vastai-host-mcp: Agent for Claude Code

.github/agents/FIREWALL.md

FIREWALL is an agent for Claude Code from Cogni-AI-OU/vastai-host-mcp. It costs 0 tokens per session (173 once invoked), scanned A, original, MIT.

A reference list of internet hosts that coding agents may need to reach when operating behind a restrictive firewall. It also points to official guidance for maintaining the list.

In plain words
What is it for?
Configuring firewall allowlists for GitHub, package registries, documentation sites, container registries, and related services.
Why use it?
It helps prevent blocked downloads, repository access, package installation, and documentation lookups caused by missing firewall rules.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is Cogni-AI-OU/vastai-host-mcp's own configuration. It tells Claude Code how to work on vastai-host-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vastai-host-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Cogni-AI-OU/vastai-host-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Cogni-AI-OU/vastai-host-mcp/main/.github/agents/FIREWALL.md
Clone the repo
git clone --depth 1 https://github.com/Cogni-AI-OU/vastai-host-mcp

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 FIREWALL

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-ai-ou/vastai-host-mcp/firewall/github.svg)](https://agentmods.dev/agents/cogni-ai-ou/vastai-host-mcp/firewall)
Your own site
<a href="https://agentmods.dev/agents/cogni-ai-ou/vastai-host-mcp/firewall"><img src="https://agentmods.dev/badge/agents/cogni-ai-ou/vastai-host-mcp/firewall/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 FIREWALL

Your own site · 80×15
<a href="https://agentmods.dev/agents/cogni-ai-ou/vastai-host-mcp/firewall"><img src="https://agentmods.dev/badge/agents/cogni-ai-ou/vastai-host-mcp/firewall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 173 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00173
Opus 5 $0.00000 $0.00086
Sonnet 5 $0.00000 $0.00035
Haiku 4.5 $0.00000 $0.00017

Measured 11d ago against content hash 4e449350d29f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

FIREWALL 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 11d 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.

.github/agents/FIREWALL.md · 35 lines

What it actually says

Firewall Allowlist for Copilot Agents

If your agent runs behind a restrictive firewall, allow these hosts. Always check the official guidance for updates.

agents.md
aka.ms
ansible.com
api.github.com
codeload.github.com
contributor-covenant.org
freecodecamp.org
galaxy.ansible.com
gh.io
ghcr.io
github.com
guides.github.com
hashicorp.com
marketplace.visualstudio.com
npm.pkg.github.com
objects.githubusercontent.com
pkg-containers.githubusercontent.com
raw.githubusercontent.com
registry.npmjs.org
support.github.com
tldrlegal.com
uploads.github.com
user-images.githubusercontent.com
yaml-multiline.info

Note: Keep the list sorted alphabetically for easier maintenance.

Reference: https://gh.io/copilot/firewall-config

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. 11d ago First seen · 35 lines · 0 tokens per session scan A 4e449350d29f

Subscribe to this mod's changes

FIREWALL is an agent published in the GitHub repository Cogni-AI-OU/vastai-host-mcp (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 173 tokens. 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.

Related

Other agents, from other repositories