Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gaelic-ghost/socketnpx agentmods add skills/gaelic-ghost/socket/companion-clisWrote 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/gaelic-ghost/socket/companion-clis)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/companion-clis"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/companion-clis/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/gaelic-ghost/socket/companion-clis"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/companion-clis.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 | $0.00026 | $0.04054 |
| Opus 5.5 | $0.00010 | $0.01622 |
| Sonnet 5.5 | $0.00005 | $0.00811 |
| Haiku 4.5 | $0.00003 | $0.00405 |
Grade A, and why
companion-clis 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.
How it starts
The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Companion CLIs
Four CLIs commonly needed alongside Runpod: HuggingFace (hf), GitHub (gh), Docker (docker), and AWS (aws). Each requires credentials before use.
Windows: Install WSL2 First
If you are on Windows, install WSL2 (Windows Subsystem for Linux) before proceeding. WSL2 gives you a native Linux environment on Windows, which all these CLIs are designed for. Run in PowerShell as Administrator, then restart:
wsl --install
This installs WSL2 with Ubuntu by default. After restarting, open the Ubuntu app to complete setup (create a Linux username and password). From that point on, follow the Linux instructions throughout this skill.
HuggingFace CLI
The HuggingFace CLI (hf) is used to download models from the Hub to your local machine so they are cached and available when you build and run the Docker container. For example, to deploy openai/gpt-oss-20b to a Runpod serverless endpoint: download the model locally first, build a Docker image that includes or mounts it, validate the container locally, then push the image to Docker Hub for Runpod to pull.
Install
# macOS / Linux (standalone installer — recommended)
curl -LsSf https://hf.co/cli/install.sh | bash
# macOS (Homebrew)
brew install hf
# Windows (WSL2): use the Linux standalone installer above
Note:
pip install huggingface_hubinstalls the older Python CLI (huggingface-cli), which uses different command syntax. The commands below are for the standalonehfCLI.
Credentials
Get a token at https://huggingface.co/settings/tokens. Use write access for uploading; read access is sufficient for downloading public or gated models.
# Option 1: interactive login (saves token to ~/.cache/huggingface/token, optionally to git credential store)
hf auth login
# Option 2: non-interactive (pass token directly, useful in scripts and pod start commands)
hf auth login --token $HF_TOKEN --add-to-git-credential
# Option 3: environment variable (takes precedence over saved token; to revert, unset the variable)
export HF_TOKEN=hf_...
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 · 423 lines · 26 tokens per session scan F 68d8c3118f4d
companion-clis is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 4,054 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 2026-09-03.
Other skills, from other repositories
cloud-administration
Administers the cloud the company runs on rather than the one it sells — tenant and subscription structure, the SaaS estate and who owns each app, identity as the real perimeter, cloud spend that arrives as a surprise, and what the provider does not do for you. Use this to structure subscriptions or tenants, get…
chief-data-officer
Owns data as an asset — governance, quality, the warehouse and semantic layer, analytics capability, and the governance of models built on top. Use this for a decision about how data is collected, stored, defined, or shared; when numbers disagree between teams; when deciding what to build in-house versus buy; when…
network-administration
Designs and operates the corporate network — segmentation, remote access, wireless, DNS and addressing, and diagnosing network problems. Use this to segment a network, set up or fix remote access, diagnose intermittent connectivity, plan addressing or DNS, or assess whether the network's trust assumptions still hold.
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…
virtualization-operations
Runs the hypervisor layer beneath the servers — host capacity and consolidation ratios, VM sprawl, snapshot discipline, resilience and live migration, and licensing that counts cores rather than instances. Use this to size or expand a cluster, work out why VMs are slow when the hosts look idle, clean up sprawl, set…
ai-workflow-architect
Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…