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 commands/attendantlion8/provider-fallback-plugin/provider-modelsgit 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-models)<a href="https://agentmods.dev/commands/attendantlion8/provider-fallback-plugin/provider-models"><img src="https://agentmods.dev/badge/commands/attendantlion8/provider-fallback-plugin/provider-models.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 | $0.00012 | $0.01747 |
| Opus 5 | $0.00006 | $0.00873 |
| Sonnet 5 | $0.00002 | $0.00349 |
| Haiku 4.5 | $0.00001 | $0.00175 |
Grade A, and why
provider-models 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Registry & Provider Mappings
View all supported models and their provider-specific identifiers. Models use a canonical name that maps to provider-specific IDs.
Usage
List All Models
/provider-models list
/provider-models list --filter claude
/provider-models list --filter gpt
/provider-models list --filter gemini
Get Model Info
/provider-models info claude-sonnet-4
/provider-models info gpt-4o
/provider-models info gemini-2.5-pro
Shows capabilities, context window, and all provider mappings.
Filter by Capability
/provider-models capability vision
/provider-models capability reasoning
/provider-models capability code
Get Providers for Model
/provider-models providers claude-sonnet-4
Model Families
Claude (Anthropic)
| Canonical Name | Context | Capabilities |
|---|---|---|
claude-4-opus |
200K | text, vision, code, reasoning |
claude-sonnet-4 |
200K | text, vision, code, reasoning |
claude-3.5-sonnet |
200K | text, vision, code |
claude-3.5-haiku |
200K | text, vision, code |
claude-3-opus |
200K | text, vision, code, reasoning |
GPT (OpenAI)
| Canonical Name | Context | Capabilities |
|---|---|---|
gpt-4.1 |
1M | text, vision, code, reasoning |
gpt-4.1-mini |
1M | text, vision, code |
gpt-4o |
128K | text, vision, code, audio |
gpt-4o-mini |
128K | text, vision, code |
o1 |
200K | text, reasoning, code |
o3-mini |
200K | text, reasoning, code |
Gemini (Google)
| Canonical Name | Context | Capabilities |
|---|---|---|
gemini-2.5-pro |
1M | text, vision, code, reasoning, audio |
gemini-2.5-flash |
1M | text, vision, code, reasoning |
gemini-2.0-flash |
1M | text, vision, code |
gemini-1.5-pro |
2M | text, vision, code |
Grok (xAI)
| Canonical Name | Context | Capabilities |
|---|---|---|
grok-3 |
131K | text, vision, code, reasoning |
grok-3-mini |
131K | text, code, reasoning |
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 · 196 lines · 12 tokens per session scan A e2ba07c262a8
provider-models is a command published in the GitHub repository AttendantLion8/provider-fallback-plugin (2 stars, last pushed 8mo ago), licensed MIT. It adds 12 tokens to every session and 1,747 once invoked, about $0.0001 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 commands, from other repositories
package-assistant
Convert an OfficeCLI skill into a fully wired AionUi assistant preset, or update an existing one.
ask
Query multiple AI agents (Gemini, OpenAI, Grok, Perplexity, Kimi, any model OpenRouter routes to, and a local ollama model) for diverse perspectives on architecture decisions, technology choices, debugging dead-ends, and security tradeoffs. Use this whenever the user names the council directly, whatever the topic …
result
Fetch, list, or cancel background council jobs started with --async.
grok-files
List, prune, or gc Grok (xAI) uploaded files. Cleanup for bridge-owned uploads only.
help
Show how to use deliberation here - what each command does, when to reach for it, and real prompts you can paste right now. Read-only.
setup
Configure deliberation with Codex (GPT), Gemini, Grok, and OpenRouter MCP servers.