Borrowing it
Nothing to install: this file belongs to MAB2908/zont-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.
curl -O https://raw.githubusercontent.com/MAB2908/zont-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/MAB2908/zont-mcpWrote 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/mab2908/zont-mcp/agents-md)<a href="https://agentmods.dev/instructions/mab2908/zont-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mab2908/zont-mcp/agents-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.
<a href="https://agentmods.dev/instructions/mab2908/zont-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mab2908/zont-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02249 | $0.02249 |
| Opus 5.5 | $0.00900 | $0.00900 |
| Sonnet 5.5 | $0.00450 | $0.00450 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
zont-mcp AGENTS.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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Working Guide for AI Agents
This document is written for AI models and autonomous agents that operate the
zont-mcp MCP server — either by installing and configuring it, or by using its
tools at runtime. Human-oriented documentation: README.md.
1. What you are operating
zont-mcp is a local MCP (Model Context Protocol) server exposing 38 tools for the
ZONT heating ecosystem (BAXI Connect+ and compatible controllers) through the official
ZONT cloud API. It controls real heating equipment in a real home. Treat every write
tool as a physical-world action: switching modes changes the boiler's behaviour.
Tool groups: devices & state (5), heating control (6), I/O & guard (6), history & events (6), analytics (3), configuration (6), commands & archives (6).
2. Installation (if you are setting it up)
git clone https://github.com/MAB2908/zont-mcp.git
cd zont-mcp
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e .
Requires Python 3.11+. After installation the zont-mcp console command exists;
python src/server.py is equivalent.
3. Configuration (if you are setting it up)
Credentials come only from environment variables or a .env file in the project
root (template: .env.example). Required values:
| Variable | Meaning |
|---|---|
ZONT_CLIENT_EMAIL |
ZONT account email — required |
ZONT_TOKEN |
permanent API token — preferred |
ZONT_LOGIN / ZONT_PASSWORD |
only for one-time token retrieval |
ZONT_DEVICES_CACHE_TTL |
optional, device-list cache seconds (default 30) |
Token retrieval flow: set login+password, leave token empty, start the server once —
the token is printed to stderr; persist it as ZONT_TOKEN, then remove the password.
The server exits immediately with a stderr explanation if credentials are missing or
invalid. Client connection snippets (Claude Desktop, Claude Code, Cursor, VS Code):
see README.md.
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 · 185 lines · 2,249 tokens per session scan A 9b68cd37e7f4
zont-mcp AGENTS.md is an instructions file published in the GitHub repository MAB2908/zont-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 2,249 tokens to every session, about $0.0090 per session on Opus 5.5. 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 2026-11-06.
zont-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zont-mcp AGENTS.mdMAB2908/zont-mcp | Instructions file | 1 | 5d ago | MIT | A | 2,249 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |