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.
npx agentmods add commands/teamspwk/nova/nextgit clone --depth 1 https://github.com/TeamSPWK/novaWhat 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.
| Model | Per session | Once 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 |
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.
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 §8세션 상태 유지 (Known Gaps 필수, 즉시 트리거)docs/nova-rules.md §10관찰성 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
-
NOVA-STATE.md 확인 및 자동 생성:
- 프로젝트 루트의
NOVA-STATE.md파일을 읽는다 - 파일이 없으면: 아래 진단(Step 1-2) 결과를 기반으로
NOVA-STATE.md를 자동 생성한다git log --oneline -10으로 최근 작업 방향 파악docs/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 →/check또는/review추천 - Phase가
done이면 → "새 기능 시작 준비 완료" 표시
- 프로젝트 루트의
-
다음 항목을 모두 확인한다:
docs/plans/디렉토리의 .md 파일 목록과 개수docs/designs/디렉토리의 .md 파일 목록과 개수docs/verifications/디렉토리의 .md 파일 목록과 개수docs/decisions/디렉토리의 .md 파일 목록과 개수git log --oneline -10— 최근 커밋 10개git status— 커밋되지 않은 변경사항git diff --name-only HEAD~5..HEAD 2>/dev/null— 최근 변경된 파일
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.
- yesterday First seen · 209 lines · 18 tokens per session scan A 78f801a1649c
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.
Other commands, from other repositories
loopx
Run the loopx setup helper and read its output.
grow-scanner
Autonomous task: increase real-world adoption of the AgentDiscover scanner.
gedd-chat
You are a GEDD coaching assistant. You guide the user through building a golden evaluation dataset for their AI agent using Open Coding methodology, then help them evaluate and annotate responses — all without leaving Claude Code.
gedd
You are a GEDD coaching agent. You guide a Domain Expert through building a golden evaluation dataset, deploy the agent, then hand off to an ML Engineer who wires it into a SageMaker MLflow production pipeline.
gedd-status
Read session.json (use the Read tool) and display a concise dashboard. If the file doesn't exist, say so and suggest running /gedd to start.
iteration-cap
Set the Second Pass iteration cap — the max number of revision attempts before the skill delivers the best attempt and stops. Accepts a positive integer.