Borrowing it
Nothing to install: this file belongs to david-eve-za/nvidia-nim-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/david-eve-za/nvidia-nim-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/david-eve-za/nvidia-nim-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/david-eve-za/nvidia-nim-mcp/agents-md)<a href="https://agentmods.dev/instructions/david-eve-za/nvidia-nim-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/david-eve-za/nvidia-nim-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/david-eve-za/nvidia-nim-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/david-eve-za/nvidia-nim-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 | $0.00941 | $0.00941 |
| Opus 5.5 | $0.00376 | $0.00376 |
| Sonnet 5.5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
nvidia-nim-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 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This document provides essential information for agentic coding systems working with this NVIDIA NIM MCP Server codebase.
Build Commands
# Clean build artifacts
npm run clean
# Build TypeScript to JavaScript
npm run build
# Development mode (watch and restart)
npm run dev
# Production start
npm start
Linting Commands
# Run ESLint on source files
npm run lint
Test Commands
# Run all tests
npm test
# Run a specific test file
npm test src/config.test.ts
# Run tests with verbose output
npm test -- --verbose
# Run tests matching a pattern
npm test -- --testNamePattern="Config"
# Run tests in watch mode
npm test -- --watch
# Generate coverage report
npm test -- --coverage
Code Style Guidelines
Imports
- Use ES modules with
.jsextensions even in TypeScript files - Import ordering: external packages, internal modules, type-only imports
- Use named imports over default imports when possible
- Group imports logically with blank lines between groups
Formatting
- TypeScript strict mode enabled
- Prettier-style formatting (via ESLint)
- 2-space indentation
- Line width: 80 characters
- Trailing commas in multi-line objects/arrays
- No semicolons (recommended by modern TypeScript)
Types
- Prefer interfaces over types for object shapes
- Use Zod for runtime validation of external inputs
- Explicit typing for function parameters and return values
- Strict null checking enabled
- Avoid
anytype except in rare justified cases
Naming Conventions
- camelCase for variables and functions
- PascalCase for classes, interfaces, and types
- UPPER_CASE for constants
- Descriptive names over abbreviations
- Boolean variables prefixed with
is,has,should, etc.
Error Handling
- Use typed errors and proper error hierarchies
- Always handle promise rejections
- Centralized error logging with winston
- User-friendly error messages for clients
- Preserve stack traces during error wrapping
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 · 159 lines · 941 tokens per session scan A 5baa657c3953
nvidia-nim-mcp AGENTS.md is an instructions file published in the GitHub repository david-eve-za/nvidia-nim-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 941 tokens to every session, about $0.0038 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.
nvidia-nim-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nvidia-nim-mcp AGENTS.mddavid-eve-za/nvidia-nim-mcp | Instructions file | 1 | 2mo ago | MIT | A | 941 | 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 |