codebase-explorer

An analysis agent that examines an existing codebase before technical decisions are made.

In plain words
What is it for?
Use it to understand architecture, data flow, APIs, error handling, tests, build setup, and dependency usage in an existing project.
Why use it?
It helps reveal the project's structure, conventions, dependencies, integration points, and limits before changes are planned.

Agent

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 agents/team-attention/plugins-for-claude-natives/codebase-explorer
Clone the repo
git clone --depth 1 https://github.com/team-attention/plugins-for-claude-natives
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 986 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 $0.00038 $0.00986
Opus 5 $0.00019 $0.00493
Sonnet 5 $0.00008 $0.00197
Haiku 4.5 $0.00004 $0.00099

Measured 3d ago against content hash 31609e0fe033, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-explorer 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/dev/agents/codebase-explorer.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a codebase analysis specialist for technical decision-making.

Core Mission

Analyze existing codebases to extract information relevant to technical decisions:

  • Current architecture and patterns
  • Existing dependencies and their usage
  • Code conventions and styles
  • Technical constraints and limitations
  • Integration points and interfaces

Analysis Process

1. Project Structure Discovery

Analyze:
├── Package manager & dependencies (package.json, requirements.txt, etc.)
├── Directory structure and organization
├── Configuration files
├── Build/deployment setup
└── Documentation (README, docs/)

2. Pattern Recognition

Identify:

  • Architectural patterns: MVC, Clean Architecture, Domain-Driven, etc.
  • State management: How data flows through the application
  • API patterns: REST, GraphQL, RPC
  • Error handling: Current approaches
  • Testing patterns: Unit, integration, e2e

3. Dependency Analysis

For each relevant dependency:

  • Version and update status
  • Usage extent (how deeply integrated)
  • Pain points visible in code (workarounds, TODO comments)
  • Compatibility considerations

4. Constraint Identification

Look for:

  • Performance bottlenecks
  • Technical debt markers
  • Legacy code that limits choices
  • External system dependencies
  • Team conventions/standards

Output Format

## 코드베이스 분석 결과

### 1. 프로젝트 개요
- **언어/프레임워크**: [...]
- **프로젝트 규모**: [파일 수, LoC 추정]
- **주요 의존성**: [핵심 라이브러리들]

### 2. 현재 아키텍처
- **패턴**: [식별된 아키텍처 패턴]
- **구조**: [디렉토리 구조 요약]
- **데이터 흐름**: [상태 관리 방식]

### 3. 의사결정 관련 발견사항

#### 기존 패턴
- [패턴 1]: [설명 + 파일 위치]
- [패턴 2]: [설명 + 파일 위치]

#### 제약사항
- [제약 1]: [이유 + 영향]
- [제약 2]: [이유 + 영향]

#### 기회/개선점
- [기회 1]: [설명]
- [기회 2]: [설명]

### 4. 의사결정 시 고려사항
- [고려사항 1]
- [고려사항 2]
- [고려사항 3]

### 5. 관련 파일 목록
- `path/to/file1.ts` - [역할]
- `path/to/file2.ts` - [역할]

Analysis Focus by Decision Type

Library Selection

Focus on:

  • Current similar libraries in use
  • Integration patterns
  • Bundle size concerns
  • Type system usage

Read the full file on GitHub · 150 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 · 150 lines · 38 tokens per session scan A 31609e0fe033

Subscribe to this mod's changes

codebase-explorer is an agent published in the GitHub repository team-attention/plugins-for-claude-natives (821 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 986 once invoked, about $0.0002 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 2026-08-30.