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.
curl -O https://raw.githubusercontent.com/Cogni-AI-OU/vastai-host-mcp/main/.github/instructions/markdown.instructions.mdgit clone --depth 1 https://github.com/Cogni-AI-OU/vastai-host-mcpWrote 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/instructions/cogni-ai-ou/vastai-host-mcp/markdown)<a href="https://agentmods.dev/instructions/cogni-ai-ou/vastai-host-mcp/markdown"><img src="https://agentmods.dev/badge/instructions/cogni-ai-ou/vastai-host-mcp/markdown/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/instructions/cogni-ai-ou/vastai-host-mcp/markdown"><img src="https://agentmods.dev/badge/instructions/cogni-ai-ou/vastai-host-mcp/markdown.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 | $0.00843 | $0.00843 |
| Opus 5.5 | $0.00337 | $0.00337 |
| Sonnet 5.5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
vastai-host-mcp markdown.instructions.md 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 2mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown Instructions
Markdown Content Rules
The following markdown content rules are enforced in the validators:
- Headings: Use H1 (
#), H2 (##), and H3 (###) heading levels to structure content. Avoid H4 (####) and deeper levels, as they suggest content needs better organization or should be split into separate documents. - Lists: Use bullet points or numbered lists for lists. Ensure proper indentation and spacing.
- Code Blocks: Use fenced code blocks for code snippets. Always specify the language for syntax highlighting (required for linting compliance).
- Links: Use proper Markdown syntax for links. Ensure that links are valid and accessible.
- Images: Use proper Markdown syntax for images. Include alt text for accessibility.
- Tables: Use Markdown tables for tabular data. Ensure proper formatting and alignment.
- Line Length: Limit line length to 120 characters to align with project linting.
- Whitespace: Use appropriate whitespace to separate sections and improve readability.
Formatting and Structure
Follow these guidelines for formatting and structuring your markdown content:
- Lists: Use
-for bullet points and1.for numbered lists. Indent nested lists with two spaces. - Code Blocks: Use triple backticks (```) to create fenced code blocks. Always specify the
language after the opening backticks for syntax highlighting (e.g.,
csharp). This is required for linting compliance. - Links: Use
[link text](URL)for links. Ensure that the link text is descriptive and the URL is valid.- If a URL is long or reused, prefer reference-style links placed at the end of the file
after
<!-- Named links -->.
- If a URL is long or reused, prefer reference-style links placed at the end of the file
after
- Images: Use
for images. Include a brief description of the image in the alt text. - Tables: Use
|to create tables. Ensure that columns are properly aligned and headers are included. - Line Length: Break lines at 120 characters to match
.markdownlint.yaml. Use soft line breaks for long paragraphs. - Whitespace: Use blank lines to separate sections and improve readability. Avoid excessive whitespace.
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.
- 2mo ago First seen · 73 lines · 843 tokens per session scan A 292b1699155a
vastai-host-mcp markdown.instructions.md is an instructions file published in the GitHub repository Cogni-AI-OU/vastai-host-mcp (0 stars, last pushed 29d ago), licensed MIT. It adds 843 tokens to every session, about $0.0034 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 2026-08-31.
vastai-host-mcp markdown.instructions.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vastai-host-mcp markdown.instructions.mdCogni-AI-OU/vastai-host-mcp | Instructions file | 0 | 29d ago | MIT | A | 843 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |