VaultysClaw: Instructions file for Claude Code

CLAUDE.md

VaultysClaw CLAUDE.md is an instructions file for Claude Code from vaultys/VaultysClaw. It costs 3,604 tokens per session, scanned A, original, MIT.

Repository instructions for VaultysClaw, a decentralized platform where a central control plane manages agent controllers over WebSockets. The controllers run tools and maintain cryptographic identities.

In plain words
What is it for?
Use them when working on policies, APIs, the dashboard, agent runtime, MCP gateway, notifications, builds, or the simulator.
Why use it?
They document the monorepo packages, commands, and architecture so agents can change the correct part without overlooking connected services.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is vaultys/VaultysClaw's own configuration. It tells Claude Code how to work on VaultysClaw 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 VaultysClaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vaultys/VaultysClaw. 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/vaultys/VaultysClaw/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vaultys/VaultysClaw

Made for: Claude Code.

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 VaultysClaw CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vaultys/vaultysclaw/claude-md/github.svg)](https://agentmods.dev/instructions/vaultys/vaultysclaw/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vaultys/vaultysclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/vaultys/vaultysclaw/claude-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.

agentmods 80×15 button for VaultysClaw CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vaultys/vaultysclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/vaultys/vaultysclaw/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,604 This file is loaded in full into every session.
When invoked 3,604 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 $0.03604 $0.03604
Opus 5.5 $0.01442 $0.01442
Sonnet 5.5 $0.00721 $0.00721
Haiku 4.5 $0.00360 $0.00360

Measured 15d ago against content hash 4b393b256c15, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

VaultysClaw CLAUDE.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 15d 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.

CLAUDE.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

VaultysClaw is an agent identity and trust platform. A control plane (Next.js + WebSocket server) maintains an append-only ledger of signed capability certificates bound to VaultysId DIDs, and decides what every Actor — agent, device, sensor, or human — is allowed to do. Clients connect over WebSocket, prove their identity with a Challenger handshake, and receive certificates they can verify offline.

Monorepo: pnpm workspaces + Turborepo.

Package Description CLAUDE.md
packages/policy Certificate wire format (sign/verify/pack), AgentCapability, CertScope, resource limits, runtime enforcement gates. Pure, no I/O. →
packages/trust Trust ledger engine: ABAC/multi-certificate permission resolution (resolvePermission) over the CapabilityCertificate ledger. Pure, no I/O. →
packages/shared The webhook event catalog + the LLM provider union. Deliberately tiny. →
packages/controlplane The control plane: Next.js App Router admin console + WebSocket server, Prisma/Postgres, the certificate ledger. →
packages/sdk TypeScript client for the control plane's protocol — handshake, capability state, certificate-status refresh, resolvePermission. The counterpart of sdk-go/. →
packages/webhook-dispatcher Standalone worker: consumes events from BullMQ, signs them (HMAC) and POSTs to endpoints; also fans out to Apprise notification channels. →
packages/videos Narrated demo videos of the console: Playwright drives the real control plane on its own stack (docker/video.env, 3013 / ws 8093 / pg 5436) with a live simulated fleet, then a Remotion intro/outro + ffmpeg mix. Same pipeline as VaultysHub's. →
packages/simulator Fleet simulator: thousands of real-VaultysId Actors — plus the people who own them — driven at a live control plane, on its own isolated stack. →

Read the full file on GitHub · 220 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. 15d ago Changed · +6 lines · +169 tokens per session 4b393b256c15
  2. 1mo ago Changed 52570595b236
  3. 1mo ago Changed · +1 lines · +35 tokens per session 5c8b2d756374
  4. 1mo ago Changed · +19 lines · +281 tokens per session f66d41bf46ee
  5. 1mo ago Changed · +41 lines · +280 tokens per session 51b2f035c2fc
  6. 2mo ago First seen · 153 lines · 2,839 tokens per session scan A 600e0d1251e1

Subscribe to this mod's changes

VaultysClaw CLAUDE.md is an instructions file published in the GitHub repository vaultys/VaultysClaw (84 stars, last pushed 2d ago), licensed MIT. It adds 3,604 tokens to every session, about $0.0144 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 2026-08-30.

Related

VaultysClaw CLAUDE.md compared with instructions from other repositories

VaultysClaw CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
VaultysClaw CLAUDE.mdvaultys/VaultysClawInstructions file842d agoMITA3,604Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode