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 skills add rhtevan/agentfs --skill skupper-model-providergit clone --depth 1 https://github.com/rhtevan/agentfsWrote 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/rhtevan/agentfs/skupper-model-provider)<a href="https://agentmods.dev/skills/rhtevan/agentfs/skupper-model-provider"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/skupper-model-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/rhtevan/agentfs/skupper-model-provider"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/skupper-model-provider.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 | $0.00066 | $0.02556 |
| Opus 5.5 | $0.00026 | $0.01022 |
| Sonnet 5.5 | $0.00013 | $0.00511 |
| Haiku 4.5 | $0.00007 | $0.00256 |
Grade A, and why
skupper-model-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 today.
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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skupper Model Provider
Expose remote GPU-hosted LLM models to localhost via a Skupper V2
Virtual Application Network. Separates one-time infrastructure setup
from daily start/stop operations. Manages a 4-site VAN across podman
and Kubernetes (CRC) platforms with automated model container
orchestration via hosted-model-ctl.
For architecture details, topology, and routing tables, see references/architecture.md.
For agent orchestration rules (signal routing, scoping, partial availability, startup/shutdown order), see references/agent-orchestration.md.
Script Separation
| Script | Purpose | When to use |
|---|---|---|
setup.sh |
One-time infrastructure | First time, or after teardown |
setup.sh --check |
Precheck only (topology + validation) | Before setup, or to inspect topology |
teardown.sh |
Remove infrastructure | Decommissioning |
upgrade.sh |
Align podman versions to CRC baseline | After CRC operator upgrade |
up.sh [SITE] |
Start VAN (controllers + routers) | Daily use |
down.sh [SITE] |
Stop VAN (routers + controllers) | End of day |
status.sh |
Full health check | Troubleshooting |
test-model.sh SITE_OR_PROFILE |
E2E connectivity test | Verification |
Operations
Precheck / Show Topology
bash ~/.agents/skills/skupper-model-provider/scripts/setup.sh --check
First-Time Setup
cp ~/.agents/skills/skupper-model-provider/topology.env.example \
~/.agents/skills/skupper-model-provider/topology.env
# Edit topology.env with actual IPs, hostnames, SANs
bash ~/.agents/skills/skupper-model-provider/scripts/setup.sh
Upgrade (align podman sites to CRC baseline)
bash ~/.agents/skills/skupper-model-provider/scripts/upgrade.sh
Start / Stop VAN
bash ~/.agents/skills/skupper-model-provider/scripts/up.sh # all sites
bash ~/.agents/skills/skupper-model-provider/scripts/up.sh rhel-ai # specific provider
bash ~/.agents/skills/skupper-model-provider/scripts/up.sh crc # CRC site only
bash ~/.agents/skills/skupper-model-provider/scripts/down.sh # all sites
bash ~/.agents/skills/skupper-model-provider/scripts/down.sh rhel-ai # specific provider
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- ACTION-PLAN-v9.md 9.6 KB
- CHANGELOG.md 16 KB
- docs/operations.lifecycle.html 624 KB
- docs/operations.lifecycle.json 4.0 KB
- docs/skupper-model-provider-diagrams.drawio 65 KB
- docs/van-topology.architecture.html 637 KB
- docs/van-topology.architecture.json 6.6 KB
- docs/van-topology.gif 1042 KB
- POSTMORTEM.md 13 KB
- references/agent-orchestration.md 4.1 KB
- references/architecture.md 3.1 KB
- references/known-issues.md 4.9 KB
- references/troubleshooting.md 2.6 KB
- scripts/common.sh 30 KB runs code
- scripts/down.sh 13 KB runs code
- scripts/setup.sh 32 KB runs code
- scripts/status.sh 18 KB runs code
- scripts/teardown.sh 6.4 KB runs code
- scripts/test-model.sh 7.2 KB runs code
- scripts/up.sh 20 KB runs code
- scripts/upgrade.sh 13 KB runs code
- topology.env.example 6.8 KB
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.
- today Changed · -225 lines · +4 tokens per session 5cc025c80401
- 5d ago Changed · +8 lines 093655d92b4c
- 6d ago Changed · +9 lines a84c171b97c4
- 26d ago Changed · +1 lines 2b2bf697160d
- 1mo ago Changed · +13 lines · -20 tokens per session f4bb1807defa
- 1mo ago Changed · +1 lines 93d3d0a5f69a
- 1mo ago First seen · 405 lines · 82 tokens per session scan A c4ae7837733e
skupper-model-provider is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 2,556 once invoked, about $0.0003 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 skills, from other repositories
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
apigee-agent-gateway-governance
Stands up an Apigee API proxy that a Google Cloud Agent Gateway calls as an ext-proc (Service Extension) callout on an agent's LLM traffic, to meter token usage per model, extract caller identity, and apply Model Armor prompt screening or a semantic cache. Use when wiring Apigee in as an AI gateway behind an Agent…
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for migrating existing AI workloads to GKE (use google-cloud-solution-guided-gke-ai-migration), GKE RAG…