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.
npx agentmods add instructions/vaultys/vaultysclaw/claude-mdgit clone --depth 1 https://github.com/vaultys/VaultysClawWrote 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/vaultys/vaultysclaw/claude-md)<a href="https://agentmods.dev/instructions/vaultys/vaultysclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/vaultys/vaultysclaw/claude-md.svg" alt="Measured on agentmods" 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 | $0.02839 | $0.02839 |
| Opus 5 | $0.01419 | $0.01419 |
| Sonnet 5 | $0.00568 | $0.00568 |
| Haiku 4.5 | $0.00284 | $0.00284 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 153 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 a decentralized AI agent orchestration platform. A central control plane (Next.js + WebSocket server) manages lightweight agent controllers that connect via WebSocket, execute LLM-driven intents using tools, and maintain cryptographic identity via VaultysId.
Monorepo: pnpm workspaces + Turborepo. Main packages:
| Package | Description | CLAUDE.md |
|---|---|---|
packages/shared |
Types, security utils, channel protocol definitions | → |
packages/policy |
Policy engine: capability/resource-limit types, cert signing/verification, runtime enforcement gates | → |
packages/control-plane |
Next.js App Router dashboard + WebSocket server (port 3000 / WS 8080) | → |
packages/control-plane/app/api |
REST API routes (ts-rest pattern) | → |
packages/agent-controller |
Agent runtime CLI, tools, skills, memory | → |
packages/mcp-gateway |
MCP server exposing VaultysClaw agents as tools | → |
packages/notifier |
Standalone worker: consumes notification events from BullMQ and delivers email / in-app / push (SSE) | → |
packages/webhook-dispatcher |
Standalone worker: consumes webhook events from BullMQ, signs them (HMAC) and POSTs to configured endpoints | → |
Commands
# Development
pnpm install
pnpm dev # Start all packages (control plane + agent)
pnpm vaultysclaw:dev # Control plane only (preferred alias)
pnpm agent:dev # Agent controller only (headless)
pnpm agent:web # Agent controller with web UI (port 3002)
pnpm agent:tui # Agent controller with Ink TUI
pnpm mcp:dev # MCP gateway (stdio, reads VC_CONTROL_PLANE_URL + VC_API_KEY)
pnpm notifier:dev # Notifier worker (reads DATABASE_URL + REDIS_URL; needs Redis running)
pnpm webhook:dev # Webhook dispatcher worker (reads DATABASE_URL + REDIS_URL; needs Redis running)
pnpm mcp:build # Build MCP gateway to dist/
# Demo / Simulator
pnpm simulator:up # Full demo stack: PostgreSQL + MinIO + Docling + LiteLLM + Grafana + 30 agents
pnpm simulator:seed # Seed DB (8 workspaces, 200+ users, 30 agents, 15 workflows) — idempotent
pnpm simulator:start # Connect 30 simulated agents (control plane must be running)
pnpm simulator:full # seed + start
./demo/setup.sh # Minimal demo: 3 real agents for recording / quick exploration
# Build
pnpm build # All packages via Turborepo
pnpm agent:build:binaries # Build standalone agent CLI binaries
# Testing
pnpm test # Run all tests (Vitest, no watch)
pnpm test:ui # Vitest interactive UI
pnpm test:docker # Docker integration tests
pnpm test:litellm # LiteLLM integration tests
pnpm vitest run __tests__/channels.test.ts # Single test file
# Code quality
pnpm lint
pnpm type-check
pnpm format
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.
- 5d ago First seen · 153 lines · 2,839 tokens per session scan A 600e0d1251e1
VaultysClaw CLAUDE.md is an instructions file published in the GitHub repository vaultys/VaultysClaw (77 stars, last pushed 3d ago), licensed MIT. It adds 2,839 tokens to every session, about $0.0142 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 2026-08-30.
Other instructions, from other repositories
open-ace CLAUDE.md
Claude Code instructions for open-ace/open-ace, covering claude.md, where process documents go, pushing, test placement and ci semantics and schema snapshots (schema-sync ci).
comis CLAUDE.md
Claude Code instructions for comisai/comis, covering claude.md, generic runtime check — before every code change, tests-first, docs-current and root-cause before patching.
comis AGENTS.md
AGENTS.md instructions for comisai/comis, covering agents.md — comis engineering protocol, 1) architecture, package map, 1.1 generic agent runtime invariant and 2) engineering principles (normative).
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
agentgram CLAUDE.md
Claude Code instructions for agentgram/agentgram, covering claude.md — agentgram development guide, project overview, tech stack, monorepo structure and core architecture patterns.
experiencer CLAUDE.md
Claude Code instructions for vincentlaucsb/experiencer: The canonical repository instructions are in AGENTS.md. Read and follow that file; this compatibility entrypoint intentionally defines no independent rules.