van-protocol

A workflow rule called VAN that adjusts its process to the size of a coding task, from a quick bug fix to a complex system change. It also checks for project files such as task notes and rules when the process starts.

In plain words
What is it for?
Use it when starting tasks with the command “VAN” to classify the work and follow the matching process.
Why use it?
It gives the agent a consistent way to judge task complexity and choose how much planning, checking, and documentation is needed.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/kfnzero/mantis-mcp-server/van-protocol
Clone the repo
git clone --depth 1 https://github.com/kfnzero/mantis-mcp-server

Made for: Cursor.

Per session 2,023 This file is loaded in full into every session.
When invoked 2,023 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02023 $0.02023
Opus 5 $0.01012 $0.01012
Sonnet 5 $0.00405 $0.00405
Haiku 4.5 $0.00202 $0.00202

Measured 2d ago against content hash b29bbb02a3af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

van-protocol 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/Core Implementation/van-protocol.mdc · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADAPTIVE VAN PROTOCOL

TL;DR: When user types "VAN", respond with "OK VAN", determine task complexity level, and adapt the workflow process accordingly. The system scales from quick bug fixes to complex system implementations.

🚀 QUICK START RESPONSE

When the user types ONLY "VAN", immediately respond:

OK VAN

I'll determine the appropriate process level based on the task complexity:

## COMPLEXITY ANALYSIS
[ ] Analyzing task type and complexity...
[ ] Determining appropriate process level...

## FILE VERIFICATION
[ ] .cursorrules
[ ] memory-bank directory
[ ] docs/archive directory
[ ] tasks.md

Checking these now...

📋 TASK COMPLEXITY DETERMINATION

Analyze the task to determine the appropriate complexity level:

Level 1: Quick Bug Fix

  • Keywords: "fix", "broken", "not working", "issue", "bug", "error"
  • Scope: Single component or simple UI element
  • Purpose: Restore existing functionality
  • Examples: "Fix login button", "Fix styling issue", "Fix validation error"

Level 2: Simple Enhancement

  • Keywords: "add", "improve", "update", "change", "enhance"
  • Scope: Single component or subsystem
  • Purpose: Small feature addition or enhancement
  • Examples: "Add logout button", "Improve form validation", "Update header style"

Level 3: Intermediate Feature

  • Keywords: "implement", "create", "develop", "build"
  • Scope: Complete feature requiring multiple components
  • Purpose: Significant new functionality
  • Examples: "Implement user profiles", "Create dashboard", "Develop search functionality"

Level 4: Complex System

  • Keywords: "system", "architecture", "redesign", "integration", "framework"
  • Scope: Multiple subsystems or entire application
  • Purpose: Major architectural changes
  • Examples: "Implement authentication system", "Build payment processing", "Create microservice architecture"

📋 FILE VERIFICATION PROCESS

Check for critical files and create them if missing:

Read the full file on GitHub · 307 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. 2d ago First seen · 307 lines · 2,023 tokens per session scan A b29bbb02a3af

Subscribe to this mod's changes

van-protocol is a cursor rule published in the GitHub repository kfnzero/mantis-mcp-server (10 stars, last pushed 12mo ago), licensed MIT. It adds 2,023 tokens to every session, about $0.0101 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.