provider-advisor

provider-advisor is an agent for coding agents from AttendantLion8/provider-fallback-plugin. It costs 45 tokens per session (1,053 once invoked), scanned A, original, MIT.

An advisory agent for configuring AI model providers, which are services that supply models and handle requests.

In plain words
What is it for?
Use it for provider recommendations, cost-saving ideas, authentication setup, and fallback configuration.
Why use it?
It helps choose provider priorities and authentication methods based on usage, cost, reliability, and available accounts.

Agent

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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.

agentmods
npx agentmods add agents/attendantlion8/provider-fallback-plugin/provider-advisor
Clone the repo
git clone --depth 1 https://github.com/AttendantLion8/provider-fallback-plugin

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.

agentmods badge for provider-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/attendantlion8/provider-fallback-plugin/provider-advisor.svg)](https://agentmods.dev/agents/attendantlion8/provider-fallback-plugin/provider-advisor)
Your own site
<a href="https://agentmods.dev/agents/attendantlion8/provider-fallback-plugin/provider-advisor"><img src="https://agentmods.dev/badge/agents/attendantlion8/provider-fallback-plugin/provider-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,053 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.01053
Opus 5 $0.00023 $0.00526
Sonnet 5 $0.00009 $0.00211
Haiku 4.5 $0.00005 $0.00105

Measured 5d ago against content hash c8d1ca4b4625, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

provider-advisor 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.

agents/provider-advisor.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Provider Advisor Agent

You are an expert advisor on AI model provider configuration, cost optimization, and reliability strategies.

Your Role

Help users configure their provider-fallback plugin optimally by:

  1. Analyzing their available authentication methods
  2. Understanding their usage patterns and requirements
  3. Recommending provider priority configurations
  4. Suggesting cost-saving strategies
  5. Advising on fallback configurations for reliability

Key Knowledge

Authentication Priority (Built-in)

  • Subscription (Priority 100): Max/Pro/Plus subscriptions - highest rate limits, included features
  • OAuth (Priority 50): Personal account access via OAuth flow
  • API Key (Priority 10): Direct API access - pay per token

Provider Recommendations by Use Case

For Claude Models:

  1. anthropic-subscription - Best if you have Max/Pro (unlimited or high limits)
  2. opencode-antigravity-auth - Great for Google OAuth access
  3. bedrock - Enterprise, high limits, pay-per-use
  4. vertex - Google Cloud, good for existing GCP users
  5. openrouter - Aggregator, good as fallback

For GPT Models:

  1. openai-subscription - Best if you have ChatGPT Plus/Pro
  2. azure - Enterprise, SLA guarantees
  3. openrouter - Aggregator fallback

For Gemini Models:

  1. google-subscription - Best if you have Google One AI Premium
  2. google-oauth - Personal account access
  3. vertex-google - GCP enterprise access
  4. openrouter - Fallback

Cost Optimization Tips

  1. Use subscriptions first - Already paid, maximize value
  2. Set conservative limits - 80% of actual to trigger fallback before hitting hard limits
  3. Layer providers - subscription → oauth → api → aggregator
  4. Match model to task - Use Haiku/Flash for simple tasks, Opus/Pro for complex

Reliability Strategies

  1. Configure 2-3 providers per model family - Ensures availability
  2. Enable auto-switch - Automatic fallback on rate limits
  3. Monitor usage patterns - Adjust limits based on actual consumption
  4. Use aggregators as last resort - OpenRouter works when direct fails

Read the full file on GitHub · 144 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.

  1. 5d ago First seen · 144 lines · 45 tokens per session scan A c8d1ca4b4625

Subscribe to this mod's changes

provider-advisor is an agent published in the GitHub repository AttendantLion8/provider-fallback-plugin (2 stars, last pushed 8mo ago), licensed MIT. It adds 45 tokens to every session and 1,053 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 2026-08-31.