원클릭으로
preflight
Pre-sprint health check — git status, build, arch drift, infra, UX audit. Run before /prd to get a go/no-go verdict.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Pre-sprint health check — git status, build, arch drift, infra, UX audit. Run before /prd to get a go/no-go verdict.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | preflight |
| description | Pre-sprint health check — git status, build, arch drift, infra, UX audit. Run before /prd to get a go/no-go verdict. |
| argument-hint | [sprint e.g. v5] |
| allowed-tools | Read, Grep, Glob, Write, Bash, Task |
You are running a pre-sprint health check for the Kapi platform.
Sprint: $ARGUMENTS
Output: ./docs/operations/sprints/$ARGUMENTS/preflight.md
Run this BEFORE /prd so the sprint is planned against accurate state, not stale status.md numbers.
Run all of these Bash commands now. They are independent — run them in parallel if possible.
Git status:
git fetch origin --quiet 2>/dev/null || true
git rev-parse --short origin/main 2>/dev/null
git rev-parse --short origin/dev 2>/dev/null
git rev-parse --short HEAD
git rev-parse --abbrev-ref HEAD
git rev-list --count origin/main..origin/dev 2>/dev/null
git rev-list --count origin/dev..HEAD 2>/dev/null
git rev-list --count HEAD..origin/dev 2>/dev/null
git status --porcelain
git log --oneline -5
Build + lint (run cd to kapi-platform first if not already there):
npm run build 2>&1 | tail -15
npm run lint 2>&1 | tail -10
Read agents.md for detailed instructions on each agent. Use the Task tool to launch all three agents in a SINGLE message (three parallel tool calls). Do not wait for one before starting the next.
Wait for all three agents before Phase 3.
Create the preflight report using the format in templates/report.md.
After writing the file, print this to the conversation:
preflight $ARGUMENTS complete:
Git {✅ in sync / ⚠️ N ahead+behind / N uncommitted}
Build {✅ clean / ❌ N errors}
Arch {✅ clean / ⚠️ N issues (N critical)}
Infra {✅ healthy / ⚠️ N issues}
UX {N/10 / skipped}
──────────────────────────────────────────
Verdict: {Green / Caution / Blocked}
Report: docs/operations/sprints/$ARGUMENTS/preflight.md
| Condition | Verdict |
|---|---|
| Build has errors | ❌ Blocked — cannot start sprint |
| Arch has critical drift (>20% overstatement) | ⚠️ Caution — update status.md before /prd |
| Infra health checks fail on staging | ⚠️ Caution — investigate before Block D smoke tests |
| Local has uncommitted changes | ⚠️ Caution — commit or stash before /dev |
| Everything passes | ✅ Green |
Multiple issues: use the most severe verdict level.
Read ../blackboard/posting.md for the posting convention.
blocker — this is critical, other terminals need to know.finding.Plan a sprint interactively — reads backlog and board, brainstorms with you, writes prd.md + tasks.md.
Rate an agent's work. Records approve/reject/edit decision in kapi/decisions.yaml for HITL competence tracking.
End-of-session debrief. Interactive 5-10 min conversation that captures your thinking state — intent, open decisions, blockers, what to do next. Run before stepping away.
Pick the next unchecked task from the sprint and implement it with TDD. Reads board, posts available, implements, commits.
Quick write to the blackboard. Use for findings, decisions, blockers, handoffs, or queued ideas you want to capture without losing your flow.
Start-of-session briefing. Reads blackboard, checkpoints, git history to reconstruct where your head was. Run when returning after hours or days away.