goose-skupper-provider

goose-skupper-provider is a skill for Claude Code from rhtevan/agentfs. It costs 32 tokens per session (1,834 once invoked), scanned C, original, Apache-2.0.

A setup guide for connecting Goose, a command-line and desktop coding assistant, to an LLM running on a remote graphics processor through Skupper, a network system that makes remote services available locally.

In plain words
What is it for?
Use it to configure Goose with the Skupper provider and select a remote model host or model profile.
Why use it?
It avoids using a cloud provider directly and handles the routing needed to reach different remote model hosts.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to configure Goose with the Skupper provider and select a remote model host or model profile.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rhtevan/agentfs/goose-skupper-provider
Install

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.

Any agent
npx skills add rhtevan/agentfs --skill goose-skupper-provider
Clone the repo
git clone --depth 1 https://github.com/rhtevan/agentfs

Made for: Claude Code.

Wrote 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.

agentmods badge for goose-skupper-provider

README.md
[![agentmods](https://agentmods.dev/badge/skills/rhtevan/agentfs/goose-skupper-provider/github.svg)](https://agentmods.dev/skills/rhtevan/agentfs/goose-skupper-provider)
Your own site
<a href="https://agentmods.dev/skills/rhtevan/agentfs/goose-skupper-provider"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/goose-skupper-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.

agentmods 80×15 button for goose-skupper-provider

Your own site · 80×15
<a href="https://agentmods.dev/skills/rhtevan/agentfs/goose-skupper-provider"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/goose-skupper-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,834 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01834
Opus 5 $0.00016 $0.00917
Sonnet 5 $0.00006 $0.00367
Haiku 4.5 $0.00003 $0.00183

Measured 8d ago against content hash 97f14788076d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

goose-skupper-provider scanned grade C with 1 finding 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 8d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/setup.sh, scripts/teardown.sh, scripts/test.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| T8 | S6 | `MODEL_ID='"};rm -rf /;{"' PORT=9000 CTX=131072 bash setup.sh --test-inject` | Validation fails, backup restored, no file damage |
skills/goose-skupper-provider/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goose Skupper Provider

Configure Goose (CLI and Desktop) to use a remote GPU-hosted LLM model as a custom provider named Skupper. The model is served through a Skupper V2 Virtual Application Network managed by skupper-model-provider, which exposes remote GPU hosts (rhel-ai, rhtevan-work) as local endpoints on localhost:9000 and localhost:10000. Use this skill after the VAN is running (skupper model up) to wire Goose to the self-hosted model instead of a cloud provider.

Host-Based Routing

Skupper routes by host:port. The active model is determined by hosted-model-ctl (profile-based mutual exclusion). The setup script discovers the model identity from the live API — no static alias mapping.

Host Port Default Profile Routing Key
rhel-ai 9000 g8b-fp8-spec-128k model-api-rhel-ai
rhtevan-work 10000 g3b-16k model-api-rhtevan-work

The script accepts host names (rhel-ai) or profile names (g8b-fp8-spec-128k) — profile names are resolved to their host. Default target: rhel-ai.

Poison-JSON Safeguard

⚠️ Goose Desktop loads ALL JSON files in ~/.config/goose/custom_providers/. One malformed file breaks ALL providers — not just the broken one.

The setup.sh script enforces three layers of defense:

  1. Python json.dumps — writes JSON programmatically (never bash heredoc interpolation)
  2. Round-trip validation — parses the output back and checks all 22 required fields before writing to disk
  3. Post-write validation — reads the file from disk and validates independently; restores backup on any failure

NEVER write this JSON manually. Always use setup.sh.

Specification

ID Capability Verifiable By
S1 Setup provider for a host or profile scripts/setup.sh HOST_OR_PROFILE → JSON + config.yaml updated
S2 Teardown provider scripts/teardown.sh → JSON + config.yaml cleaned
S3 Recreate provider (teardown + setup) teardown.sh then setup.sh HOST_OR_PROFILE
S4 Verify provider configuration scripts/test.sh → 6 checks pass
S5 API-driven model discovery setup.sh queries /v1/models for model ID + context
S6 Poison-JSON prevention setup.sh validates JSON pre- and post-write; restores backup on failure

Read the full file on GitHub · 161 lines

Files

What ships with it

5 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.

Changes

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.

  1. 8d ago First seen · 161 lines · 32 tokens per session scan C 97f14788076d

Subscribe to this mod's changes

goose-skupper-provider is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 1,834 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens