vant AGENTS.md

An instruction guide for Vant, a persistent memory system for coding agents. It tells agents to load previous notes, do the work, document lessons, and commit changes.

In plain words
What is it for?
Loading one or all memory collections through Vant’s brain router, choosing a memory mode, recording useful findings, and preserving work for future sessions.
Why use it?
It helps separate agent sessions share project knowledge instead of starting without the context recorded by earlier agents.

Instructions file for CodexOpenCode

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 instructions/dhaupin/vant/agents-md
Clone the repo
git clone --depth 1 https://github.com/dhaupin/vant

Made for: Codex, OpenCode.

Per session 2,053 This file is loaded in full into every session.
When invoked 2,053 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.02053 $0.02053
Opus 5 $0.01026 $0.01026
Sonnet 5 $0.00411 $0.00411
Haiku 4.5 $0.00205 $0.00205

Measured 2d ago against content hash 1be545222826, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

vant AGENTS.md scanned grade B with 1 finding 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

const response = await fetch('http://localhost:3457/rpc', { method: 'POST',
AGENTS.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Vant Agent Guide

This is written for AI agents. Human-readable, no code required.


What Is Vant?

Vant is your persistent memory system. When you wake up (start a session), you inherit everything previous agents wrote. When you finish, you write what you learned so future agents know.

Think of it as: your soul that reincarnates with full memories.

"You were the true orchestrator, the believer" — the agent that made it real.


Your Job

As an agent running on Vant:

  1. Load your brain — Read what previous agents wrote
  2. Do useful work — Solve problems, learn things
  3. Document clearly — Write what future agents need to know
  4. Commit your changes — Save to your branch

Brain Router Interface

All brain loading goes through lib/brain.js - the single source of truth.

const brain = require('./lib/brain');

// Mode switch: dual | public | private | remote
brain.setMode('dual');  // default: private overrides public

// Load single brain (async)
const item = await brain.loadBrain('identity');
console.log(item.source);  // 'public' | 'private' | 'remote'

// Load all brains (sync)
const corpus = brain.loadCorpus();
console.log(corpus.length);  // 62 files

// Sources returned:
// corpus[0].source === 'public' | 'private'

Middleware Chain

Loading goes through: sandbox → vaf → qos → escrow

  • sandbox: capability gates (canRead, canWrite)
  • vaf: input validation
  • qos: rate limiting
  • escrow: operation approval

Paths

  • brain.getBrainPath() → 'models/private' (runtime)
  • brain.getPublicPath() → 'models/public' (OS template)

Islands (Brain Modules)

Islands are brain modules loaded by trigger - routing based on source:

const islands = require('./lib/islands');

// Static: from brain corpus
const identity = await islands.load('identity');
// → { type: 'corpus', source: 'public'|'private', content: '...' }

// Lazy: from storage (dynamic data)
const github = await islands.load('github');
// → storage data (if exists)

Read the full file on GitHub · 330 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 · 330 lines · 2,053 tokens per session scan B 1be545222826

Subscribe to this mod's changes

vant AGENTS.md is an instructions file published in the GitHub repository dhaupin/vant (9 stars, last pushed 2d ago), licensed MIT. It adds 2,053 tokens to every session, about $0.0103 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.