checkpoint

A session-closing check for comparing the recorded project state with what was actually completed in Git. It separates verified work, suspected work, and items that cannot be tracked.

In plain words
What is it for?
Use it before ending a coding session to run state reconciliation and produce a clear count and list of verified, doubtful, and untracked items.
Why use it?
It prevents unfinished or unverified work from being reported as complete. It also shows when the checking process itself fails and manual review is needed.

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/checkpoint
Clone the repo
git clone --depth 1 https://github.com/TeamSPWK/nova

Made for: Claude Code.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,433 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 $0.00042 $0.01433
Opus 5 $0.00021 $0.00717
Sonnet 5 $0.00008 $0.00287
Haiku 4.5 $0.00004 $0.00143

Measured yesterday against content hash cebbaabf66b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/commands/checkpoint.md · 128 lines

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 §8 상태 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.sh사용자 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:

  1. 각 항목에 대해 reconcile가 제시한 명령을 사용자에게 보여준다:

    bash "$NOVA_PLUGIN_ROOT/scripts/registry-write.sh" transition {WI_ID} done --evidence-commit={SHA}
    
  2. 사용자에게 실행 여부를 확인한다:

    "위 명령으로 WI 상태를 전이할까요? (y/n)"

  3. 승인 시 해당 registry-write.sh transition 명령을 실행한다.

  4. 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

Read the full file on GitHub · 128 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 · 128 lines · 42 tokens per session scan A cebbaabf66b3

Subscribe to this mod's changes

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.