deepplan

A planning skill that explores a complex development task from several angles, combines the findings, and improves the plan through review. It is intended for difficult architecture choices or plans that are too shallow.

In plain words
What is it for?
Use it for highly complex work, architecture decisions, or when a normal development plan needs deeper investigation and independent criticism.
Why use it?
A quick plan can miss important technical options, risks, or checks before implementation starts.

Skill for Claude CodeCodex

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 skills/teamspwk/nova/deepplan
Any agent
npx skills add TeamSPWK/nova --skill deepplan
Clone the repo
git clone --depth 1 https://github.com/TeamSPWK/nova

Made for: Claude Code, Codex.

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,819 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 $0.00069 $0.04819
Opus 5 $0.00034 $0.02410
Sonnet 5 $0.00014 $0.00964
Haiku 4.5 $0.00007 $0.00482

Measured 2d ago against content hash 4073bfdb4984, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deepplan 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 2d 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.

Makes network callslowCapability

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

| 1 | {검증 가능한 Done 조건} | {grep/test/curl 등 구체적 명령} | Critical/Nice-to-have |
.claude/skills/deepplan/SKILL.md · 475 lines

How it starts

The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nova DeepPlan

자연어 요청을 받아 Explorer 3개를 병렬로 실행하고, 그 결과를 종합하여 Critic-Refiner 루프로 강화된 Plan 문서를 생성한다.

핵심 원칙

  • 기존 체계 침범 금지: CPS 골격을 유지한다. deepplan 출력물은 /nova:design, /nova:auto가 그대로 소비할 수 있어야 한다.
  • 구조화된 핸드오프: Explorer 3개의 출력 포맷을 사전 정의해서 Synthesizer가 예측 가능하게 통합한다.
  • Adaptive thinking 우선: Explorer/Critic/Refiner 서브에이전트에 고정 thinking budget을 강제하지 않는다. 모델이 작업 복잡도에 따라 자율로 조절한다. (Anthropic 권고 — 고정 budget은 복잡한 작업에서 열위)
  • Generator ≠ Evaluator: Critic(evaluator/jury)은 Plan을 작성한 컨텍스트와 독립된 서브에이전트로 실행한다.
  • 무한 루프 방지: --iterations 최대 3으로 clamp. Critic이 PASS를 내거나 iteration 소진 시 종료.

오케스트레이션 추적

Phase 진행 시 MCP 도구로 추적한다. MCP 도구가 사용 불가능한 환경에서는 추적 없이 실행한다.

시점 MCP 도구 호출
파이프라인 시작 orchestration_start
Phase 시작/완료 orchestration_update

Execution

사전 처리: 플래그 파싱 + NOVA-STATE.md 갱신

  1. $ARGUMENTS에서 요청 텍스트와 플래그를 분리한다.

    플래그 기본값 규칙
    --iterations=N 1 max(1, min(N, 3)) — 초과 시 3으로 clamp, 미만 시 1로 clamp
    --jury false true이면 Critic에서 jury 스킬 호출
  2. slug 추출 (orchestrator와 동일 규칙):

    • 따옴표(' 또는 ") 안의 텍스트를 추출한다. 따옴표가 없으면 플래그(--xxx)를 제외한 전체 텍스트를 사용한다.
    • 공백을 -로 치환한다.
    • 한글·영문·숫자·하이픈 이외의 특수문자를 제거한다. 한글은 유지한다.
    • slug가 빈 문자열이면 요청 첫 단어를 slug로 사용하고 경고를 출력한다: [DeepPlan] slug 추출 실패 — 첫 단어를 slug로 사용: {단어}
    • 예시: "건폐율 시각화 추가"건폐율-시각화-추가, "add carousel"add-carousel
  3. NOVA-STATE.md 갱신 (파일이 있을 때만):

    • Phase를 deep-planning으로 설정한다.
    • Last Activity 갱신:
      - /nova:deepplan → 시작 — docs/plans/{slug}.md | {ISO 8601}
      
    • 시계열은 events.jsonl 단일 진실원 (v5.44.0+): NOVA-STATE.md의 Recent Activity / Recently Done 표에 행 추가 X. 활동 기록은 hooks/record-event.sh(자동 호출)가 .nova/events.jsonl에, v3 marker 영역은 Stop hook이 scripts/registry-render-state.sh로 자동 갱신. AI는 Current/Phase/Refs/Risks 본문 스냅샷만 손편집 — 트림 의무 없음. (상세: skills/context-chain/SKILL.md)
  4. 로그 출력:

    [DeepPlan] 시작 — slug: {slug}, iterations: {N}, jury: {true/false}
    [DeepPlan] 출력 경로: docs/plans/{slug}.md
    

Read the full file on GitHub · 475 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. 2d ago First seen · 475 lines · 69 tokens per session scan A 4073bfdb4984

Subscribe to this mod's changes

deepplan is a skill published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 4,819 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

loopx-project

Use when connecting a repository or project goal document to LoopX, maintaining project-local goal state, refreshing stale dashboard status, syncing local projects into the shared global registry, or diagnosing LoopX CLI/PATH/status/history issues across multiple repos. For registering durable project materials such…

huangruiteng/loopx · 74 tokens

loopx-auto-research

Use when a LoopX worker is operating an auto-research lane, demo pane, frontier item, evidence packet, promotion/retirement decision, or visible tmux/Codex auto-research rehearsal. Identity must come from the LoopX role profile and quota/frontier packet; this skill only provides role-specific execution checklists…

huangruiteng/loopx · 79 tokens

loopx-benchmark

Use when a LoopX-managed goal runs, tracks, scores, or analyzes a benchmark experiment through benchmark-toolkit, including experiment-board rows, solver arms, integrity qualification, matched comparisons, or case insights. Do not use for casual benchmark discussion, ordinary software microbenchmarks, or eval mentions…

huangruiteng/loopx · 69 tokens

loopx-change-quality

Qualify the exact final diff for a LoopX-managed goal. Use when goal policy enables changequalityqualification, before a non-trivial delivery or merge, and when producing or repairing an exact-scope quality receipt. The workflow is language-neutral, permits at most one policy-authorized safe-fix pass, and never grants…

huangruiteng/loopx · 75 tokens

loopx-material

Operate an explicitly activated LoopX Material Lifecycle for a connected project. Use for material-store inventory, lossless migration, candidate/archive transitions, exact-read-backed ranking, ranked-entry rebuilds, bounded Explore intake, owner-gated apply, rollback, and audit. Do not use for ordinary one-off…

huangruiteng/loopx · 74 tokens

loopx-pr-review

Use for /loopx-pr-review or evidence-backed PR queue review. Run loopx pr-review first, execute the capability-owned review plan for each selected exact head, then publish full bilingual PR reviews (complete Chinese five-block review plus one concise English verdict) that match the verified findings. Use…

huangruiteng/loopx · 79 tokens