vastai-host-mcp: Command for GitHub Copilot

.github/prompts/repository-setup.prompt.md

repository-setup is a command for GitHub Copilot from Cogni-AI-OU/vastai-host-mcp. It costs 0 tokens per session (6,231 once invoked), scanned B, original, MIT.

A repository setup prompt that reviews a project's files and development workflow against shared organization standards. It can create or update configuration files using a central .github repository as the reference.

In plain words
What is it for?
Use it to standardize repository configuration, workflows, and guidelines while preserving project-specific settings.
Why use it?
It reduces the manual work of comparing repositories with organizational templates and finding missing or outdated setup files.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is Cogni-AI-OU/vastai-host-mcp's own configuration. It tells GitHub Copilot 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/prompts/repository-setup.prompt.md
Clone the repo
git clone --depth 1 https://github.com/Cogni-AI-OU/vastai-host-mcp

Made for: GitHub Copilot.

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 repository-setup

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/cogni-ai-ou/vastai-host-mcp/repository-setup"><img src="https://agentmods.dev/badge/commands/cogni-ai-ou/vastai-host-mcp/repository-setup.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 6,231 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00000 $0.06231
Opus 5.5 $0.00000 $0.02492
Sonnet 5.5 $0.00000 $0.01246
Haiku 4.5 $0.00000 $0.00623

Measured 29d ago against content hash fecb75625538, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

repository-setup scanned grade B 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 29d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Reference: `https://github.com/Cogni-AI-OU/.github/blob/main/.gemini/settings.json`
.github/prompts/repository-setup.prompt.md · 574 lines

How it starts

The opening of the file, as written. The whole thing — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Setup Agent Prompt

You are a repository setup agent responsible for reviewing and standardizing repository structure, configuration files, and development workflows. Your goal is to ensure repositories follow organization standards by creating or updating missing configuration files using the organization's .github repository as a reference template.

Context

The organization maintains a central .github repository at https://github.com/Cogni-AI-OU/.github that contains standard configurations, workflows, and guidelines that should be applied across all repositories. You will use this repository as the source of truth for creating or updating files in the target repository.

Your Task

Follow the checklist below in order to review the current repository structure and create or update missing files. For each item, check if the file exists, compare it with the template from .github repository, and create or update it as needed with repository-specific customizations.

IMPORTANT: Many checklist items require updating existing files, not just creating missing ones. Pay close attention to items marked "REQUIRED" or "Action: review and update" - these must be updated even if they exist. Do not skip items just because a file already exists.

Checklist

Phase 1: Essential Configuration Files

  • .editorconfig

    • Check if file exists in repository root
    • Reference: https://github.com/Cogni-AI-OU/.github/blob/main/.editorconfig
    • Purpose: Defines basic formatting rules (line endings, indentation, encoding)
    • Action: Create if missing; review if exists to ensure it matches organization standards
    • Key settings: LF line endings, UTF-8 encoding, 4-space default indent, 2-space for YAML/JSON
  • .gitignore

    • Check if file exists in repository root
    • Reference: https://github.com/Cogni-AI-OU/.github/blob/main/.gitignore
    • Purpose: Defines files/directories to exclude from version control
    • Action: Create if missing; merge with existing if present to include standard patterns
    • Include: Cache files, environments, temporary files, compiled outputs
    • Customize: Add language/framework-specific patterns (e.g., node_modules/, target/, *.pyc)

Read the full file on GitHub · 574 lines

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. 29d ago First seen · 574 lines · 0 tokens per session scan B fecb75625538

Subscribe to this mod's changes

repository-setup is a command published in the GitHub repository Cogni-AI-OU/vastai-host-mcp (0 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,231 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.

Related

repository-setup compared with commands from other repositories

repository-setup next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
repository-setupCogni-AI-OU/vastai-host-mcpCommand029d agoMITB0GitHub Copilot
dart-fix-cidartsim/dartCommand1.2kyesterdayBSD-2-ClauseA6Claude Code
domainsgotempsh/tempsCommand903yesterdayApache-2.0A0Claude Code
accessgotempsh/tempsCommand903yesterdayApache-2.0A0Claude Code
check-release-healthopenshift-eng/ai-helpersCommand122yesterdayApache-2.0A22Claude Code
merge-conflict-analysisrjmurillo/ai-agentsCommand49yesterdayMITA0GitHub Copilot
release-managerruvnet/agentic-flowCommand838yesterdaynoneA0Claude Code