claude-senator-mcp: Instructions file for Claude Code

CLAUDE.md

claude-senator-mcp CLAUDE.md is an instructions file for Claude Code from Vvkmnn/claude-senator-mcp. It costs 764 tokens per session, scanned A, original, MIT.

Architecture notes for Claude Senator, a tool that lets multiple Claude Code sessions communicate through files in a temporary directory. JSONL is a line-by-line text format commonly used for messages and logs.

In plain words
What is it for?
Use them when developing or maintaining Claude Senator, troubleshooting its file-based communication, or considering whether its storage design should change.
Why use it?
They explain how sessions discover one another, exchange messages, and inject commands without requiring a separate database or service. They also document the expected performance limits of the current design.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Vvkmnn/claude-senator-mcp's own configuration. It tells Claude Code how to work on claude-senator-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 claude-senator-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Vvkmnn/claude-senator-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/Vvkmnn/claude-senator-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Vvkmnn/claude-senator-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 claude-senator-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vvkmnn/claude-senator-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vvkmnn/claude-senator-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 764 This file is loaded in full into every session.
When invoked 764 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.00764 $0.00764
Opus 5 $0.00382 $0.00382
Sonnet 5 $0.00153 $0.00153
Haiku 4.5 $0.00076 $0.00076

Measured 10d ago against content hash fa2eea3f5e70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude-senator-mcp CLAUDE.md scanned grade A with 1 finding 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 10d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Zero dependencies**: Only Node.js built-ins (fs, path, os, child_process)
CLAUDE.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Senator Architecture Notes

Current Implementation: Directory-Based IPC

Claude Senator uses a minimal, zero-dependency file-based approach for inter-Claude communication:

Architecture

/tmp/claude-senator/
├── instances/          # Each Claude writes {pid}.json with status/info
├── messages/           # Individual message files in JSONL format  
└── commands/           # Command injection files for input manipulation

Benefits

  • Zero dependencies: Only Node.js built-ins (fs, path, os, child_process)
  • No concurrency conflicts: Each Claude owns its files (no shared writes)
  • JSONL format preserved: Native Claude messaging format
  • Auto-cleanup: Files removed when Claude instances exit
  • Cross-platform: Works on any Unix-like system with /tmp

Performance Characteristics

  • 2-20 Claudes: Excellent performance, <10ms operations
  • 20-100 Claudes: Good performance, minimal filesystem overhead
  • 100+ Claudes: May benefit from SQLite upgrade (see below)

Current Status

  • ✅ Directory structure and session management implemented
  • ✅ Message passing via individual JSONL files
  • ✅ Instance discovery via process filtering + file registry
  • ✅ Automatic cleanup of dead instances and old messages
  • 🔧 Testing inter-Claude communication in progress

Future Consideration: SQLite Upgrade

If directory-based approach hits performance limits, upgrade to SQLite with better-sqlite3:

When to Consider SQLite

  • Message delivery >1 second due to filesystem overhead
  • Complex querying needs (message history, advanced routing)
  • Transaction safety requirements for message delivery
  • Scaling beyond 100+ concurrent Claude instances

SQLite Benefits

  • Performance: 2000+ queries/second, excellent concurrency
  • ACID transactions: Guaranteed message delivery, no corruption
  • Native JSONL support: Built-in JSON functions for Claude messages
  • Mature technology: Battle-tested, widely used

Implementation Plan

npm install better-sqlite3  # Single dependency

Read the full file on GitHub · 94 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. 10d ago First seen · 94 lines · 764 tokens per session scan A fa2eea3f5e70

Subscribe to this mod's changes

claude-senator-mcp CLAUDE.md is an instructions file published in the GitHub repository Vvkmnn/claude-senator-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 764 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens