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.
/plugin marketplace add aegntic/cldcdenpx agentmods add plugins/aegntic/cldcde/remote-visual-debuggergit clone --depth 1 https://github.com/aegntic/cldcdeGrade A, and why
remote-visual-debugger 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 2d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "remote-visual-debugger",
"version": "1.0.0",
"description": "Comprehensive remote visual debugging toolkit for browser applications, React development, and web performance analysis by ae.ltd",
"author": {
"name": "ae.ltd",
"email": "[email protected]"
},
"maintainer": {
"name": "ae.ltd",
"email": "[email protected]"
},
"repository": "https://github.com/aegntic/remote-visual-debugger",
"website": "https://cldcde.cc/plugins/remote-visual-debugger",
"license": "MIT",
"keywords": [
"remote-debugging",
"visual-debugger",
"react-development",
"browser-inspector",
"performance-analysis",
"web-debugging",
"developer-tools",
"frontend-optimization",
"claude-code",
"ae-ltd"
],
"category": "developer-tools",
"type": "ai-instruction",
"claude_code_version": ">=1.0.0",
"tags": ["production-ready", "developer-tools", "debugging", "performance"],
"rating": 5.0,
"downloads": 0,
"created_at": "2025-11-19T08:00:00Z",
"updated_at": "2025-11-19T08:00:00Z",
"dependencies": {
"node": ">=18.0.0",
"typescript": ">=5.0.0",
"puppeteer": "latest",
"chrome-remote-interface": "latest"
},
"permissions": [
"network_access",
"file_system_read",
"file_system_write"
],
"security": {
"credential_storage": "encrypted",
"api_key_required": false,
"https_only": false
},
"features": [
"Remote browser debugging with advanced visual inspection capabilities",
"React component analysis with props, state, and performance profiling",
"Real-time performance monitoring with Core Web Vitals tracking",
"Comprehensive error tracking with stack trace analysis and resolution suggestions",
"Visual DOM inspection with interactive element highlighting and modification",
"Network request monitoring with detailed timing analysis and optimization recommendations",
"Cross-browser compatibility testing with automated screenshot compariWhat 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.
- 2d ago First seen · 118 lines scan A bf0219c7d583
remote-visual-debugger is a plugin published in the GitHub repository aegntic/cldcde (11 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
titen-memory
Use Titen's evidence-grounded collaborative memory. The local stdio mode needs no configuration; a served Titen endpoint is the alternative for a shared store.
titen
Evidence-grounded collaborative memory for coding agents.
zangia
Live zangia.mn job search, ATS resume matching, and salary benchmarks for Claude Code.
zangia
zangia.mn live job search, ATS CV matching, and salary analysis MCP tools.
cyanheads-mcp-server
Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets.
scriptwriter
Decentralised scriptwriter recognition + co-brainstorm — REAL RECOGNISE REAL cascades, signed writers' rooms, chaos cards, and a 15-tool MCP surface. Drop into /.claude/ to give Claude Code six slash commands and three skills.