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/subnetangel/toolmux/claude-mdgit clone --depth 1 https://github.com/subnetangel/ToolMuxWrote 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/subnetangel/toolmux/claude-md)<a href="https://agentmods.dev/instructions/subnetangel/toolmux/claude-md"><img src="https://agentmods.dev/badge/instructions/subnetangel/toolmux/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 | $0.02253 | $0.02253 |
| Opus 5 | $0.01126 | $0.01126 |
| Sonnet 5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
ToolMux 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 3d 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.
- **Transport abstraction**: `HttpMcpClient` instances and `subprocess.Popen` instances are both stored in `self.server_processes` and differentiated via `isinstance()` checks. How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - ToolMux
Project Overview
ToolMux is an MCP (Model Context Protocol) server aggregation tool that achieves ~98.65% token reduction by exposing 4 meta-tools instead of loading hundreds of individual tool schemas upfront. It supports both stdio and HTTP/SSE transports.
- Version: 2.3.0
- License: MIT
- Python: 3.10+
- PyPI: https://pypi.org/project/toolmux/
Repository Structure
ToolMux/
├── toolmux/ # Main Python package
│ ├── __init__.py # Package init, exports main/ToolMux/HttpMcpClient
│ ├── main.py # Core implementation (~684 lines, single module)
│ ├── Prompt/ # Agent instructions bundled with package
│ │ └── AGENT_INSTRUCTIONS.md
│ ├── examples/ # 11 JSON config templates (bundled with package)
│ └── scripts/ # Helper scripts (toolmux_hook.sh)
├── tests/ # pytest test suite (8 modules)
│ ├── test_simple.py # Basic functionality
│ ├── test_http_transport.py # HTTP/SSE transport
│ ├── test_http_mcp.py # HTTP MCP protocol
│ ├── test_http_server.py # Mock HTTP server for testing
│ ├── test_mcp_protocol.py # MCP protocol compliance
│ ├── test_e2e.py # End-to-end integration
│ ├── test_e2e_simple.py # Simplified E2E
│ └── test_e2e_pypi.py # PyPI installation E2E
├── docs/ # Extended documentation
│ ├── ARCHITECTURE.md # Detailed architecture (~53KB)
│ ├── DEPLOYMENT_PLAN.md # Deployment strategy
│ ├── FIX_SUMMARY.md # Bug fix summaries
│ ├── GIT_COMMIT_CHECKLIST.md # Pre-commit checklist
│ └── PUBLICATION_REPORT.md # PyPI publication details
├── pyproject.toml # Project metadata (setuptools build)
├── requirements.txt # Runtime dependencies
├── Makefile # Build/test/lint commands
├── mcp.json # Default server configuration
├── CHANGELOG.md # Version history
├── AGENT_INSTRUCTIONS.md # Agent integration guide
├── setup.sh / install.sh # Shell-based setup scripts
└── README.md # Main documentation
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.
- 3d ago First seen · 181 lines · 2,253 tokens per session scan A e64d24a07adc
ToolMux CLAUDE.md is an instructions file published in the GitHub repository subnetangel/ToolMux (8 stars, last pushed 2mo ago), licensed MIT. It adds 2,253 tokens to every session, about $0.0113 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 2026-09-01.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.