Go -- Ship What You Built
Phases 4-6 of /development-lifecycle, standalone command. Use when code written, ready launch.
Assumes: implementation done, tests written. If not -- run /development-lifecycle.
Phase 4: Verify
Run all checks. Fix failures before proceed.
bun run type:check (tsgo)bun run lint:fix (biome)bun vitest run --related (changed files)- Route touched ->
bun vitest run *.browser.test.tsx
- Dev server running -> browser smoke via
scripts/skills-browser.sh (Vercel agent-browser). Skip if not installed.
- Frontend diff -> run
/visual-review (screenshots, states, a11y, console, mobile/cross-browser when feasible). Skip only with reason.
- When green: commit now. One commit per passing state.
Phase 4b: Refine (Self-Review Loop)
Skip if: trivial change (<10 lines, no logic) | test-only | docs-only.
- Dispatch
self-reviewer agent on session diff
- Diff >50 lines OR touches auth/security -> also dispatch
adversarial-reviewer parallel
- Process findings by priority -- see REFERENCE.md
- Fix P0/P1 now, apply P2
safe_auto, show P2 gated_auto to user
- Commit fixes:
refactor(scope): self-review fixes
- Re-verify (tests + types + lint)
- Max 2 refine rounds. Then proceed.
Phase 5: Simplify + Ship
- Run
/simplify -- review changed code for reuse, quality, efficiency
- Fix issues, commit
- Frontend diff and
/visual-review not run this session -> run it now or record explicit skip reason
- Run
/commit-push-pr -- conventional commits, push, open PR
- Dispatch
code-reviewer agent (fresh-eyes review)
Phase 5b: Iterate
Monitor: gh pr checks <number> --watch -- stream CI background- CI fail -> diagnose, fix, push, re-monitor
code-reviewer agent findings -> /resolve-pr-feedback triage, fix, reply, push- AI self-review cap: up to 3 auto
code-reviewer rounds. Early-exit when reviewer returns APPROVED or empty findings -- never run round N+1 on clean round N. After 3 rounds still noisy -> hand off to human.
- Human review (incl cloud/Copilot): NO cap. Address EVERY thread.
pr-feedback-completeness-stop hook blocks session exit until bash scripts/pr-unresolved-count.sh returns 0 and no CHANGES_REQUESTED reviews remain.
Phase 6: Compound
After non-trivial tasks: "Learn something worth preserve?"
- Write rule to
.claude/rules/<topic>.md with paths: glob
- AI bug -> create eval/test fixture catch same error class
Done
- Post final PR comment: changes, review findings, test coverage
- Request review:
gh pr edit <number> --add-reviewer <username>
- Report PR URL + CI status
- Stop. No poll for human approval.
Entry Gate
Before start, check work to ship:
- No uncommitted changes AND no unpushed commits -> nothing do, stop
- On default branch, no feature branch -> auto-spawn via
scripts/mux-worktree.sh <type>/<name> before proceed. Never ship from main. [ETHOS: Worktree Isolation]
Skills Composed
| Skill |
Phase |
How |
self-reviewer agent |
4b |
Auto-dispatch on diff |
adversarial-reviewer agent |
4b |
Conditional (>50 lines or auth/security) |
/simplify |
5 |
Code quality review |
/visual-review |
4/5 |
Frontend screenshot, state, a11y, console, mobile/cross-browser review when UI changed |
/commit-push-pr |
5 |
Conventional commits + push + PR |
code-reviewer agent |
5 |
Fresh-eyes review on PR |
/resolve-pr-feedback |
5b |
Triage + fix review comments |
See REFERENCE.md for detailed checklists, gate logic, flowchart.
1---2name: go3description: Ship what built. Run verify -> self-review -> simplify -> commit-push-pr -> monitor CI -> fix -> done. Use when implementation done, ready to launch.4---56# Go -- Ship What You Built78Phases 4-6 of `/development-lifecycle`, standalone command. Use when code written, ready launch.910**Assumes**: implementation done, tests written. If not -- run `/development-lifecycle`.1112## Phase 4: Verify1314Run all checks. Fix failures before proceed.15161. `bun run type:check` (tsgo)172. `bun run lint:fix` (biome)183. `bun vitest run --related` (changed files)194. Route touched -> `bun vitest run *.browser.test.tsx`205. Dev server running -> browser smoke via `scripts/skills-browser.sh` (Vercel agent-browser). Skip if not installed.216. Frontend diff -> run `/visual-review` (screenshots, states, a11y, console, mobile/cross-browser when feasible). Skip only with reason.227. **When green: commit now.** One commit per passing state.2324## Phase 4b: Refine (Self-Review Loop)2526**Skip if**: trivial change (<10 lines, no logic) | test-only | docs-only.27281. Dispatch `self-reviewer` agent on session diff292. Diff >50 lines OR touches auth/security -> also dispatch `adversarial-reviewer` parallel303. Process findings by priority -- see [REFERENCE.md](REFERENCE.md)314. Fix P0/P1 now, apply P2 `safe_auto`, show P2 `gated_auto` to user325. Commit fixes: `refactor(scope): self-review fixes`336. Re-verify (tests + types + lint)347. **Max 2 refine rounds.** Then proceed.3536## Phase 5: Simplify + Ship37381. Run `/simplify` -- review changed code for reuse, quality, efficiency392. Fix issues, commit403. Frontend diff and `/visual-review` not run this session -> run it now or record explicit skip reason414. Run `/commit-push-pr` -- conventional commits, push, open PR425. Dispatch `code-reviewer` agent (fresh-eyes review)4344## Phase 5b: Iterate45461. `Monitor: gh pr checks <number> --watch` -- stream CI background472. CI fail -> diagnose, fix, push, re-monitor483. `code-reviewer` agent findings -> `/resolve-pr-feedback` triage, fix, reply, push494. **AI self-review cap**: up to 3 auto `code-reviewer` rounds. **Early-exit** when reviewer returns `APPROVED` or empty findings -- never run round N+1 on clean round N. After 3 rounds still noisy -> hand off to human.505. **Human review (incl cloud/Copilot)**: NO cap. Address EVERY thread. `pr-feedback-completeness-stop` hook blocks session exit until `bash scripts/pr-unresolved-count.sh` returns 0 and no CHANGES_REQUESTED reviews remain.5152## Phase 6: Compound5354After non-trivial tasks: "Learn something worth preserve?"5556- Write rule to `.claude/rules/<topic>.md` with `paths:` glob57- AI bug -> create eval/test fixture catch same error class5859## Done60611. Post final PR comment: changes, review findings, test coverage622. Request review: `gh pr edit <number> --add-reviewer <username>`633. Report PR URL + CI status644. **Stop.** No poll for human approval.6566## Entry Gate6768Before start, check work to ship:6970- No uncommitted changes AND no unpushed commits -> nothing do, stop71- On default branch, no feature branch -> **auto-spawn via `scripts/mux-worktree.sh <type>/<name>`** before proceed. Never ship from main. [ETHOS: Worktree Isolation]7273## Skills Composed7475| Skill | Phase | How |76|---|---|---|77| `self-reviewer` agent | 4b | Auto-dispatch on diff |78| `adversarial-reviewer` agent | 4b | Conditional (>50 lines or auth/security) |79| `/simplify` | 5 | Code quality review |80| `/visual-review` | 4/5 | Frontend screenshot, state, a11y, console, mobile/cross-browser review when UI changed |81| `/commit-push-pr` | 5 | Conventional commits + push + PR |82| `code-reviewer` agent | 5 | Fresh-eyes review on PR |83| `/resolve-pr-feedback` | 5b | Triage + fix review comments |8485See [REFERENCE.md](REFERENCE.md) for detailed checklists, gate logic, flowchart.
redpanda-data