Borrowing it
Nothing to install: this file belongs to hlebtkachenko/ovhcloud-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/hlebtkachenko/ovhcloud-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/hlebtkachenko/ovhcloud-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/hlebtkachenko/ovhcloud-mcp/agents-md)<a href="https://agentmods.dev/instructions/hlebtkachenko/ovhcloud-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hlebtkachenko/ovhcloud-mcp/agents-md/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/hlebtkachenko/ovhcloud-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hlebtkachenko/ovhcloud-mcp/agents-md.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 | $0.00343 | $0.00343 |
| Opus 5.5 | $0.00137 | $0.00137 |
| Sonnet 5.5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
ovhcloud-mcp AGENTS.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 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.
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.
What it actually says
AGENTS.md
MCP server for the OVHcloud API (VPS, domains and DNS, billing, API explorer, raw calls) plus SSH command execution. TypeScript, Node 22+, stdio transport. Layout and design: ARCHITECTURE.md.
Commands
npm ci
npm run build # tsc -> dist/
npm test # build + node:test suite (fake OVH API and SSH server, no credentials)
npm run check:contract # validate every tool's OVH request against OVH's published API schemas
Rules
- Any change to a request a tool sends must pass
npm run check:contract. Look up paths, methods and parameter names in the OVH schemas (.spec-cache/after the first run, orhttps://eu.api.ovh.com/v1/<api>.json), not in memory. - Build API paths with the
apiPathtagged template so every parameter is encoded as one segment. - Every tool gets MCP annotations; writes report errors through
errorResult(err, "<read tool>")so a timed-out write names the tool to verify with. - New tools: one area per file in
src/tools/, register insrc/index.ts, add a test intest/and a row in the README tools table. - Synthetic data only in tests and docs:
example.com,192.0.2.x, placeholder IDs. No real hostnames, accounts or bills. - Never commit credentials; configuration is env-only. Keep the README tool tables and env tables in sync with the code.
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.
- 29d ago First seen · 22 lines · 343 tokens per session scan A 12ff9c159117
ovhcloud-mcp AGENTS.md is an instructions file published in the GitHub repository hlebtkachenko/ovhcloud-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 343 tokens to every session, about $0.0014 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 2026-10-08.
ovhcloud-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ovhcloud-mcp AGENTS.mdhlebtkachenko/ovhcloud-mcp | Instructions file | 3 | 1mo ago | MIT | A | 343 | Codex, OpenCode |
| 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 |