
|
+
</process>
|
|
122
|
+
|
|
123
|
+
<error_codes>
|
|
124
|
+
|
|
125
|
+
| Code | Severity | Description | Repairable |
|
|
126
|
+
|------|----------|-------------|------------|
|
|
127
|
+
| E001 | error | .planning/ directory not found | No |
|
|
128
|
+
| E002 | error | PROJECT.md not found | No |
|
|
129
|
+
| E003 | error | ROADMAP.md not found | No |
|
|
130
|
+
| E004 | error | STATE.md not found | Yes |
|
|
131
|
+
| E005 | error | config.json parse error | Yes |
|
|
132
|
+
| W001 | warning | PROJECT.md missing required section | No |
|
|
133
|
+
| W002 | warning | STATE.md references invalid phase | Yes |
|
|
134
|
+
| W003 | warning | config.json not found | Yes |
|
|
135
|
+
| W004 | warning | config.json invalid field value | No |
|
|
136
|
+
| W005 | warning | Phase directory naming mismatch | No |
|
|
137
|
+
| W006 | warning | Phase in ROADMAP but no directory | No |
|
|
138
|
+
| W007 | warning | Phase on disk but not in ROADMAP | No |
|
|
139
|
+
| I001 | info | Plan without SUMMARY (may be in progress) | No |
|
|
140
|
+
|
|
141
|
+
</error_codes>
|
|
142
|
+
|
|
143
|
+
<repair_actions>
|
|
144
|
+
|
|
145
|
+
| Action | Effect | Risk |
|
|
146
|
+
|--------|--------|------|
|
|
147
|
+
| createConfig | Create config.json with defaults | None |
|
|
148
|
+
| resetConfig | Delete + recreate config.json | Loses custom settings |
|
|
149
|
+
| regenerateState | Create STATE.md from ROADMAP structure | Loses session history |
|
|
150
|
+
|
|
151
|
+
**Not repairable (too risky):**
|
|
152
|
+
- PROJECT.md, ROADMAP.md content
|
|
153
|
+
- Phase directory renaming
|
|
154
|
+
- Orphaned plan cleanup
|
|
155
|
+
|
|
156
|
+
</repair_actions>
|