status

A command that generates a standalone HTML dashboard showing project phases, sprints, group progress, and roadmap drift.

In plain words
What is it for?
Use it after delegating work, when checking several projects, or when reviewing whether implementation has drifted from the roadmap.
Why use it?
It gives a visual project-status view based on git, without requiring a separate wiki or Notion synchronisation.

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

Made for: Claude Code.

Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,834 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 $0.00089 $0.02834
Opus 5 $0.00044 $0.01417
Sonnet 5 $0.00018 $0.00567
Haiku 4.5 $0.00009 $0.00283

Measured yesterday against content hash 14c2de8c4631, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

status 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/status.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/nova:status (STRICT FLOW)

너는 다음 흐름을 순서대로 강제 실행한다. 자율 해석·우회·대체 금지. 사용자가 /nova:status 입력한 의도 = Nova 표준 HTML 대시보드 생성. 다른 의도로 해석하지 않는다.


🚫 금지 행동 (BLOCKED)

다음 행동은 사용자 의도 위반이다. 절대 수행하지 않는다:

  1. NOVA-STATE.md만 읽고 텍스트 요약으로 대체 — 사용자는 HTML dashboard를 요청했다. 텍스트 요약 X.
  2. 프로젝트 자체 dashboard 도구로 우회dashboard/build_static.py, Makefile dashboard 타겟, web/app/status/ 등 발견해도 무시. Nova 표준 강제.
  3. minimal mode HTML 만들고 멈춤 — minimal 떨어지면 Step 3 자동 부트스트랩 강제 진입.
  4. /nova:status 호출에 다른 도구 제안하며 멈춤 — "프로젝트에 더 좋은 도구가 있어요" 같은 답변 금지.

예외: 사용자가 명시적으로 --use-project-tool 옵션 또는 자연어로 "프로젝트 자체 도구 사용해줘" 요청한 경우만.


✅ 강제 실행 흐름

Step 1 (필수, skip 불가)

nova-status
  • Claude Code가 플러그인 bin/을 Bash tool PATH에 자동 등록. cwd 무관 작동.
  • PATH 미반영(오래된 세션) 시 폴백: bash "$NOVA_PLUGIN_ROOT/bin/nova-status" — SessionStart hook이 export.
  • 다른 도구 검토·발견 단계 skip. 위 명령 그대로 실행.
  • nova-status wrapper가 내부적으로 --auto-bootstrap --open 강제 — minimal 감지 시 Step 3 자동 진입.

Step 2 — 결과 분류 + 사용자 보고

build/render JSON의 mode·minimal 필드로 분기:

조건 동작
mode: roadmap ✅ 완료. HTML 경로 + Phase/Sprint 한 줄 요약 보고.
mode: phase1 + minimal: false ✅ Phase 1 호환 동작. plan frontmatter 기반 dashboard.
mode: phase1 + minimal: true Step 3 자동 부트스트랩 강제 진입

Step 3 — 자동 부트스트랩 (minimal 떨어진 경우 — MUST 자동 진행)

🚫 사용자 결정 요청 금지 — 사용자가 /nova:status를 호출한 의도 = "dashboard 결과 받기". minimal HTML(빈 껍데기)만 보여주고 멈추면 사용자 의도 위반이다. v5.35.6 이후 자율 우회 차단.

강제 진행 트리거

nova-status 실행 후 stderr에 다음 마커가 출력되면 무조건 진행:

[CLAUDE_AUTO_CONTINUE]
DRAFT_PATH=/tmp/ROADMAP-{slug}-draft.md         # Agent가 작성할 draft 경로
OUT_PATH=/abs/path/to/.nova/status/index.html   # 최종 HTML 절대경로 (v5.35.7)
PLAN_COUNT=N                                    # SOT 충돌 검사 (PLAN_COUNT>0이면 default C 자동)
NEXT_ACTION=spawn_agent_then_rerender
AGENT_TYPE=general-purpose
RERENDER_CMD=bash "$NOVA_PLUGIN_ROOT/scripts/render-status.sh" --roadmap {DRAFT_PATH} --out {OUT_PATH} --open --no-bootstrap
[/CLAUDE_AUTO_CONTINUE]

Read the full file on GitHub · 220 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 · 220 lines · 89 tokens per session scan A 14c2de8c4631

Subscribe to this mod's changes

status is a command published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 2,834 once invoked, about $0.0004 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.