What is llm-providers?

A reference for configuring the large language model, or LLM, that powers a Cognigy agent. It covers supported providers, model names, connection types, credentials, and compatible services.

Use it when selecting or creating an LLM for an AI agent, knowledge search, answer extraction, or a custom OpenAI-compatible service. It supports hosted and self-hosted configurations described in the input.

It prevents choosing an invalid provider, model string, or connection setup. It also clarifies the difference between chat models and embedding models used to index knowledge.

llm-providers — Skill for Claude Code by Cognigy/cognigy-plugin

Install

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.

Any agent

npx skills add Cognigy/cognigy-plugin --skill llm-providers

Clone the repo

git clone --depth 1 https://github.com/Cognigy/cognigy-plugin

Made for: Claude Code.

Or install cognigy, the plugin that ships this one along with the rest of its 16 skills, 2 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/llm-providers/github.svg)](https://agentmods.dev/skills/cognigy/cognigy-plugin/llm-providers)

Your own site

<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/llm-providers"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/llm-providers/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/llm-providers"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/llm-providers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,642 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 78
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00087	$0.02642
Opus 5.5	$0.00035	$0.01057
Sonnet 5.5	$0.00017	$0.00528
Haiku 4.5	$0.00009	$0.00264

Measured 14d ago against content hash 3e4337e08baf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

llm-providers 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 14d 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.

plugin/skills/llm-providers/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Provider Reference

When to call setup_llm

setup_llm creates a brand-new LLM resource and is a last resort. Before calling it, all of these must be true:

You listed all projects (list_resources { resourceType: "project" }).
You checked every other project for existing LLMs (list_resources { resourceType: "llm_model", projectId }).
Where another project has a reusable LLM with a non-empty connectionId, you attempted to transfer it together with its connection via manage_packages (see the package-management skill).
You are proceeding only because reuse is unavailable, the transfer failed, or the user explicitly asked for a brand-new LLM.

If any step is missing, stop and do it first. To list existing LLMs use list_resources { resourceType: "llm_model", projectId }; to delete one use delete_resource { resourceType: "llm_model", id }.

setup_llm parameters

provider	modelType examples	Connection type	Notes
openAI	gpt-4o, gpt-4o-mini, gpt-4.1, gpt-4.1-mini	OpenAIProvider	Requires apiKey (sk-...)
anthropic	claude-sonnet-4-0, claude-opus-4-0, claude-3-opus-20240229	AnthropicProvider	Requires apiKey
azureOpenAI	gpt-4o (deployment name)	AzureOpenAIProviderV2	Requires apiKey, may need connectionId with deployment config
google	gemini-2.0-flash, gemini-1.5-pro	GoogleVertexAIProvider	Requires apiKey
mistral	mistral-small-2503, mistral-medium-latest	MistralProvider	Requires apiKey
openAICompatible	custom-model, custom-embedding-model	OpenAICompatibleProvider	Requires apiKey + baseCustomUrl + customModel (see below)
awsBedrock	amazon.nova-pro-v1:0, custom-model	AwsBedrockProvider / AwsBedrockProviderIamRole	Requires region + accessKeyId/secretAccessKey or roleArn (see below)

Read the full file on GitHub · 145 lines

Changes

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.

14d ago Changed · +19 lines 3e4337e08baf
1mo ago Changed · +36 lines · +9 tokens per session 6e39c4059e55
2mo ago First seen · 90 lines · 78 tokens per session scan A d365cbf9ca81

Subscribe to this mod's changes

llm-providers is a skill published in the GitHub repository Cognigy/cognigy-plugin (18 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 2,642 once invoked, about $0.0003 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.

Building agents

llm-providers next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
llm-providersCognigy/cognigy-plugin	Skill	18	yesterday	MIT	A	87	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code