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.
git clone --depth 1 https://github.com/TeamSPWK/novaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/teamspwk/nova/scan)<a href="https://agentmods.dev/commands/teamspwk/nova/scan"><img src="https://agentmods.dev/badge/commands/teamspwk/nova/scan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/teamspwk/nova/scan"><img src="https://agentmods.dev/badge/commands/teamspwk/nova/scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.01149 |
| Opus 5.5 | $0.00011 | $0.00460 |
| Sonnet 5.5 | $0.00006 | $0.00230 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
scan 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 1mo ago.
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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
새 프로젝트에 처음 투입됐을 때 코드베이스를 자동 분석하고 "어디를 먼저 봐야 하는지", "알려진 기술 부채는 무엇인지"를 요약한다.
Role
너는 신규 투입된 개발자에게 코드베이스 온보딩 브리핑을 제공하는 가이드다. 빠르고 정확하게 핵심만 짚는다. 불필요한 설명은 생략한다.
Execution
Step 1: 프로젝트 구조 분석
다음 파일과 디렉토리를 순서대로 확인한다:
CLAUDE.md— 프로젝트 규칙, 기술 스택, 구조 설명package.json/pyproject.toml/go.mod/Cargo.toml/pom.xml— 의존성과 스크립트- 디렉토리 구조 (최대 2단계 깊이)
README.md— 프로젝트 목적과 실행 방법NOVA-STATE.md— 현재 작업 상태 (있으면)
Step 2: 기술 스택 요약
감지된 파일 기반으로 스택을 자동 분류한다:
- 언어: (lockfile, 설정파일 기준)
- 프레임워크: (의존성 기준)
- 빌드/패키지 매니저: (lockfile 기준 — pnpm-lock.yaml, package-lock.json, yarn.lock, poetry.lock, go.sum 등)
- 테스트 도구: (devDependencies 또는 설정파일 기준)
- 인프라/배포: (Dockerfile, docker-compose, .github/workflows 등)
Step 3: 주요 진입점 식별
다음 패턴으로 진입점을 찾는다:
main,index,app,server,handler파일package.json의main,scripts.start,scripts.dev필드src/또는 최상위 소스 디렉토리의 루트 파일
Step 4: 기술 부채 수집
다음을 파일 전체에서 검색한다:
grep -rn "TODO\|FIXME\|HACK\|XXX\|DEPRECATED" --include="*.ts" --include="*.tsx" --include="*.js" --include="*.jsx" --include="*.py" --include="*.go" --include="*.rs" --include="*.java" .
- 건수 집계 (파일별)
- 상위 5개 발췌 (라인 포함)
- 밀도가 높은 파일/모듈 식별
Step 5: NOVA-STATE.md 브리핑 (있으면)
- Current Goal, Phase, Blocker 확인
- Tasks 작업 목록 (doing 상태)
- Known Gaps 확인
Step 6: "어디부터 볼지" 추천
분석 결과를 기반으로 다음 관점에서 우선순위를 추천한다:
- 핵심 비즈니스 로직이 있는 모듈/파일
- 최근 변경이 많은 영역 (
git log --oneline -20 --name-only기반) - 기술 부채가 집중된 파일
- 테스트 커버리지가 없어 보이는 고위험 영역
Output Format
━━━ Nova Scan: {프로젝트명} ━━━━━━━━━━━━━━━━
## 기술 스택
언어: {언어}
프레임워크: {프레임워크}
패키지 관리: {매니저} ({lockfile 기준})
테스트: {도구 또는 "미확인"}
인프라: {Docker/K8s/없음 등}
## 진입점
{파일 경로} — {한줄 설명}
{파일 경로} — {한줄 설명}
## 기술 부채 ({총 건수}건)
상위 파일: {파일} ({N}건), {파일} ({N}건)
주목할 항목:
- {파일:라인} — {내용}
- {파일:라인} — {내용}
## 현재 상태 {NOVA-STATE.md 있을 때만}
목표: {Goal}
Phase: {Phase}
Blocker: {있으면 내용, 없으면 "없음"}
진행 중: {Tasks doing 항목}
Known Gaps: {항목 또는 "없음"}
## 어디부터 볼까
1. {파일/모듈} — {이유}
2. {파일/모듈} — {이유}
3. {파일/모듈} — {이유}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
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.
- 1mo ago First seen · 109 lines · 28 tokens per session scan A 8683fe74c5d8
scan is a command published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 22d ago), licensed MIT. It adds 28 tokens to every session and 1,149 once invoked, about $0.0001 per session on Opus 5.5. 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
ccc-debug-session
Run a structured debug session: gather context, rank hypotheses, test them without editing code, then fix with a regression test and record the lesson. Use when a bug's cause is unclear.
perf
Structured performance investigation with baselines, profiling, and evidence-backed decisions.
bifrost-debug
Diagnose why the Bifrost gateway, memory injection, or skill discovery isn't working.
bug-fix
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.
fix
Execute audit findings by ID (human-gated) -- re-verify, fix, prove, ledger.
parallax-status
Summarize the current session and run package/native lifecycle diagnostics.