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 skills/teamspwk/nova/orchestratornpx skills add TeamSPWK/nova --skill orchestratorgit clone --depth 1 https://github.com/TeamSPWK/novaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/teamspwk/nova/orchestrator)<a href="https://agentmods.dev/skills/teamspwk/nova/orchestrator"><img src="https://agentmods.dev/badge/skills/teamspwk/nova/orchestrator.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00060 | $0.08405 |
| Opus 5 | $0.00030 | $0.04202 |
| Sonnet 5 | $0.00012 | $0.01681 |
| Haiku 4.5 | $0.00006 | $0.00840 |
Grade A, and why
orchestrator scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 실제 동작 (curl/playwright) | 생략 | 필수 | How it starts
The opening of the file, as written. The whole thing — 612 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nova Orchestrator
적용 규칙 (on-demand 로드)
docs/nova-rules.md §2Generator-Evaluator 분리 + 핸드오프 (self_verify 필드)docs/nova-rules.md §6복잡한 작업의 스프린트 분할 (각 스프린트 완료 = Evaluator 필수)docs/nova-rules.md §10관찰성 계약 — Phase 전이·스프린트 전환 시 이벤트 기록
관찰성 훅 (v5.12.0+)
Phase 전이 시 (예: Phase A→B, pending→running→completed) 이벤트 기록:
bash hooks/record-event.sh phase_transition "$(jq -cn \
--arg oid "$ORCHESTRATION_ID" \
--arg phase "$PHASE_NAME" \
--arg from "$FROM_STATUS" \
--arg to "$TO_STATUS" \
'{orchestration_id:$oid, phase_name:$phase, from_status:$from, to_status:$to}')"
Sprint 전환 시:
bash hooks/record-event.sh sprint_started "{...}" # 착수
bash hooks/record-event.sh sprint_completed "{...}" # 종료 (verdict 포함)
블로커 감지/해소 시 (§7 분류):
bash hooks/record-event.sh blocker_raised "$(jq -cn --arg t \"$BTYPE\" --arg c \"$CAUSE\" '{blocker_type:$t, cause:$c}')" 2>/dev/null || true
bash hooks/record-event.sh blocker_resolved "$(jq -cn --arg t \"$BTYPE\" --arg r \"$RESOLUTION\" '{blocker_type:$t, resolution:$r}')" 2>/dev/null || true
Safe-default: 실패는 exit 0, 상위 파이프라인 영향 없음.
자연어 한 줄을 받아서 설계→구현→검증→수정 전체 파이프라인을 자동 실행한다.
핵심 원칙
- 설계가 구현보다 먼저다 (CPS)
- Generator ≠ Evaluator (역할 분리)
- 구조화된 프롬프트가 자연어보다 낫다
- 멀티 프로젝트 병렬 지원
오케스트레이션 추적 (MCP 도구) — 필수 계약
이 섹션은 soft 권고가 아니라 계약이다. 각 Phase 진행 상황은 반드시 MCP 도구로 추적한다. 세션 중단 시 .nova-orchestration.json으로 복구 지점이 되며, 누락 시 Evolve 피드백 루프의 관찰 데이터가 공백이 된다.
| 시점 | MCP 도구 호출 | 누락 시 영향 |
|---|---|---|
| Phase 0: 오케스트레이션 등록 | orchestration_start — task, complexity, phases 전체 등록 |
세션 끊기면 복구 불가 + 외부에서 진행 조회 불가 |
| Phase N 시작 | orchestration_update — status: "running" |
어느 Phase에서 끊겼는지 모름 |
| Phase N 완료 | orchestration_update — status: "completed" + result |
Phase 소요 시간·산출물 메트릭 공백 |
| Phase N 실패 | orchestration_update — status: "failed" + result |
실패 패턴 분석 불가 |
| 상태 확인 | orchestration_status — 현재 진행 상황 조회 |
(조회용, 선택) |
Phase 0: 오케스트레이션 등록 (무조건 최우선)
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.
- 3d ago First seen · 612 lines · 60 tokens per session scan A 7f4e28f82050
orchestrator is a skill published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 8,405 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.
Other skills, from other repositories
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
codex-test-gen
Generate unit tests for specified functions using Codex MCP.
brand-docx
Brand-aware Word engine. Use to (1) EXTRACT a company's brand from a Word template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE new on-brand .docx documents FROM a saved profile. Trigger on "extract our brand", "learn/match this template", "use our…
travel-itinerary
Create, update, sanitize, route, and export structured business-trip itineraries from booking confirmations, emails, tickets, PDFs, screenshots, calendar invites, or notes. Use for day-by-day itinerary generation, privacy-safe sharing, route links, and Markdown/PDF/DOCX/Google Doc/ICS exports.