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.
git 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/commands/attendantlion8/provider-fallback-plugin/provider-analytics)<a href="https://agentmods.dev/commands/attendantlion8/provider-fallback-plugin/provider-analytics"><img src="https://agentmods.dev/badge/commands/attendantlion8/provider-fallback-plugin/provider-analytics/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.
<a href="https://agentmods.dev/commands/attendantlion8/provider-fallback-plugin/provider-analytics"><img src="https://agentmods.dev/badge/commands/attendantlion8/provider-fallback-plugin/provider-analytics.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00011 | $0.00605 |
| Opus 5.5 | $0.00004 | $0.00242 |
| Sonnet 5.5 | $0.00002 | $0.00121 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
provider-analytics 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 1mo 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.
What it actually says
Provider Analytics Command
Display comprehensive usage analytics for AI providers.
Usage
/provider-analytics [period] [--view=<type>]
Arguments
period: Time period (1h, 24h, 7d, 30d, all)--view: View type (summary, providers, models, costs, errors)
Instructions
When this command is invoked:
-
Load Analytics Module
- Import from
{{PLUGIN_ROOT}}/lib/analytics.js - Call
getSummary(period)for the requested period
- Import from
-
Format Output Based on View
summary (default):
📊 Provider Analytics - {period} ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Total Requests: {count} Success Rate: {rate}% Avg Latency: {ms}ms Tokens Used: {tokens} Est. Cost: ${cost} Fallbacks: {count} 🏆 Top Providers: 1. {provider} - {requests} req ({successRate}%) 2. ... 🤖 Top Models: 1. {model} - {requests} requests 2. ...providers:
- Show
getProviderComparison()results - Include success rate, latency, cost per provider
models:
- Show model-level statistics
- Group by family
costs:
- Show
getCostAnalysis('provider')results - Include cost per request breakdown
errors:
- Show recent errors from analytics
- Include timestamps and error messages
- Show
-
Handle No Data
- If no analytics data exists, show friendly message
- Suggest running some requests first
Examples
/provider-analytics # Last 24h summary
/provider-analytics 7d # Last 7 days
/provider-analytics --view=costs # Cost breakdown
/provider-analytics 30d --view=providers # Provider comparison
Implementation Notes
Use the analytics module functions:
getSummary(period)- Overview statsgetProviderComparison()- Provider performancegetCostAnalysis(groupBy)- Cost breakdown
Data is stored in .data/analytics.json within the plugin directory.
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.
- 1mo ago First seen · 98 lines · 11 tokens per session scan A 79ed751d7b41
provider-analytics is a command published in the GitHub repository AttendantLion8/provider-fallback-plugin (2 stars, last pushed 9mo ago), licensed MIT. It adds 11 tokens to every session and 605 once invoked, about $0.0000 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.
Other commands, from other repositories
security-scan
Run AgentShield against agent, hook, MCP, permission, and secret surfaces.
learn
Extract patterns and learnings from current session.
quality-gate
Run the ECC quality pipeline on demand for a file or project scope.
export-closedloop-learnings
Exports pending ClosedLoop learnings to global location with deduplication.
doctor
Diagnose a broken llm-router setup.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.