multi-perspective-review

multi-perspective-review is a skill for Claude Code, Codex from This-HW/claude-code-kit. It costs 27 tokens per session (3,552 once invoked), scanned A, original, MIT.

A collaborative review method that examines a plan or document from ten viewpoints, including requirements, technical design, security, user experience, data, and code quality. The viewpoints discuss their findings in three rounds and produce an agreed list of priorities and actions.

In plain words
What is it for?
Reviewing complex plans, designs, and documents; comparing trade-offs; checking areas such as security, dependencies, data structure, usability, and maintainability.
Why use it?
It helps reveal missing requirements, conflicts, risks, and wider system effects that a single reviewer may overlook.

Skill for Claude CodeCodex

Part of the claude-code-kit plugin — 19 skills, 4 hooks 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/this-hw/claude-code-kit/multi-perspective-review
Any agent
npx skills add This-HW/claude-code-kit --skill multi-perspective-review
Clone the repo
git clone --depth 1 https://github.com/This-HW/claude-code-kit

Made for: Claude Code, Codex.

Or install claude-code-kit, the plugin that ships this one along with the rest of its 19 skills, 4 hooks.

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 multi-perspective-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/this-hw/claude-code-kit/multi-perspective-review.svg)](https://agentmods.dev/skills/this-hw/claude-code-kit/multi-perspective-review)
Your own site
<a href="https://agentmods.dev/skills/this-hw/claude-code-kit/multi-perspective-review"><img src="https://agentmods.dev/badge/skills/this-hw/claude-code-kit/multi-perspective-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,552 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 $0.00027 $0.03552
Opus 5 $0.00014 $0.01776
Sonnet 5 $0.00005 $0.00710
Haiku 4.5 $0.00003 $0.00355

Measured 3d ago against content hash 34fc2179ea18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-perspective-review 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.

plugins/common/skills/multi-perspective-review/SKILL.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

multi-perspective-review: 다관점 협업 리뷰

Deliberation Pattern 기반 문서 검토 10개 관점의 전문가가 의견 교류하며 합의 도출


개요

이 스킬은 복잡한 기획/설계 문서를 여러 관점의 전문가가 협업하여 검토합니다. 단순 체크리스트가 아닌, 의견 교류합의 도출 과정을 통해 깊이 있는 리뷰를 제공합니다.

핵심 특징:

  • 10개 관점: Requirements, Technical, Security, UX, Business Logic, Dependencies, Code Quality, Metrics, Data/Schema, Devil's Advocate
  • 3-Round Deliberation: 초기 의견 → 상호 검토 → 합의 도출
  • 충돌 해결: 관점 간 상충 의견을 트레이드오프 분석으로 해결
  • 영향도 분석: 변경사항의 시스템 전체 영향 평가
  • 최종 합의안: Critical/Important/Nice-to-have 분류 + 액션 아이템

10개 관점 (Perspectives)

관점 역할 관련 에이전트 포커스
Requirements 기획자 clarify-requirements P0 모호함, 엣지 케이스, 비기능 요구사항
Technical 개발자 plan-implementation 기술적 실현가능성, 개발 기간, 시스템 충돌
Security 보안 security-scan 인증/권한, 민감 데이터, 공격 벡터
UX/Flow UX 디자이너 design-user-journey 사용자 흐름, 상호작용, 접근성
Business Logic 비즈니스 분석가 define-business-logic 비즈니스 규칙, 도메인 로직, 정책
Dependencies 아키텍트 analyze-dependencies 외부 연동, 라이브러리, 시스템 간 의존성
Code Quality 리뷰어 review-code 코드 품질, 유지보수성, 테스트 가능성
Metrics 데이터 엔지니어 define-metrics 성능 지표, 모니터링, SLA
Data/Schema DB 설계자 design-database 스키마 설계, 데이터 모델, 마이그레이션
Devil's Advocate 전략 비평가 devils-advocate 실패 시나리오, 설계 약점, 리스크 정량화

상세: perspectives-guide.md


워크플로우 (3-Round Deliberation)

┌──────────────────────────────────────────┐
│ Round 0: Facilitation (사전 준비)        │
│   → Facilitator가 문서 분석              │
│   → 필요한 관점 식별                     │
│   → 각 관점의 초점 영역 정의             │
│   → common_context_files 출력            │
└──────────────────────────────────────────┘
                    ↓
┌──────────────────────────────────────────┐
│ Context 수집 (메인 Claude)               │
│   → facilitator 결과에서 Level 1 파일 추출│
│   → CLAUDE.md 읽기                       │
│   → planning-protocol.md 읽기            │
│   → Meta 에이전트용 Level 2 파일 별도 준비│
└──────────────────────────────────────────┘
                    ↓
┌──────────────────────────────────────────┐
│ Round 1: 초기 의견 수집 (병렬)           │
│   → 각 관점의 에이전트 동시 실행         │
│   → Level 1 Context를 prompt에 포함      │
│   → Meta 에이전트는 Level 2도 포함       │
│   → 독립적 의견 도출                     │
│   → Synthesizer가 종합 (중복/충돌 식별)  │
└──────────────────────────────────────────┘
                    ↓
┌──────────────────────────────────────────┐
│ Round 2: 상호 검토 (순차)                │
│   → Round 1 의견을 컨텍스트로 포함       │
│   → 다른 관점 의견 고려하여 재검토       │
│   → 추가 이슈 식별 및 충돌 제안          │
└──────────────────────────────────────────┘
                    ↓
┌──────────────────────────────────────────┐
│ Round 3: 합의 도출                       │
│   → Consensus-Builder가 충돌 분석        │
│   → 트레이드오프 제시                    │
│   → 합의안 도출 (필요시 사용자 질문)     │
│   → Impact-Analyzer가 영향도 분석        │
│   → Synthesizer가 최종 리포트 작성       │
└──────────────────────────────────────────┘

Read the full file on GitHub · 408 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 408 lines · 27 tokens per session scan A 34fc2179ea18

Subscribe to this mod's changes

multi-perspective-review is a skill published in the GitHub repository This-HW/claude-code-kit (4 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 3,552 once invoked, about $0.0001 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

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

mochi-remind

Handle due reminders — notify the user with natural language and mark them done.

kirodotdev/KiroCrew · 20 tokens