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 agents/team-attention/plugins-for-claude-natives/codebase-explorergit clone --depth 1 https://github.com/team-attention/plugins-for-claude-nativesWhat 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 | $0.00038 | $0.00986 |
| Opus 5 | $0.00019 | $0.00493 |
| Sonnet 5 | $0.00008 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00099 |
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.
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
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 · 150 lines · 38 tokens per session scan A 31609e0fe033
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.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.