run

A full development cycle that carries out an implementation and then verifies the result, with an option to verify existing work only.

In plain words
What is it for?
Use it for implementation followed by validation, or use verify-only when another system has already made the changes and needs an independent check.
Why use it?
It keeps coding and checking connected, so changes are tested as part of the same workflow. It also records sprint and blocker events when those records are available.

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

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,142 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00026 $0.04142
Opus 5 $0.00013 $0.02071
Sonnet 5 $0.00005 $0.00828
Haiku 4.5 $0.00003 $0.00414

Measured yesterday against content hash bacba4739461, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- 핵심 API: curl로 주요 엔드포인트 정상 응답 확인
.claude/commands/run.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

적용 규칙 (on-demand 로드)

  • docs/nova-rules.md §5 검증 경량화 원칙 (기본 Lite, --strict Full)
  • docs/nova-rules.md §6 복잡한 작업의 스프린트 분할 (8+ 파일 → 독립 검증 가능한 스프린트)
  • docs/nova-rules.md §7 블로커 분류 (Auto/Soft/Hard, 2회 실패 시 강제 분류)
  • docs/nova-rules.md §10 관찰성 계약 — 스프린트/블로커 이벤트 기록

관찰성 훅 (v5.12.0+)

  • Sprint 착수: bash hooks/record-event.sh sprint_started "$(jq -cn --arg n \"$SPRINT\" --argjson pf $PLANNED_FILES '{sprint_name:$n, planned_files:$pf}')" 2>/dev/null || true
  • Sprint 완료: bash hooks/record-event.sh sprint_completed "$(jq -cn --arg n \"$SPRINT\" --arg v \"$VERDICT\" --argjson rt $REGRESSION_PASS '{sprint_name:$n, verdict:$v, regression_tests_pass:$rt}')" 2>/dev/null || true
  • 블로커 감지: bash hooks/record-event.sh blocker_raised "$(jq -cn --arg t \"$BTYPE\" --arg c \"$CAUSE\" '{blocker_type:$t, cause:$c}')" 2>/dev/null || true
  • 블로커 해소: bash hooks/record-event.sh blocker_resolved "$(jq -cn --arg t \"$BTYPE\" --arg r \"$RESOLUTION\" '{blocker_type:$t, resolution:$r}')" 2>/dev/null || true

Safe-default: 기록 실패는 run 사이클 진행에 영향 없음.

Role

너는 Nova Quality Gate의 종합 검증자다. 기본 모드에서는 구현 + 검증을 한 사이클로 수행한다. --verify-only 모드에서는 검증만 수행한다 (외부 오케스트레이터 연동용).

핵심 원칙

  • 검증은 반드시 독립 서브에이전트로 실행한다 (Generator-Evaluator 분리)
  • 자동 재시도는 FAIL 판정에만, 최대 1회
  • CONDITIONAL은 사용자에게 판단을 넘긴다
  • 기본은 경량(--fast), 명시적 요청 시만 정밀(--strict)

Execution

Phase 0: Mode & Preflight

모드 판별

입력에서 모드를 판별한다:

플래그 모드 동작
(없음) Full Cycle Generator 서브에이전트 → Evaluator 서브에이전트
--verify-only Verify Only Evaluator 서브에이전트만 (현행 동작)
--with-refiner GAN 3단 Evaluator FAIL 시 refiner 서브에이전트 호출. 수정안 제시, 자동 적용 없음.

Preflight Check

  1. 변경된 파일 목록 확인 (git diff --name-only)
  2. 관련 설계 문서 탐색 (docs/designs/, docs/plans/)
  3. 테스트 존재 여부 확인

Phase 1: Risk Assessment

변경 규모와 위험도를 자동 판단하여 검증 강도를 결정한다.

규모 기준 검증 강도
Small 1~2 파일, 단순 변경 Lite: 정적 분석만
Medium 3~7 파일 Standard: 정적 + 구조적 리뷰
Large 8+ 파일 또는 다중 모듈 Full: 정적 + 구조적 + 설계 정합성

Read the full file on GitHub · 324 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 · 324 lines · 26 tokens per session scan A bacba4739461

Subscribe to this mod's changes

run is a command published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 4,142 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.