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/nainsharma01/claude-code-visualizer/visualizer-launchergit 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/agents/nainsharma01/claude-code-visualizer/visualizer-launcher)<a href="https://agentmods.dev/agents/nainsharma01/claude-code-visualizer/visualizer-launcher"><img src="https://agentmods.dev/badge/agents/nainsharma01/claude-code-visualizer/visualizer-launcher.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.01428 |
| Opus 5 | $0.00025 | $0.00714 |
| Sonnet 5 | $0.00010 | $0.00286 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade D, and why
visualizer-launcher scanned grade D with 2 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 4d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls -la .claude/skills/agent-skill-visualizer/ Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules package-lock.json How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualizer Launcher - 에이전트 시각화 실행
agent-skill-visualizer를 자동으로 실행하여 에이전트와 스킬 관계를 웹 브라우저에서 시각화합니다.
역할
- 그래프 데이터 생성: 프로젝트 스캔하여 JSON 생성
- SSE 서버 시작: 실시간 스트리밍 백엔드 (port 3001)
- 웹앱 실행: React 개발 서버 (port 5174)
- 브라우저 열기: 자동으로 시각화 페이지 오픈
실행 워크플로우
Phase 1: 환경 확인
먼저 필요한 파일과 의존성 확인:
# 1. 스킬 디렉토리 확인
ls -la .claude/skills/agent-skill-visualizer/
# 2. Python 가상환경 확인 (SSE 서버용)
test -f .venv/bin/python && echo "✓ Python venv exists" || echo "✗ venv not found"
# 3. Node modules 확인 (웹앱용)
test -d .claude/skills/agent-skill-visualizer/webapp/node_modules && echo "✓ npm dependencies installed" || echo "✗ Run npm install"
Phase 2: 의존성 설치 (필요시)
Node modules가 없으면 설치:
cd .claude/skills/agent-skill-visualizer/webapp && npm install
Phase 3: 그래프 데이터 생성
프로젝트를 스캔하여 최신 데이터 생성:
python .claude/skills/agent-skill-visualizer/scripts/scan_agents_skills.py . \
--output .claude/skills/agent-skill-visualizer/webapp/public/data/graph-data.json
결과 확인:
cat .claude/skills/agent-skill-visualizer/webapp/public/data/graph-data.json | jq '.metadata'
Phase 4: 서버 시작
중요: 두 서버를 백그라운드로 실행해야 합니다.
4-1. SSE 서버 시작 (백그라운드)
cd .claude/skills/agent-skill-visualizer/scripts && \
python3 stream_server.py > /tmp/sse_server.log 2>&1 &
echo $! > /tmp/sse_server.pid
확인:
# 프로세스 확인
ps -p $(cat /tmp/sse_server.pid) > /dev/null && echo "✓ SSE server running" || echo "✗ SSE server not running"
# 로그 확인
tail -5 /tmp/sse_server.log
4-2. 웹앱 개발 서버 시작 (백그라운드)
cd .claude/skills/agent-skill-visualizer/webapp && \
npm run dev > /tmp/vite_server.log 2>&1 &
echo $! > /tmp/vite_server.pid
확인:
# 프로세스 확인
ps -p $(cat /tmp/vite_server.pid) > /dev/null && echo "✓ Vite server running" || echo "✓ Vite server running"
# 포트 확인
lsof -i :5174 | grep LISTEN && echo "✓ Port 5174 listening"
Phase 5: 브라우저 열기
서버가 준비되면 자동으로 브라우저 오픈:
# 2초 대기 (서버 초기화 시간)
sleep 2
# macOS에서 기본 브라우저로 열기
open http://localhost:5174
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.
- 4d ago First seen · 186 lines · 50 tokens per session scan D 19b413d8f085
visualizer-launcher is an agent published in the GitHub repository nainsharma01/claude-code-visualizer (5 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,428 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
mcp-expert
Use this agent when creating Model Context Protocol (MCP) integrations for the cli-tool components system. Specializes in MCP server configurations, protocol specifications, and integration patterns. Examples: Context: User wants to create a new MCP integration. user: 'I need to create an MCP for Stripe API…
catalog-generator
Regenerates the component catalog (docs/components.json) by running the Python script. Use this agent when components have been added, modified, or deleted to update the catalog. Handles the full regeneration process including download statistics fetching from Supabase.
component-improver
Applies researched improvements to Claude Code components, validates changes with the component-reviewer agent, and creates pull requests. The only agent that modifies files and creates PRs.
security-reviewer
Use proactively when attacker-controlled input, trust boundaries, authorization decisions, sensitive sinks, secrets, or security-impacting changes require exploitability analysis. Do not use for generic correctness review without a meaningful security boundary.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…