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/owretch/zencontrol-cloud-mcp/agents-mdgit clone --depth 1 https://github.com/oWretch/zencontrol-cloud-mcpWhat 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 | $0.01081 | $0.01081 |
| Opus 5 | $0.00541 | $0.00541 |
| Sonnet 5 | $0.00216 | $0.00216 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
zencontrol-cloud-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 yesterday.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — zencontrol-cloud-mcp
This is an MCP (Model Context Protocol) server that lets AI assistants control ZenControl DALI-2 lighting systems. Keep these conventions in mind when working on the codebase.
Language & Runtime
- Python 3.11+, async-first (
async defeverywhere,httpx.AsyncClient). - Package manager: uv. Run tools with
uv run. - Entry point:
src/zencontrol_cloud_mcp/server.py→main().
Key Libraries
| Library | Purpose |
|---|---|
fastmcp |
MCP server framework (tools, lifespan, transports) |
httpx |
Async HTTP client for ZenControl Cloud REST API |
pydantic |
Data models / schemas for all API types |
cryptography |
Fernet encryption for stored OAuth tokens |
platformdirs |
Cross-platform token storage paths |
File Organisation
src/zencontrol_cloud_mcp/
server.py — FastMCP server, lifespan, CLI
tools/ — MCP tool definitions (one file per domain)
api/ — HTTP client (client.py) and domain methods (rest.py)
models/ — Pydantic schemas (schemas.py)
auth/ — OAuth flow, token storage, proxy server
Naming Conventions
- Functions / tools:
snake_case(e.g.,list_sites,control_light). - Pydantic models:
PascalCase(e.g.,SiteDetails,GroupSummary). - Files:
snake_case.py, one module per logical domain.
Tool Design Patterns
Scope-parameterised tools
Tools that list entities (groups, devices) accept scope_type and scope_id
instead of having separate tools per scope. Example:
@mcp.tool()
async def list_groups(
ctx: Context,
scope_type: Literal["site", "floor", "map", "gateway"],
scope_id: str,
) -> str: ...
Accessing the API
All tools get the API client from the MCP lifespan context:
api: ZenControlAPI = ctx.lifespan_context["api"]
Never construct ZenControlAPI or ZenControlClient inside a tool.
Return values
Tools return formatted strings (not raw JSON), because the output is consumed by an LLM. Use bullet lists, tables, or short paragraphs.
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.
- yesterday First seen · 119 lines · 1,081 tokens per session scan A 9624a331b1a2
zencontrol-cloud-mcp AGENTS.md is an instructions file published in the GitHub repository oWretch/zencontrol-cloud-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,081 tokens to every session, about $0.0054 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 2026-08-31.
Other instructions, from other repositories
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.
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).
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.