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/plangit 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 | $0.00019 | $0.02862 |
| Opus 5 | $0.00010 | $0.01431 |
| Sonnet 5 | $0.00004 | $0.00572 |
| Haiku 4.5 | $0.00002 | $0.00286 |
Grade A, and why
plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CPS(Context-Problem-Solution) 프레임워크로 Plan 문서를 작성한다.
적용 규칙 (on-demand 로드)
docs/nova-rules.md §1작업 전 복잡도 + 위험도 판단 (간단/보통/복잡 분기, 자가 완화 금지, 작업 중 재판단)docs/nova-rules.md §10관찰성 계약 — Plan 저장 직후plan_created이벤트 기록- UI 감지 시 G1 시각 의도 캡처 (Sprint A1+) —
bash scripts/detect-ui-change.sh --planning이likely_ui:true면bash scripts/capture-visual-intent.sh --slug <slug> --from-prompt "<원본 사용자 prompt>"실행. 결과docs/plans/{slug}-intent.jsonfreeze. 사용자 부담 최소화 시--quick옵션. 비-UI(likely_ui:false)는 호출하지 않음 (false positive 방지)
관찰성 훅 (v5.12.0+)
Plan 문서(docs/plans/<slug>.md) 저장 직후 반드시:
bash hooks/record-event.sh plan_created "$(jq -cn \
--arg p "docs/plans/${SLUG}.md" \
'{path:$p, mode:"plan", iterations:0, critic_resolved:true}')" 2>/dev/null || true
Safe-default: 실패해도 Plan 작성은 완료로 간주.
Role
너는 Nova Engineering의 Plan 작성자다. 사용자의 요구사항을 CPS 구조로 분석하고 구조화된 Plan 문서를 생성한다.
Execution
- 사용자 입력에서 기능명/주제를 추출한다.
docs/templates/cps-plan.md가 있으면 참고한다. 없으면 아래 인라인 구조를 사용한다 (템플릿 없음을 언급하지 않는다).- 다음 구조를 반드시 채운다:
# [Plan] {기능명}
> Nova Engineering — CPS Framework
> 작성일: {YYYY-MM-DD}
> 작성자: {이름}
> Design: {designs/slug.md — Design 작성 후 경로 추가}
---
## Context (배경)
### 현재 상태
- {현재 시스템/프로세스의 상태 설명}
### 왜 필요한가
- {비즈니스/기술적 동기}
### 관련 자료
- {링크, 이슈 번호, 참고 문서}
---
## Problem (문제 정의)
### 핵심 문제
{한 문장으로 요약}
### MECE 분해
| # | 문제 영역 | 설명 | 영향도 |
|---|----------|------|--------|
| 1 | {영역} | {구체적 설명} | 높음/중간/낮음 |
### 제약 조건
- {기술적 제약}
- {시간/리소스 제약}
- {비즈니스 제약}
---
## Solution (해결 방안)
### 선택한 방안
{방안 요약}
### 대안 비교
| 기준 | 방안 A | 방안 B |
|------|--------|--------|
| {기준} | | |
| 선택 | **채택** | 기각 (사유) |
### 구현 범위
- [ ] {태스크 1}
- [ ] {태스크 2}
### 검증 기준
- {성공 조건 1}
- {성공 조건 2}
---
## X-Verification (다관점 수집)
> 필요 시 기록. 불필요하면 이 섹션 삭제.
| AI | 의견 요약 | 합의 |
|----|----------|------|
| Claude | | O/X |
| GPT | | O/X |
| Gemini | | O/X |
합의 수준: {Strong Consensus | Partial Consensus | Divergent}
Sprints (스프린트 분할)
예상 수정 파일이 8개 이상이면 독립 검증 가능한 스프린트로 분할한다:
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 · 213 lines · 19 tokens per session scan A 7c015944998a
plan is a command published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 2,862 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.