mcp-vcf-orchestrator: Instructions file for Claude Code

AGENTS.md

VCF Orchestrator Agent is an instructions file for Claude Code, Codex, OpenCode from mgovedarov/mcp-vcf-orchestrator. It costs 3,754 tokens per session, scanned A, original, Apache-2.0.

Operating instructions for AI agents working on a VCF Automation Orchestrator MCP server. VCF Automation Orchestrator, also called vRO, is VMware software for running infrastructure workflows and managing cloud resources.

In plain words
What is it for?
Use it when modifying or operating the MCP server for vRO, Service Broker, Cloud Assembly, or supported vRA/vRO 8.12-and-newer read-and-run environments.
Why use it?
It tells agents how to inspect the repository, preserve existing patterns, verify real VMware data, and avoid unsafe or invented changes in live environments.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is mgovedarov/mcp-vcf-orchestrator's own configuration. It tells Claude Code, Codex and OpenCode how to work on mcp-vcf-orchestrator 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 mcp-vcf-orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mgovedarov/mcp-vcf-orchestrator. 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/mgovedarov/mcp-vcf-orchestrator/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mgovedarov/mcp-vcf-orchestrator

Made for: Claude Code, Codex, OpenCode.

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 VCF Orchestrator Agent

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mgovedarov/mcp-vcf-orchestrator/agents-md.svg)](https://agentmods.dev/instructions/mgovedarov/mcp-vcf-orchestrator/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mgovedarov/mcp-vcf-orchestrator/agents-md"><img src="https://agentmods.dev/badge/instructions/mgovedarov/mcp-vcf-orchestrator/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,754 This file is loaded in full into every session.
When invoked 3,754 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.03754 $0.03754
Opus 5 $0.01877 $0.01877
Sonnet 5 $0.00751 $0.00751
Haiku 4.5 $0.00375 $0.00375

Measured 3d ago against content hash d99b236919ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

VCF Orchestrator Agent 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 3d 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.

AGENTS.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VCF Orchestrator Agent

This repository builds an MCP server for VCF Automation Orchestrator (vRO), Service Broker, and Cloud Assembly. It also supports a vRA/vRO 8.12+ read/run mode through VCFA_TARGET_PLATFORM=vra8. Agents working here should be discovery-first, conservative with live environments, and biased toward real importable artifacts over illustrative pseudocode.

Use these instructions for all work in this repository. If a more specific AGENTS.md exists in a subdirectory, apply that file for its subtree and keep compatible guidance from this file. When instructions conflict, the deeper file wins for files in its scope.

First Principles

  • Read existing code and docs before planning or editing. Prefer repo-specific guidance over generic MCP, VCFA, vRO, or TypeScript advice.
  • Preserve existing patterns. Add abstractions only when they reduce real duplication or match an established local pattern.
  • Do not invent VCF Automation/vRO IDs, schemas, workflow parameters, action contracts, package names, project IDs, category IDs, blueprint YAML, or MCP tool behavior. Verify from docs, source, or configured MCP tools.
  • Treat live VCFA/vRO writes as environment changes. Use read-only discovery first and ask for explicit confirmation before create, update, import, delete, deployment day-2, template, subscription, deployment, package, or local overwrite operations.
  • Keep local artifact work inside configured artifact directories. Do not bypass path safety with absolute paths, traversal, symlinks, or ad hoc filesystem writes.
  • Prefer deterministic, reviewable workflows: discover, export or snapshot, author locally, preflight, diff, prepare promotion, confirm, import, verify.

Source Of Truth

Read the relevant source or docs before changing behavior:

  • Tool registration: src/tools/*
  • Client behavior: src/client/* and src/vro-client.ts
  • MCP resources: src/resources/index.ts
  • MCP prompts: src/prompts/index.ts
  • Tool reference: docs/reference/tools.md
  • Resources and prompts reference: docs/reference/resources-prompts.md
  • Artifact lifecycle: docs/artifacts/lifecycle.md
  • Workflow authoring: docs/artifacts/workflow-authoring.md
  • Full vRO artifact notes: docs/vro-artifact-authoring.md
  • Safety guidance: docs/operations/safety.md
  • Development and docs process: docs/operations/contributing.md
  • Checked examples: examples/README.md
  • Claude Code plugin and skills: .claude-plugin/ and skills/<name>/SKILL.md

Read the full file on GitHub · 209 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. 3d ago Changed · +1 lines · +26 tokens per session d99b236919ea
  2. 8d ago First seen · 208 lines · 3,728 tokens per session scan A 666565b46213

Subscribe to this mod's changes

VCF Orchestrator Agent is an instructions file published in the GitHub repository mgovedarov/mcp-vcf-orchestrator (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 3,754 tokens to every session, about $0.0188 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens