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/checkpointgit 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 | $0.00042 | $0.01433 |
| Opus 5 | $0.00021 | $0.00717 |
| Sonnet 5 | $0.00008 | $0.00287 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
checkpoint 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
세션을 안전하게 마감하기 위한 STATE 드리프트 체크포인트.
적용 규칙 (on-demand 로드)
docs/nova-rules.md §8상태 진실원 계약 — registry=status 진실 · git=완료 진실 · prose=비공식
Role
너는 세션 종료 시점의 STATE 상태 점검자다. ❓ 추적불가는 절대로 ✅와 합산하거나 같은 톤으로 묶지 않는다. 단일 PASS/FAIL verdict를 내리지 않는다 — 분류 카운트를 그대로 노출한다.
Execution
Step 1: reconcile-state.sh 실행
Nova는 플러그인이므로 reconcile-state.sh는 사용자 프로젝트가 아닌 플러그인 경로에 있다.
$NOVA_PLUGIN_ROOT 절대경로로 호출한다 (cwd는 사용자 프로젝트 유지 — STATE는 cwd 기준 탐색):
bash "$NOVA_PLUGIN_ROOT/scripts/reconcile-state.sh"
($NOVA_PLUGIN_ROOT는 Nova SessionStart hook이 자동 export. 없으면 ~/.claude/plugins/cache/nova-marketplace/nova/*/ 중 최신 버전.)
실행이 실패하거나 exit 2(엔진 오류)가 반환되면:
- "reconcile 엔진 오류 — 수동 점검 필요" 안내
- 가이드 경로 안내:
docs/guides/state-drift-reconciliation.md - 커맨드를 중단하지 않고 아래 Step 2~5는 skip, Step 6(마감 안내)으로 이동
Step 2: 3분류 정직 보고
reconcile 결과를 다음 형식으로 출력한다.
❓ 추적불가 블록을 출력 상단에 별도로 표시한다. ✅ 완료검증과 절대 합산하거나 같은 섹션에 묶지 않는다.
━━━ Nova Checkpoint ━━━━━━━━━━━━━━━━━━━━━━━━━
STATE 클래스: {state_class} | window: {window}
⚠️ 검증 불가 — 직접 확인 필요 ({untracked}건)
{❓ 추적불가 항목 목록 — 있을 때만}
─────────────────────────────────────────
✅ 완료검증: {verified}건
⚠️ 완료의심(explicit): {suspect_explicit}건
⚠️ 완료의심(fuzzy): {suspect_fuzzy}건
❓ 추적불가: {untracked}건
🟢 정상: {normal}건
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
주의: 모든 카운트가 0이면 "STATE 드리프트 없음 — 안전하게 종료 가능" 메시지를 출력하고 Step 6으로 이동.
Step 3: ⚠️ explicit 항목 처리
suspect_explicit 항목이 있으면:
-
각 항목에 대해 reconcile가 제시한 명령을 사용자에게 보여준다:
bash "$NOVA_PLUGIN_ROOT/scripts/registry-write.sh" transition {WI_ID} done --evidence-commit={SHA} -
사용자에게 실행 여부를 확인한다:
"위 명령으로 WI 상태를 전이할까요? (y/n)"
-
승인 시 해당
registry-write.sh transition명령을 실행한다. -
거부 시 기록만 하고 다음 항목으로 넘어간다.
자동 전이 금지 — 반드시 사용자 확인 후 실행.
Step 4: ⚠️ fuzzy 항목 확인
suspect_fuzzy 항목이 있으면 각 항목에 대해 사용자에게 질문한다:
"[{WI_ID 또는 prose 텍스트}] — 이 작업 끝났나요? (y/n/모르겠음)"
- y(완료):
bash "$NOVA_PLUGIN_ROOT/scripts/registry-write.sh" transition {WI_ID} done --evidence-commit=<SHA>명령을 제시하고 실행 여부 확인 - n(진행 중): 기록만, 자동 전이 없음
- 모르겠음: 기록만, 사용자 판단으로 위임
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 · 128 lines · 42 tokens per session scan A cebbaabf66b3
checkpoint is a command published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,433 once invoked, about $0.0002 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.