jury

jury is a skill for Claude Code, Codex from TeamSPWK/nova. It costs 64 tokens per session (2,887 once invoked), scanned A, original, MIT.

A review method that asks several independent perspectives to judge an important code, plan, or security decision. It combines their results into a shared decision.

In plain words
What is it for?
Use it for code reviews, architecture or plan reviews, release-gate decisions, and security checks where one opinion is not enough.
Why use it?
A single reviewer can favor the first option they see or give too much weight to long explanations. Several perspectives make these biases easier to spot.

Skill for Claude CodeCodex

Part of the nova plugin — 14 skills, 19 commands, 6 agents, 5 hooks, 1 MCP server shipped together

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

Made for: Claude Code, Codex.

Or install nova, the plugin that ships this one along with the rest of its 14 skills, 19 commands, 6 agents, 5 hooks, 1 MCP server.

Wrote 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.

agentmods badge for jury

README.md
[![agentmods](https://agentmods.dev/badge/skills/teamspwk/nova/jury.svg)](https://agentmods.dev/skills/teamspwk/nova/jury)
Your own site
<a href="https://agentmods.dev/skills/teamspwk/nova/jury"><img src="https://agentmods.dev/badge/skills/teamspwk/nova/jury.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,887 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 $0.00064 $0.02887
Opus 5 $0.00032 $0.01443
Sonnet 5 $0.00013 $0.00577
Haiku 4.5 $0.00006 $0.00289

Measured 3d ago against content hash 8bf4806307a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jury 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 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.

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/skills/jury/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nova LLM Jury

적용 규칙 (on-demand 로드)

  • docs/nova-rules.md §10 관찰성 계약 — 최종 합의 판정 직후 jury_verdict 이벤트 기록

관찰성 훅 (v5.12.0+)

합의 판정 후 반드시:

bash hooks/record-event.sh jury_verdict "$(jq -cn \
  --arg cl "$CONSENSUS" \
  --argjson cd "$CHANGED" \
  '{consensus_level:$cl, changed_direction:$cd}')" 2>/dev/null || true

Safe-default: 기록 실패는 판정 반환에 영향 없음.

단일 LLM 심판은 위치 편향(position bias)과 장황함 편향(verbosity bias)이 있다. 다중 관점으로 평가하면 이 편향을 구조적으로 상쇄할 수 있다.

이 스킬은 3가지 모드로 호출된다:

모드 호출처 페르소나
코드 리뷰 /nova:review --jury Correctness / Design / User
Plan 리뷰 skills/deepplan Phase C (--jury 옵션) architect / security / qa
보안 진단 (Nova 개발자 전용) dev/commands/audit-self.md --jury (v5.23.0+) Red(공격자) / Blue(방어자) / Auditor(중재자)

모드 1: 코드 리뷰

/nova:review --jury 옵션으로 활성화한다.

Jury 구성 (3인)

각 Jury는 독립 서브에이전트로 실행한다:

Jury 관점 핵심 질문
Correctness 정확성 코드가 요구사항대로 동작하는가?
Design 설계 아키텍처 원칙과 일관되는가?
User 사용자 사용자가 문제 없이 쓸 수 있는가?

합의 프로토콜

Jury 합의 최종 판정
3/3 PASS PASS
2/3 PASS + 1 CONDITIONAL PASS with notes — 소수 의견 기록
2/3 PASS + 1 FAIL CONDITIONAL — FAIL 사유 검토 필요
2/3 FAIL 이상 FAIL

합의와 다른 판정을 낸 Jury의 의견은 반드시 기록한다.


모드 2: Plan 리뷰

skills/deepplan Phase C에서 --jury 옵션이 지정될 때 호출된다. 호출 컨텍스트에 mode: planfile: docs/plans/{slug}.md가 포함된다.

Jury 구성 (3인)

Plan 리뷰 전용 페르소나. 코드 리뷰 페르소나와 독립적이다.

Jury 관점 핵심 질문
architect 아키텍처 타당성 Plan의 Solution이 기존 시스템과 자연스럽게 연결되는가? 확장성과 유지보수성이 고려되었는가?
security 보안 경계 보안 경계, 권한 모델, 데이터 누출 시나리오가 Risk Map에 충분히 반영되었는가?
qa 검증 가능성 Verification Hooks의 Done 조건이 측정 가능한가? Sprint Contract 품질이 충분한가? 엣지 케이스가 누락되지 않았는가?

Plan 리뷰 페르소나 프롬프트

architect
역할: 시니어 아키텍트.
대상: docs/plans/{slug}.md

이 Plan의 아키텍처 타당성을 검토하라:
1. Solution이 기존 시스템 구조와 자연스럽게 연결되는가?
2. 확장성 문제(트래픽 증가, 데이터 증가)가 고려되었는가?
3. 다른 시스템 컴포넌트에 미치는 영향이 누락되지 않았는가?

판정: PASS 또는 FAIL. FAIL이면 구체적 이슈를 Critic Issues 포맷으로 반환하라.

Read the full file on GitHub · 229 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. 3d ago First seen · 229 lines · 64 tokens per session scan A 8bf4806307a2

Subscribe to this mod's changes

jury is a skill published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 2,887 once invoked, about $0.0003 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.

Related

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…

nowork-studio/notfair-plugin · 114 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

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.

alivecontext/alive · 57 tokens

codex-test-gen

Generate unit tests for specified functions using Codex MCP.

sd0xdev/sd0x-harness · 15 tokens

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…

ferdinandobons/brand-docs · 144 tokens

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.

moonlight-lupin/agent-skills · 66 tokens