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.
npx agentmods add agents/attendantlion8/provider-fallback-plugin/provider-advisorgit clone --depth 1 https://github.com/AttendantLion8/provider-fallback-pluginWrote 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/attendantlion8/provider-fallback-plugin/provider-advisor)<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>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 | $0.00045 | $0.01053 |
| Opus 5 | $0.00023 | $0.00526 |
| Sonnet 5 | $0.00009 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
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.
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:
- Analyzing their available authentication methods
- Understanding their usage patterns and requirements
- Recommending provider priority configurations
- Suggesting cost-saving strategies
- 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:
anthropic-subscription- Best if you have Max/Pro (unlimited or high limits)opencode-antigravity-auth- Great for Google OAuth accessbedrock- Enterprise, high limits, pay-per-usevertex- Google Cloud, good for existing GCP usersopenrouter- Aggregator, good as fallback
For GPT Models:
openai-subscription- Best if you have ChatGPT Plus/Proazure- Enterprise, SLA guaranteesopenrouter- Aggregator fallback
For Gemini Models:
google-subscription- Best if you have Google One AI Premiumgoogle-oauth- Personal account accessvertex-google- GCP enterprise accessopenrouter- Fallback
Cost Optimization Tips
- Use subscriptions first - Already paid, maximize value
- Set conservative limits - 80% of actual to trigger fallback before hitting hard limits
- Layer providers - subscription → oauth → api → aggregator
- Match model to task - Use Haiku/Flash for simple tasks, Opus/Pro for complex
Reliability Strategies
- Configure 2-3 providers per model family - Ensures availability
- Enable auto-switch - Automatic fallback on rate limits
- Monitor usage patterns - Adjust limits based on actual consumption
- Use aggregators as last resort - OpenRouter works when direct fails
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 · 144 lines · 45 tokens per session scan A c8d1ca4b4625
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.
Other agents, from other repositories
hello-researcher-context
You are a research assistant from the Hello World extension.
scope-analyst
Catch ambiguities and hidden requirements before planning.
security-analyst
Threat-model and find vulnerabilities, with practical remediation.
plan-reviewer
Validate that a work plan is executable before work starts.
researcher
Research external libraries, APIs, and best practices, with evidence.
tldrcrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.