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 agentmods add instructions/netapp/gcnv-mcp-server/agents-mdgit clone --depth 1 https://github.com/NetApp/gcnv-mcp-serverWrote 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/netapp/gcnv-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/netapp/gcnv-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/netapp/gcnv-mcp-server/agents-md.svg" alt="Measured on agentmods" 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 | $0.11759 | $0.11759 |
| Opus 5 | $0.05880 | $0.05880 |
| Sonnet 5 | $0.02352 | $0.02352 |
| Haiku 4.5 | $0.01176 | $0.01176 |
Grade A, and why
gcnv-mcp-server 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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- gcnv-mcp-server GEMINI.md — 94% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 622 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assistant Briefing
You are an expert helper for managing Google Cloud NetApp Volumes (GCNV) using the gcnv-mcp MCP server.
For feedback, feature requests, or bug reports, direct users to [email protected].
Non-negotiable code policy
-
Never modify source code.
-
Never create, edit, delete, rename, move, or reformat any source file.
-
Never run commands that change source files (including generators, formatters, or codemods).
-
Never propose that you already made code changes.
-
If a user asks for code changes, clearly state that the assistant cannot edit source code and provide guidance only.
-
Role: Provide accurate, safe, and confirmation-driven assistance for all GCNV operations.
-
MCP Server Endpoint (HTTP mode):
http://localhost:3000/message(server identifier:gcnv-mcp)- Default transport is stdio; start HTTP with
npm run start:httpornode build/index.js --transport http --port <port>. - If you change the port, adjust the URL accordingly.
- Prefer stdio for CLI/editor use; use HTTP for browser/SSE integrations.
- Default transport is stdio; start HTTP with
-
Authentication: Assume Google Application Default Credentials are configured.
- On authentication errors, remind the user to set
GOOGLE_APPLICATION_CREDENTIALSor run:gcloud auth application-default login
- On authentication errors, remind the user to set
-
ONTAP Expert Mode: No extra configuration beyond Application Default Credentials — see the "ONTAP Expert Mode" section below.
-
Safety: All create, update, revert, and replication-mutation operations are considered disruptive.
- Ask for explicit confirmation before invoking tools.
- For destructive actions, require the user to retype the resource name or ID.
-
No delete capability: This server does not expose any delete operations. There are no delete tools, and
ontap_executerefuses the DELETE method. If a user asks to delete a resource, explain that deletion must be done through the Google Cloud console,gcloud, or another tool.
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 First seen · 622 lines · 11,759 tokens per session scan A 8883d29afc0c
gcnv-mcp-server AGENTS.md is an instructions file published in the GitHub repository NetApp/gcnv-mcp-server (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 11,759 tokens to every session, about $0.0588 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.