next

A project-status diagnosis and next-step recommendation command for the Nova workflow. It reads the project state, recent Git history, and planning, design, and verification documents.

In plain words
What is it for?
Use it to inspect the current phase, identify blockers and known gaps, recommend the next Nova command, and optionally include recent workflow measurements.
Why use it?
It helps when you are unsure what the project is currently doing or which task should come next. It can create a missing NOVA-STATE.md file from its diagnosis.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/teamspwk/nova/next
Clone the repo
git clone --depth 1 https://github.com/TeamSPWK/nova

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,356 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.03356
Opus 5 $0.00009 $0.01678
Sonnet 5 $0.00004 $0.00671
Haiku 4.5 $0.00002 $0.00336

Measured yesterday against content hash 78f801a1649c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

next scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/next.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

현재 프로젝트 상태를 진단하고 다음에 실행할 Nova 커맨드를 추천한다.

적용 규칙 (on-demand 로드)

  • docs/nova-rules.md §8 세션 상태 유지 (Known Gaps 필수, 즉시 트리거)
  • docs/nova-rules.md §10 관찰성 계약 — 진단 결과 하단에 KPI 요약 1줄 포함

KPI 요약 (v5.12.0+, 진단 결과 포함)

진단 결과 끝에 scripts/nova-metrics.sh --since 30d 출력을 1줄 요약으로 표시:

📊 KPI(30d): Process consistency: 78% (n=41) · Gap detection: 85% (n=13) · Rule evolution: N/A · Multi-perspective: 62% (n=8)

값이 모두 N/A (insufficient data)면 생략(경량). scripts/nova-metrics.sh 실행 실패도 생략(safe-default).

Role

너는 Nova Engineering의 워크플로우 가이드다. 프로젝트의 현재 상태를 분석하여 Nova 워크플로우에서 다음 단계를 추천한다.

Execution

  1. NOVA-STATE.md 확인 및 자동 생성:

    • 프로젝트 루트의 NOVA-STATE.md 파일을 읽는다
    • 파일이 없으면: 아래 진단(Step 1-2) 결과를 기반으로 NOVA-STATE.md를 자동 생성한다
      • git log --oneline -10으로 최근 작업 방향 파악
      • docs/plans/, docs/designs/, docs/verifications/ 스캔
      • 결과를 다음 템플릿으로 생성:
        # Nova State
        
        ## Current
        - **Goal**: {진단에서 추론한 현재 목표}
        - **Phase**: {planning|building|verifying|done 중 추론}
        - **Blocker**: none
        
        ## Tasks
        | Task | Status | Verdict | Note |
        |------|--------|---------|------|
        | {추천 액션} | todo | - | - |
        
        <!-- v5.44.0+: 시계열(Recent Activity/Recently Done)은 .nova/events.jsonl + v3 marker 자동 렌더가 진실원. AI/사용자 손편집 X. -->
        
        ## Refs
        - Plan: {docs/plans/xxx.md 또는 none}
        - Design: {docs/designs/xxx.md 또는 none}
        - Last Verification: {docs/verifications/xxx.md 또는 none}
        
      • 생성 후 사용자에게 "📋 NOVA-STATE.md를 자동 생성했습니다." 안내
    • 파일이 있으면: 읽고 상태 기반 추천
      • Blocker가 있으면 → 블로커 해결을 최우선 추천
      • Tasks에 doing 작업이 있으면 → 해당 작업 이어가기 추천
      • Phase가 verifying이면 → /check 또는 /review 추천
      • Phase가 done이면 → "새 기능 시작 준비 완료" 표시
  2. 다음 항목을 모두 확인한다:

    • docs/plans/ 디렉토리의 .md 파일 목록과 개수
    • docs/designs/ 디렉토리의 .md 파일 목록과 개수
    • docs/verifications/ 디렉토리의 .md 파일 목록과 개수
    • docs/decisions/ 디렉토리의 .md 파일 목록과 개수
    • git log --oneline -10 — 최근 커밋 10개
    • git status — 커밋되지 않은 변경사항
    • git diff --name-only HEAD~5..HEAD 2>/dev/null — 최근 변경된 파일

Read the full file on GitHub · 209 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 209 lines · 18 tokens per session scan A 78f801a1649c

Subscribe to this mod's changes

next is a command published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 3,356 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.