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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/vaultys/vaultysclaw/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/vaultys/vaultysclaw/copilot-instructions.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 | $0.01402 | $0.01402 |
| Opus 5 | $0.00701 | $0.00701 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
VaultysClaw copilot-instructions.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 4d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VaultysClaw — Agent Instructions
Decentralized AI agent orchestration platform. Monorepo (pnpm workspaces + Turborepo) with three packages:
packages/shared— core types, security utils, channel protocolpackages/control-plane— Next.js App Router dashboard + WebSocket server (port 3000 / WS 8080)packages/agent-controller— agent runtime CLI, tools, skills, memory
See CLAUDE.md for the full architecture overview.
Build & Test
pnpm install
pnpm build # All packages (shared must build first — handled by Turborepo)
pnpm dev # All packages dev mode
pnpm vaultysclaw:dev # Control plane only
pnpm dev -F @vaultysclaw/agent-controller
pnpm test # Vitest, no watch (default config)
pnpm type-check
pnpm lint
Single test file: pnpm vitest run __tests__/channels.test.ts
See docs/QUICK_START.md for setup and docs/DEVELOPMENT.md for full dev workflow.
Key Architecture Decisions
- ORM: Prisma with PostgreSQL. All DAOs live in
packages/control-plane/db/and use the Prisma client (db/client.ts). Schema inprisma/schema.prisma, migrations inprisma/migrations/. Never use raw SQL in route handlers — use the appropriate DAO. - Auth: Passwordless (VaultysId ECDSA challenge-response) via NextAuth. Each route handler calls
getAuthContext()from@/lib/auth-utils— no middleware file. - WebSocket protocol: All messages are typed envelopes from
packages/shared/src/channel-types.ts. Critical messages (policies, intents) carry ECDSA signatures verified before processing. @/*alias: Only works inpackages/control-plane(Next.js). Agent-controller uses relative imports.- Skills are pre-compiled JS: Skills discovered at runtime must be
.js/.mjsfiles, not.ts. - Agent-controller SQLite: The agent-controller keeps its own local SQLite (
agent.db) for identity, sessions, and memory — this is separate from the control plane's PostgreSQL.
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.
- 4d ago First seen · 96 lines · 1,402 tokens per session scan A ccd873afdefd
VaultysClaw copilot-instructions.md is an instructions file published in the GitHub repository vaultys/VaultysClaw (77 stars, last pushed 8d ago), licensed MIT. It adds 1,402 tokens to every session, about $0.0070 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
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
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
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).
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.
bitcoin-mcp copilot-instructions.md
Instructions for Bortlesboat/bitcoin-mcp, covering bitcoin-mcp copilot instructions, rules, satoshi api reference and verification.