Skills › gstack › plan-eng-review › checklist.md
checklist.md
36 lines · plan-eng-review/sections/checklist.md at 3f79d81
Most marks come from matching words in the file, so treat them as pointers.
1<!-- AUTO-GENERATED from checklist.md.tmpl — do not edit directly -->
2<!-- Regenerate: bun run gen:skill-docs -->
<!-- AUTO-GENERATED from checklist.md.tmpl — do not edit directly --> <!-- Regenerate: bun run gen:skill-docs -->
Raw lines 1 to 23## Checklist (runner profile)
5Eng phase steps and required outputs for `bin/gstack-autoplan` (unattended or
6`light` runs); interactive runs read `sections/review-sections.md` in full.
Checklist (runner profile)
Eng phase steps and required outputs for bin/gstack-autoplan (unattended or light runs); interactive runs read sections/review-sections.md in full.
Runs code bin/gstack-autoplan :5
8### Steps
91. Scope Challenge (A assess, B selectors, C findings) with the decision
10 procedure; every prior-phase consensus is in the prompt before review.
11 A ends with the reality rows: one `REALITY:` line per applicable row
12 (`gstack-plan-reality rows --phase eng`), each with a file:line receipt.
132. Sections 1–4 in order: architecture (with the design-twice pass when the
14 plan adds a module or boundary), code quality, test, performance
15 (`perf` scope). Continue after the outside voice.
163. Final planning decisions, then the finish sequence below in order.
Steps
- Scope Challenge (A assess, B selectors, C findings) with the decision procedure; every prior-phase consensus is in the prompt before review. A ends with the reality rows: one
REALITY:line per applicable row (gstack-plan-reality rows --phase eng), each with a file:line receipt. - Sections 1–4 in order: architecture (with the design-twice pass when the plan adds a module or boundary), code quality, test, performance (
perfscope). Continue after the outside voice. - Final planning decisions, then the finish sequence below in order.
18### Required outputs → producing section
20| Output | Produced by | Scope |
21|---|---|---|
22| Review body | Output reference — review body | always |
23| Reality rows (`REALITY:` lines, `PLAN_REALITY` check) | Reality rows (why each exists) | always |
24| NOT in scope | "NOT in scope" section | always |
25| What already exists | "What already exists" section | always |
26| Two shapes and red flags (new module or boundary only) | Two shapes before one (design-twice) | always |
27| Diagrams | Diagrams | always |
28| Failure modes | Failure modes | always |
29| Worktree parallelization strategy | Worktree parallelization strategy | always |
30| Test Plan | 3. Test review | always |
31| Performance findings | 4. Performance review | perf |
32| Unresolved decisions | Unresolved decisions | always |
33| Completion summary | Completion summary | always |
34| Review log row | Review Log | always |
35| Next-skill handoff | Next Steps — Review Chaining | always |
36| Learnings | Learning hooks | always |
Required outputs → producing section
| Output | Produced by | Scope |
|---|---|---|
| Review body | Output reference — review body | always |
Reality rows (REALITY: lines, PLAN_REALITY check) | Reality rows (why each exists) | always |
| NOT in scope | "NOT in scope" section | always |
| What already exists | "What already exists" section | always |
| Two shapes and red flags (new module or boundary only) | Two shapes before one (design-twice) | always |
| Diagrams | Diagrams | always |
| Failure modes | Failure modes | always |
| Worktree parallelization strategy | Worktree parallelization strategy | always |
| Test Plan | 3. Test review | always |
| Performance findings | 4. Performance review | perf |
| Unresolved decisions | Unresolved decisions | always |
| Completion summary | Completion summary | always |
| Review log row | Review Log | always |
| Next-skill handoff | Next Steps — Review Chaining | always |
| Learnings | Learning hooks | always |