openmm-mcp: Skill for Claude Code

.claude/skills/vault-ipc/SKILL.md

vault-ipc is a skill for Claude Code from QBT-Labs/openmm-mcp. It costs 0 tokens per session (286 once invoked), scanned A, original, MIT.

A Unix socket service that lets local programs request payment signatures or exchange credentials from an unlocked vault through JSON messages.

In plain words
What is it for?
Use it for local wallet signing, retrieving credentials for supported exchanges, checking vault status, and communicating securely with the vault service.
Why use it?
It replaces separate sockets and keeps sensitive vault data out of long-running client processes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is QBT-Labs/openmm-mcp's own configuration. It tells Claude Code how to work on openmm-mcp 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 openmm-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to QBT-Labs/openmm-mcp. 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/QBT-Labs/openmm-mcp/main/.claude/skills/vault-ipc/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/QBT-Labs/openmm-mcp

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 vault-ipc

README.md
[![agentmods](https://agentmods.dev/badge/skills/qbt-labs/openmm-mcp/vault-ipc/github.svg)](https://agentmods.dev/skills/qbt-labs/openmm-mcp/vault-ipc)
Your own site
<a href="https://agentmods.dev/skills/qbt-labs/openmm-mcp/vault-ipc"><img src="https://agentmods.dev/badge/skills/qbt-labs/openmm-mcp/vault-ipc/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 vault-ipc

Your own site · 80×15
<a href="https://agentmods.dev/skills/qbt-labs/openmm-mcp/vault-ipc"><img src="https://agentmods.dev/badge/skills/qbt-labs/openmm-mcp/vault-ipc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 286 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.
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 $0.00000 $0.00286
Opus 5 $0.00000 $0.00143
Sonnet 5 $0.00000 $0.00057
Haiku 4.5 $0.00000 $0.00029

Measured 11d ago against content hash bd23520dfac6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vault-ipc 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 11d 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/skills/vault-ipc/SKILL.md · 32 lines

What it actually says

Vault IPC Socket

Unified Unix socket replacing the old two-socket model (x402-signer.sock + openmm-creds.sock).

Socket

  • Path: /tmp/openmm.sock (override via OPENMM_SOCKET env var)
  • Permissions: mode 0600 (owner-only)
  • Started by: openmm serve after interactive vault unlock

Message Protocol

JSON messages over the socket, dispatched by type:

{ "type": "sign_payment", "payload": {} }
→ { "signature": "0x..." }

{ "type": "get_credentials", "exchange": "mexc" }
→ { "apiKey": "...", "secret": "..." }

{ "type": "ping" }
→ { "status": "ok", "wallet": "0x...", "exchanges": ["mexc", "gateio"] }

signAndWipe Pattern

Private key is decrypted inline, used once, and goes out of scope immediately. It is NEVER held in a long-lived variable.

Security Invariants

  • Password typed once interactively in terminal — never passed as flag or env var
  • Socket file = proof of authentication (exists → vault is unlocked)
  • Stale socket cleaned up on startup, deleted on shutdown
  • MCP server connects via socket — does NOT hold vault data in its own memory
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. 11d ago First seen · 32 lines · 0 tokens per session scan A bd23520dfac6

Subscribe to this mod's changes

vault-ipc is a skill published in the GitHub repository QBT-Labs/openmm-mcp (3 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 286 tokens. 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 2026-08-31.