analyze

analyze is a skill for Claude Code, Codex from cubha/claude-workflow-plugins. It costs 119 tokens per session (2,977 once invoked), scanned A, original, MIT.

A codebase analysis workflow for existing projects. It explores the code, adds outside research, and produces a Markdown report about architecture, technical debt, security, performance, and possible improvements.

In plain words
What is it for?
Use it to audit an existing codebase, understand how its parts fit together, identify technical debt or security and performance concerns, and plan improvements.
Why use it?
It brings the project's structure and risks into one review, so you do not have to inspect every part manually. It is intended for projects that already contain code, not brand-new ones.

Skill for Claude CodeCodex

Part of the analyze plugin — 1 skill 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/cubha/claude-workflow-plugins/analyze
Any agent
npx skills add cubha/claude-workflow-plugins --skill analyze
Clone the repo
git clone --depth 1 https://github.com/cubha/claude-workflow-plugins

Made for: Claude Code, Codex.

Or install analyze, the plugin that ships this one along with the rest of its 1 skill.

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 analyze

README.md
[![agentmods](https://agentmods.dev/badge/skills/cubha/claude-workflow-plugins/analyze.svg)](https://agentmods.dev/skills/cubha/claude-workflow-plugins/analyze)
Your own site
<a href="https://agentmods.dev/skills/cubha/claude-workflow-plugins/analyze"><img src="https://agentmods.dev/badge/skills/cubha/claude-workflow-plugins/analyze.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,977 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 $0.00119 $0.02977
Opus 5 $0.00060 $0.01489
Sonnet 5 $0.00024 $0.00595
Haiku 4.5 $0.00012 $0.00298

Measured 3d ago against content hash 009e57663be9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze 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/analyze/skills/analyze/SKILL.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze — 프로젝트 심층 분석 파이프라인

$ARGUMENTS 에 대해 코드베이스를 탐색하고, 외부 리서치를 수행한 뒤, 종합 분석 보고서를 MD 파일로 출력한다.

SCAN → RESEARCH → ANALYZE → REPORT

적용 범위: 기존 코드베이스(브라운필드) 전용. 이 스킬의 SCAN은 package.json·기존 소스·아키텍처·기술부채를 감사한다. 코드가 전무한 그린필드 프로젝트에는 사용하지 않는다 — 그 경우 요구사항·리서치로부터 범위·스택을 확정하는 워크플로우(예: scope 스킬이 설치돼 있으면 활용)를 사용한다.


Phase 1: SCAN — 코드베이스 전체 탐색

1-1. 기본 컨텍스트 수집

Read 도구로 아래를 병렬 수집한다:

  • CLAUDE.md — 기술 스택, 구조, 규칙
  • package.json (또는 해당 언어의 의존성 파일) — 의존성 목록
  • 프로젝트 히스토리 문서 — 존재하면 로드 (예: docs/, CHANGELOG.md, ADR 등에 기록된 기술 결정사항·알려진 이슈)
  • README.md — 프로젝트 설명, 현재 문서 상태

1-2. 에이전트 병렬 탐색

Task 도구로 아래 3개 에이전트를 동시에 실행한다:

Agent A: 구조 탐색 (Explore, thoroughness: "very thorough")

프롬프트:

프로젝트의 전체 구조를 분석하라:
1. 디렉토리 트리 및 파일 구성
2. 진입점(entry point) 식별
3. 주요 모듈/컴포넌트 목록
4. 설정 파일 (빌드, 린트, 테스트 등) 현황
5. 의존성 패키지 분류 (core / UI / 유틸리티 / dev)
코드를 수정하지 말고 탐색 결과만 반환하라.
Agent B: 아키텍처 분석 (feature-dev:code-explorer)

프롬프트:

프로젝트의 아키텍처를 심층 분석하라:
1. 레이어 구조 (데이터 / 비즈니스 로직 / UI)
2. 상태 관리 패턴
3. 데이터 흐름 (입력 → 처리 → 출력)
4. 사용된 디자인 패턴 식별
5. 모듈 간 의존성 그래프 (주요 import 관계)
6. 추상화 수준 평가
코드를 수정하지 말고 분석 결과만 반환하라.
Agent C: 코드 품질 리뷰 (feature-dev:code-reviewer)

프롬프트:

프로젝트 전체 코드 품질을 리뷰하라:
1. 보안 취약점 (OWASP Top 10 기준)
2. 성능 병목 가능 지점
3. 기술 부채 식별 (하드코딩, 중복 코드, TODO/FIXME 등)
4. 테스트 커버리지 현황
5. 에러 핸들링 패턴 일관성
6. 프로젝트 컨벤션 준수도
confidence HIGH 이슈만 보고하라. 코드를 수정하지 말고 리뷰 결과만 반환하라.

Phase 2: RESEARCH — 외부 리서치

2-0. 기존 팀 리서치 결과 확인

docs/research/RESEARCH-*.md 파일이 존재하는지 Glob으로 탐색한다:

상황 동작
RESEARCH 파일 존재 Read로 로드 → 이미 조사된 항목 확인 → 해당 항목은 2-1, 2-2에서 생략
RESEARCH 파일 없음 2-1, 2-2를 전체 수행

사전 리서치 결과(docs/research/RESEARCH-*.md)가 이미 있으면(예: team-research 스킬이 설치돼 있어 미리 조사를 돌렸다면), 중복 조사를 방지하기 위해 이 단계를 자동 적용한다.

2-1. 기술 스택 리서치

Phase 1에서 파악한 핵심 기술 스택(상위 3~5개) 중 2-0에서 확인되지 않은 항목에 대해:

도구 조회 내용
Context7 각 라이브러리의 최신 버전, 주요 변경사항, 권장 패턴
WebSearch 해당 기술의 트렌드, 커뮤니티 평가, 대안 기술 비교

Read the full file on GitHub · 308 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 · 308 lines · 119 tokens per session scan A 009e57663be9

Subscribe to this mod's changes

analyze is a skill published in the GitHub repository cubha/claude-workflow-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 2,977 once invoked, about $0.0006 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

etsy-category-listing

Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…

browser-act/skills · 209 tokens

ix

This skill should be used when answering structural questions about a codebase: understanding what a symbol is, tracing flows, measuring change impact, finding callers/callees/imports, or detecting code smells. It drives the Ix CLI (ix map/explain/trace/impact/search/rank/smells) against a persistent code graph stored…

ix-infrastructure/Ix · 103 tokens

etsy-shipping-strategy

Shipping strategy — free shipping vs markup, shipping profiles, international shipping, tracking.

nexscope-ai/eCommerce-Skills · 21 tokens

deep-audit

Comprehensive adversarial audit of a theory, proof, math/econ paper, codebase, or set of claims — decompose into components, fan out independent skeptics that must return CONCRETE defects, adjudicate every finding with a separate judge, fix all confirmed defects, then re-verify. Use when correctness must be…

pedrohcgs/claude-code-my-workflow · 117 tokens

studio

Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.

AlpacaLabsLLC/skills-for-architects · 65 tokens

idea

Use when capturing ONE new idea the user voices and wants recorded — "save this idea", "I have an idea", "log this idea", "/idea", "idea: ...". Creates a provenance-tracked folder (one folder per idea) in your ideas repo, dedups against an index, optionally mirrors to a GitHub Project view filtered by label:idea. NOT…

serejaris/personal-corp-os · 135 tokens