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 Cognigy/cognigy-pluginnpx agentmods add plugins/cognigy/cognigy-plugin/plugingit clone --depth 1 https://github.com/Cognigy/cognigy-pluginGrade A, and why
cognigy 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 yesterday.
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
{
"name": "cognigy",
"version": "1.14.0",
"description": "NiCE Cognigy Plugin — create, test, and manage AI Agents on the NiCE Cognigy platform",
"author": {
"name": "Cognigy",
"url": "https://www.cognigy.com"
},
"homepage": "https://www.cognigy.com",
"repository": "https://github.com/Cognigy/cognigy-plugin",
"license": "MIT",
"keywords": ["cognigy", "ai-agents", "conversational-ai", "mcp", "llm"],
"userConfig": {
"cognigy_api_base_url": {
"type": "string",
"title": "Cognigy API base URL",
"description": "Your Cognigy instance API URL. Use https://api-trial.cognigy.ai if you are on the trial.",
"default": "https://api-trial.cognigy.ai",
"required": true
},
"cognigy_api_key": {
"type": "string",
"title": "Cognigy API key",
"description": "Find it in Cognigy.AI → User Menu → My Profile → API Keys.",
"sensitive": true,
"required": true
}
},
"mcpServers": {
"platform": {
"command": "npx",
"args": [
"-y",
"-p",
"cognigy-engine@npm:@cognigy/[email protected]",
"cognigy-mcp"
],
"env": {
"COGNIGY_API_BASE_URL": "${user_config.cognigy_api_base_url}",
"COGNIGY_API_KEY": "${user_config.cognigy_api_key}"
}
},
"docs": {
"type": "http",
"url": "https://docs.cognigy.com/mcp"
}
}
}
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.
- yesterday First seen · 49 lines scan A f925d64fd77d
cognigy is a plugin published in the GitHub repository Cognigy/cognigy-plugin (8 stars, last pushed 4d 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 2026-08-31.
Other plugins, from other repositories
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
nextjs
Official Claude Code plugin marketplace for Next.js, serving the skills that ship in the vercel/next.js repository.
claude-plugins-official
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins
Plugin marketplace listing 97 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
ecc
Plugin marketplace listing 1 plugin: ecc.
ecc
Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.