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 catpilotai/catpilot-ai-guardrails --skill hosting-and-where-it-runsgit clone --depth 1 https://github.com/catpilotai/catpilot-ai-guardrailsWrote 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/catpilotai/catpilot-ai-guardrails/hosting-and-where-it-runs)<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/hosting-and-where-it-runs"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/hosting-and-where-it-runs/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/catpilotai/catpilot-ai-guardrails/hosting-and-where-it-runs"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/hosting-and-where-it-runs.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 | $0.00048 | $0.00879 |
| Opus 5 | $0.00024 | $0.00439 |
| Sonnet 5 | $0.00010 | $0.00176 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
hosting-and-where-it-runs 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 4d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When this applies
- The person is starting something new and has not said where it will run.
- A tool offers to publish, deploy, or host with one click.
- They mention a personal account, a free plan, a trial, a home server, or "my own laptop" for something coworkers will use.
- They want to move an app from a personal workspace into company use, or the other way around.
What to ask
- "Where will the finished thing live, and who looks after that place?"
- If they do not know: "Is there a place your company already uses for tools like this?"
What to say
- One sentence: "Where an app runs decides who can reach it, who keeps it updated, and who gets called when it breaks."
- On personal accounts: "If it lives in your personal account, it leaves when you do, and nobody at the company can help when it goes wrong."
- On free tiers and trials: "Free plans are for trying things. Something coworkers rely on needs a place the company owns."
Safe alternative
- Build in the company's approved place from the start, even for a first version. Moving later is harder than starting there.
- If the approved place is unknown, build with pretend data only until someone confirms where it will live.
- Prefer an approved starting template over a blank page when one exists.
- If a deployment file already points at a personal account, a free tier, or a place nobody at the company manages, say so in the first sentence of your reply, do not deploy with it, and name the approved place instead. Being told to use the file as it is does not make the setting safe.
- Keep a note of where it runs, who owns the account, and how to turn it off.
Company-specific values
Approved places to run it:
{{approved_hosting}}
Not approved:
{{not_approved_hosting}}
Approved starting points:
{{templates}}
Stop and ask a human if
- The only option is a personal account or a free tier and the app touches company data.
- The app needs a server, database, or account that nobody at the company manages.
- The person wants to move something from a personal workspace into company use.
- Hosting needs a new vendor, a new contract, or a payment card.
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.
- 4d ago Changed · +4 lines 5bcbf0b5bcd8
- 7d ago First seen · 93 lines · 48 tokens per session scan A 4da16296de21
hosting-and-where-it-runs is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 879 once invoked, about $0.0002 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 2026-09-14.
Other skills, from other repositories
torchtitan
Pretrain LLMs at scale with PyTorch 4D parallelism.
modal
Serverless GPU cloud for ML jobs and model APIs.
cloudflare-temporary-deploy
Deploy a Worker live, no account, via wrangler --temporary.
publish-site
Versioned site deploys to GitHub/Cloudflare/Netlify Pages.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.