Plano is a proxy server and data plane that handles shared infrastructure for applications built with AI agents, including agent routing, orchestration, model selection, traces, metrics, and guardrails. Developers use it to connect agents and language models to production applications without embedding this middleware in each application. The catalogue entries provide skills and instructions for operating or developing with Plano.
Borrowing it
Nothing to install: this file belongs to katanemo/plano. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/katanemo/plano/main/.claude/skills/new-provider/SKILL.mdgit clone --depth 1 https://github.com/katanemo/planoWrote 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/skills/katanemo/plano/new-provider)<a href="https://agentmods.dev/skills/katanemo/plano/new-provider"><img src="https://agentmods.dev/badge/skills/katanemo/plano/new-provider/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/skills/katanemo/plano/new-provider"><img src="https://agentmods.dev/badge/skills/katanemo/plano/new-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.00223 |
| Opus 5.5 | $0.00009 | $0.00089 |
| Sonnet 5.5 | $0.00005 | $0.00045 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
new-provider 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 2mo 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
Add a new LLM provider to hermesllm. The user will provide the provider name as $ARGUMENTS.
- Add a new variant to
ProviderIdenum incrates/hermesllm/src/providers/id.rs - Implement string parsing in the
TryFrom<&str>impl for the new provider - If the provider uses a non-OpenAI API format, create request/response types in
crates/hermesllm/src/apis/ - Add variant to
ProviderRequestTypeandProviderResponseTypeenums and update all match arms - Add model list to
crates/hermesllm/src/providers/provider_models.yaml - Update
SupportedUpstreamAPIsmapping if needed
After making changes, run cd crates && cargo test --lib to verify everything compiles and tests pass.
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.
- 2mo ago First seen · 18 lines · 23 tokens per session scan A 6e2297413c91
new-provider is a skill published in the GitHub repository katanemo/plano (7,100 stars, last pushed 5d ago), licensed Apache-2.0. It adds 23 tokens to every session and 223 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
neuron-agent
Create, configure, and extend Neuron AI agents in PHP using providers, tools, chat history, memory, and custom workflow nodes. Use for Neuron Agent implementation, configuration, conversation lifecycle, and input/output extensions.
guardrails-developer-create-guardrails
Helps developers create a NeMo Guardrails configuration for an LLM application. Use when users want to build, scaffold, configure, test, or iterate on input, output, retrieval, dialog, execution, Colang, or catalog-based guardrails. Trigger keywords - create guardrails, build guardrails, scaffold config, write rails…
neuron-laravel-integration
Integrate Neuron AI agents into a Laravel 13 app the framework-native way — setup checklist (App\Neuron layout, config/services.php keys, one migration, NeuronServiceProvider, bootstrap/app.php exception mapping, neuron:evaluate), container-built agents bound per thread with for(), thread authorization, JSON and…
neuron-symfony-integration
Integrate Neuron AI agents into a Symfony 8 app, from packages, env keys, a Doctrine migration for the Neuron tables and services.yaml wiring to a shared agent bound per request with for(), a thread voter, JSON and AG-UI (CopilotKit) or useChat streaming with StreamedResponse, reload with pending approvals, Messenger…
neuron-evaluation
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
neuron-streaming
Stream Neuron AI agent and workflow output to a consumer — iterating native chunks, yielding portable progress events from nodes, attaching a stream adapter for a UI protocol (Vercel AI SDK, AG-UI, SSE) or for Neuron's native vocabulary, and pushing output through a streaming channel when the consumer is not the HTTP…