VaultysClaw: Skill for Claude Code

.github/skills/add-ws-message/SKILL.md

add-ws-message is a skill for Claude Code from vaultys/VaultysClaw. It costs 74 tokens per session (1,336 once invoked), scanned A, original, MIT.

A procedure for adding a new message type to a WebSocket protocol, which lets a control system and its agents exchange commands, reports, and events.

In plain words
What is it for?
Use it to add new control commands, agent status reports, or two-way features such as synchronization, configuration, and notifications.
Why use it?
It prevents the shared message format, data fields, and handling code from getting out of sync when communication is extended.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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/.github/skills/add-ws-message/SKILL.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 add-ws-message

README.md
[![agentmods](https://agentmods.dev/badge/skills/vaultys/vaultysclaw/add-ws-message.svg)](https://agentmods.dev/skills/vaultys/vaultysclaw/add-ws-message)
Your own site
<a href="https://agentmods.dev/skills/vaultys/vaultysclaw/add-ws-message"><img src="https://agentmods.dev/badge/skills/vaultys/vaultysclaw/add-ws-message.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,336 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00074 $0.01336
Opus 5 $0.00037 $0.00668
Sonnet 5 $0.00015 $0.00267
Haiku 4.5 $0.00007 $0.00134

Measured 8d ago against content hash 94b9daea0bcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

add-ws-message 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (assets/message-template.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.github/skills/add-ws-message/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add WebSocket Message Type

When to Use

  • Adding a new command the control plane sends to agents
  • Adding a new report/event agents send back to the control plane
  • Extending the protocol for a new feature (sync, config, notifications, etc.)

Protocol Overview

WSMessage is a flat interface (not a discriminated union) — all messages share the same envelope:

{
  messageId: string;      // e.g. "memory-sync-1748700000000"
  type: WSMessageType;    // string literal from the union
  agentId?: string;       // sender's DID (set by the agent or control plane)
  payload: any;           // typed by convention via payload interface
  timestamp: string;      // ISO 8601
  signature?: string;     // ECDSA hex — only for critical messages
}

Procedure

1. Add the Type String to the Union

File: packages/shared/src/types.ts

Add your new type literal to the WSMessageType union:

export type WSMessageType =
  | ... existing types ...
  | "my_new_type";   // ← add here

2. Add the Payload Interface

In the same file (packages/shared/src/types.ts), add a typed payload interface:

export interface WSMyNewTypePayload {
  // required fields
  sourceId: string;
  // optional fields
  metadata?: Record<string, unknown>;
}

Naming convention: WS + PascalCase(type) + Payload (e.g. WSMemorySyncPayload).

3. Handle in the Control Plane (lib/ws-server.ts)

Direction: agent → control plane (agent sends, server receives):

Add a case to the switch (message.type) in handleMessage():

case "my_new_type":
  this.handleMyNewType(message);
  break;

Then implement the handler as a private method:

private handleMyNewType(message: WSMessage): void {
  const payload = message.payload as WSMyNewTypePayload;
  const agentId = message.agentId;
  // ... business logic ...
}

Direction: control plane → agent (server sends):

Add a public method to send the message:

Read the full file on GitHub · 183 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 183 lines · 74 tokens per session scan A 94b9daea0bcb

Subscribe to this mod's changes

add-ws-message is a skill published in the GitHub repository vaultys/VaultysClaw (77 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,336 once invoked, about $0.0004 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.

Related

Other skills, from other repositories