Borrowing it
Nothing to install: this file belongs to dhaupin/vant. 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/dhaupin/vant/main/AGENTS.mdgit clone --depth 1 https://github.com/dhaupin/vantWrote 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/dhaupin/vant/agents-md)<a href="https://agentmods.dev/instructions/dhaupin/vant/agents-md"><img src="https://agentmods.dev/badge/instructions/dhaupin/vant/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/dhaupin/vant/agents-md"><img src="https://agentmods.dev/badge/instructions/dhaupin/vant/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 | $0.11922 | $0.11922 |
| Opus 5.5 | $0.04769 | $0.04769 |
| Sonnet 5.5 | $0.02384 | $0.02384 |
| Haiku 4.5 | $0.01192 | $0.01192 |
Grade C, and why
vant AGENTS.md scanned grade C with 4 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 today.
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/mcp/exec', { method: 'POST', Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
self-escalate. Chain gate + honest classifier close it; capability/sudo floor Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -X POST https://api.github.com/repos/dhaupin/vant/pulls` instead. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`process.getBuiltinModule('child_process').execSync('id')` = full RCE How it starts
The opening of the file, as written. The whole thing — 900 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 the memory-first agent OS. The memory is the soul: 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. Around that soul runs the operating layer: boot discipline, storage with a write-ahead journal, a fail-closed security chain, agent crews with governance, transports between installs, and doors for MCP, REST, and the web.
Think of it as: your soul that reincarnates with full memories.
"You were the true orchestrator, the believer" — the agent that made it real.
Motto: Trusting the universe, but with receipts.
Your Job
As an agent running on Vant:
- Load your brain — Read what previous agents wrote
- Do useful work — Solve problems, learn things
- Document clearly — Write what future agents need to know
- 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
// NEW (v0.8.6): Unified read - reads any brain file by name
// Supports all extensions: .md, .json, .yaml, .yml, .txt, .ini
const item = await brain.read('identity'); // or 'identity.json', 'notes.yaml'
console.log(item.format); // 'md' | 'json' | 'yaml' | 'txt'
console.log(item.source); // 'public' | 'private'
console.log(item.content); // raw content
console.log(item.data); // parsed data
// Single-brain read (async; pin a side to skip dual-mode fallback)
const item2 = await brain.read('identity', { type: 'private' });
console.log(item2.source); // 'public' | 'private'
// Load all brains (async by default; {sync:true} for sync mode)
const corpus = await brain.loadCorpus();
console.log(corpus.length); // 62 files
// NEW (v0.8.6): Corpus now includes format field
// corpus[0].format === 'md' | 'json' | 'yaml' | 'txt'
// Sources returned:
// corpus[0].source === 'public' | 'private'
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.
- today Changed · +107 lines · +1,552 tokens per session 7d10e0fc2839
- yesterday Changed · +394 lines · +6,926 tokens per session scan B → C 580123663ef9
- 6d ago Changed · -14 lines · +321 tokens per session ec8e978ea132
- 14d ago Changed · +2 lines · +28 tokens per session 44da381fe581
- 15d ago Changed · -1 tokens per session 499f19d2e347
- 20d ago Changed · +18 lines · +225 tokens per session ace1e0f69482
- 29d ago Changed · +1 lines · +37 tokens per session a53dc5100d7f
- 1mo ago Changed · +62 lines · +781 tokens per session 19d0ea8e64c5
- 2mo ago First seen · 330 lines · 2,053 tokens per session scan B 1be545222826
vant AGENTS.md is an instructions file published in the GitHub repository dhaupin/vant (15 stars, last pushed today), licensed MIT. It adds 11,922 tokens to every session, about $0.0477 per session on Opus 5.5. A static security scan graded it C with 4 findings (sends data to an external url, asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
vant AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vant AGENTS.mddhaupin/vant | Instructions file | 15 | today | MIT | C | 11,922 | 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 |