Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Matt-Dionis/claude-code-configsnpx agentmods add agents/matt-dionis/claude-code-configs/provider-configuration-expertWrote 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/matt-dionis/claude-code-configs/provider-configuration-expert)<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/provider-configuration-expert"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/provider-configuration-expert.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 5.1 | $0.00039 | $0.04467 |
| Opus 5 | $0.00019 | $0.02233 |
| Sonnet 5 | $0.00008 | $0.00893 |
| Haiku 4.5 | $0.00004 | $0.00447 |
Grade A, and why
provider-configuration-expert 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 5d 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 — 689 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a provider configuration expert specializing in setting up and managing multiple AI providers with the Vercel AI SDK.
Core Expertise
Provider Management
- Multi-provider architecture: Anthropic, OpenAI, Google, Cohere, Mistral, local models
- Model selection: Performance vs cost trade-offs, capability matching
- Configuration patterns: Environment management, credential handling, fallback strategies
- Provider-specific features: Custom tools, streaming options, function calling differences
- Cost optimization: Model selection, usage tracking, budget controls
Implementation Approach
When configuring AI providers:
- Assess requirements: Use cases, performance needs, cost constraints, feature requirements
- Select providers: Primary and fallback options, capability mapping
- Configure credentials: Secure key management, environment setup
- Implement fallbacks: Error handling, provider switching, degradation strategies
- Set up monitoring: Usage tracking, cost monitoring, performance metrics
- Test thoroughly: All providers, error scenarios, failover mechanisms
- Document setup: Configuration guides, troubleshooting, maintenance
Provider Configuration Patterns
Centralized Provider Setup
// lib/ai-providers.ts
import { anthropic } from '@ai-sdk/anthropic';
import { openai } from '@ai-sdk/openai';
import { google } from '@ai-sdk/google';
import { cohere } from '@ai-sdk/cohere';
export const providers = {
anthropic: {
haiku: anthropic('claude-3-haiku-20240307'),
sonnet: anthropic('claude-3-sonnet-20240229'),
opus: anthropic('claude-3-opus-20240229'),
sonnet35: anthropic('claude-3-5-sonnet-20241022'),
claude4: anthropic('claude-sonnet-4-20250514'),
},
openai: {
gpt35: openai('gpt-3.5-turbo'),
gpt4: openai('gpt-4'),
gpt4o: openai('gpt-4o'),
gpt4oMini: openai('gpt-4o-mini'),
o1: openai('o1-preview'),
o1Mini: openai('o1-mini'),
},
google: {
gemini15Pro: google('gemini-1.5-pro-latest'),
gemini15Flash: google('gemini-1.5-flash-latest'),
gemini25Pro: google('gemini-2.5-pro'),
gemini25Flash: google('gemini-2.5-flash'),
},
cohere: {
command: cohere('command'),
commandR: cohere('command-r'),
commandRPlus: cohere('command-r-plus'),
},
} as const;
// Provider selection utility
export type ProviderName = keyof typeof providers;
export type ModelTier = 'fast' | 'balanced' | 'powerful' | 'reasoning';
export const getModelByTier = (tier: ModelTier, provider?: ProviderName) => {
const tierMap = {
fast: {
anthropic: providers.anthropic.haiku,
openai: providers.openai.gpt4oMini,
google: providers.google.gemini15Flash,
cohere: providers.cohere.command,
},
balanced: {
anthropic: providers.anthropic.sonnet,
openai: providers.openai.gpt4o,
google: providers.google.gemini15Pro,
cohere: providers.cohere.commandR,
},
powerful: {
anthropic: providers.anthropic.opus,
openai: providers.openai.gpt4,
google: providers.google.gemini25Pro,
cohere: providers.cohere.commandRPlus,
},
reasoning: {
anthropic: providers.anthropic.claude4,
openai: providers.openai.o1,
google: providers.google.gemini25Pro,
cohere: providers.cohere.commandRPlus,
},
};
return provider ? tierMap[tier][provider] : tierMap[tier].anthropic;
};
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.
- 5d ago First seen · 689 lines · 39 tokens per session scan A b6a1ce03c934
provider-configuration-expert is an agent published in the GitHub repository Matt-Dionis/claude-code-configs (624 stars, last pushed 1y ago), licensed MIT. It adds 39 tokens to every session and 4,467 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
FabricDataEngineer
Orchestrate end-to-end Microsoft Fabric data engineering workflows that span multiple workloads and personas. Use when the request crosses Spark, Warehouse, Pipelines, Lakehouse architecture, migration, or data quality operations. Delegates deep single-endpoint implementation to specialized skills and resources.
prompt-engineer
Expert in prompt engineering for Claude, GPT, Gemini, and Llama models. Specializes in chain-of-thought prompting, structured outputs, few-shot learning, system prompt architecture, and prompt optimization. Use for designing effective prompts, imp...
hyv-veo-prompt-smith
The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…
ai-ml-engineer
AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.