Borrowing it
Nothing to install: this file belongs to nainsharma01/claude-code-visualizer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nainsharma01/claude-code-visualizer/master/.claude/skills/agent-skill-visualizer/SKILL.mdgit clone --depth 1 https://github.com/nainsharma01/claude-code-visualizerWrote 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.
[](https://agentmods.dev/skills/nainsharma01/claude-code-visualizer/agent-skill-visualizer)<a href="https://agentmods.dev/skills/nainsharma01/claude-code-visualizer/agent-skill-visualizer"><img src="https://agentmods.dev/badge/skills/nainsharma01/claude-code-visualizer/agent-skill-visualizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nainsharma01/claude-code-visualizer/agent-skill-visualizer"><img src="https://agentmods.dev/badge/skills/nainsharma01/claude-code-visualizer/agent-skill-visualizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.00644 |
| Opus 5.5 | $0.00022 | $0.00258 |
| Sonnet 5.5 | $0.00011 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
agent-skill-visualizer 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 2mo 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.
What it actually says
Agent-Skill Visualizer
Claude Code 프로젝트의 .claude/ 폴더 구조를 분석하여 에이전트와 스킬 간의 관계를 인터랙티브한 노드 그래프로 시각화합니다.
사용 시점
- "에이전트 구조 보여줘"
- "스킬 의존성 확인해줘"
- "에이전트와 스킬 관계 시각화해줘"
- "프로젝트 구조 그래프로 보고 싶어"
실행 방법
1. 데이터 생성 (Python 스캐너)
cd .claude/skills/agent-skill-visualizer
# 현재 프로젝트 스캔
python scripts/scan_agents_skills.py ../../../ --output webapp/public/data/graph-data.json
# 다른 프로젝트 스캔
python scripts/scan_agents_skills.py /path/to/other/project --output graph-data.json
2. 웹앱 실행
cd webapp
npm install
npm run dev
# → http://localhost:5173
3. 빌드 후 배포
npm run build
# dist/ 폴더에 정적 파일 생성
npx serve dist
기능
- 노드 그래프: D3.js force-directed 레이아웃
- 드래그 & 줌: 노드 위치 조정, 확대/축소
- 노드 타입: 🤖 Agent (파란색), 🔧 Skill (초록색)
- 연결 타입: uses (실선), depends (점선)
- 검색: 노드 이름/설명으로 필터링
- 상세 패널: 노드 클릭 시 메타데이터 표시
범용성
이 스킬은 다른 Claude Code 프로젝트에서도 사용할 수 있습니다:
- 스킬 폴더를 복사:
cp -r agent-skill-visualizer /new/project/.claude/skills/ - 데이터 생성:
python scripts/scan_agents_skills.py /new/project - 웹앱 실행:
cd webapp && npm run dev
출력 데이터 형식
{
"nodes": [
{ "id": "agent:name", "type": "agent", "name": "...", ... },
{ "id": "skill:name", "type": "skill", "name": "...", ... }
],
"edges": [
{ "source": "agent:x", "target": "skill:y", "type": "uses" }
],
"metadata": {
"projectName": "...",
"agentCount": 5,
"skillCount": 6
}
}
What ships with it
25 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.
- README.md 3.0 KB
- scripts/scan_agents_skills.py 13 KB runs code
- scripts/stream_server.py 11 KB runs code
- webapp/index.html 673 B
- webapp/package-lock.json 113 KB
- webapp/package.json 749 B
- webapp/postcss.config.js 80 B runs code
- webapp/src/App.tsx 23 KB
- webapp/src/components/BezierEdge.tsx 2.4 KB
- webapp/src/components/CallStack.tsx 2.2 KB
- webapp/src/components/CommandBuilder.tsx 6.8 KB
- webapp/src/components/DetailPanel.tsx 7.3 KB
- webapp/src/components/Legend.tsx 4.3 KB
- webapp/src/components/NodeCard.tsx 5.8 KB
- webapp/src/components/SearchBar.tsx 1.4 KB
- webapp/src/hooks/code-visualizer-claude-v2.9-beta.3.zip 1365 KB
- webapp/src/hooks/useActivityStream.ts 2.7 KB runs code
- webapp/src/hooks/useGraphData.ts 1.3 KB runs code
- webapp/src/main.tsx 237 B
- webapp/src/styles/index.css 2.7 KB
- webapp/src/types/graph.ts 1.6 KB runs code
- webapp/tailwind.config.js 434 B runs code
- webapp/tsconfig.json 562 B
- webapp/tsconfig.node.json 213 B
- webapp/vite.config.ts 254 B runs code
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.
- 2mo ago First seen · 83 lines · 54 tokens per session scan A 159eeec8dddc
agent-skill-visualizer is a skill published in the GitHub repository nainsharma01/claude-code-visualizer (5 stars, last pushed 18d ago), licensed MIT. It adds 54 tokens to every session and 644 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
email-sequence
When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle…
emerging-techniques-long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases…
prompt-engineering-guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
content-research-writer
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.