fan-manager AGENTS.md

fan-manager AGENTS.md is an instructions file for Codex, OpenCode from Knuckles-Team/fan-manager. It costs 3,892 tokens per session, scanned A, original, MIT.

Project instructions for Fan Manager, a small Python tool for controlling Dell PowerEdge server fans and checking temperatures. It uses IPMI, a server-management interface, and local sensor tools to communicate with hardware.

In plain words
What is it for?
They are for working on fan and temperature control, server power and sensor operations, BMC management, asynchronous tools, and tests or commands in the repository.
Why use it?
They define the project's architecture, supported control paths, credential handling, and exact commands, helping changes fit the tool's intentionally simple design.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/knuckles-team/fan-manager/agents-md
Clone the repo
git clone --depth 1 https://github.com/Knuckles-Team/fan-manager

Made for: Codex, OpenCode.

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 fan-manager AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/knuckles-team/fan-manager/agents-md.svg)](https://agentmods.dev/instructions/knuckles-team/fan-manager/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/knuckles-team/fan-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/knuckles-team/fan-manager/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,892 This file is loaded in full into every session.
When invoked 3,892 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03892 $0.03892
Opus 5 $0.01946 $0.01946
Sonnet 5 $0.00778 $0.00778
Haiku 4.5 $0.00389 $0.00389

Measured 3d ago against content hash e0e95b7b2437, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fan-manager 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 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.

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.

AGENTS.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Claude Code loads this file via CLAUDE.md (@AGENTS.md import) — the two stay in sync. Edit this file, not CLAUDE.md.

Tech Stack & Architecture

  • Language/Version: Python 3.11+
  • Core Libraries: agent-utilities, fastmcp (via agent-utilities[mcp]), pydantic-ai
  • Domain: Dell PowerEdge / IPMI 2.0 control via ipmitool + lm-sensors. Thermal (fan/temperature) runs local with no creds; the IPMI/BMC wrapper (CONCEPT:FM-OS.governance.power-chassis..008: power, sensors, SEL, SoL, BMC LAN/user config, raw) runs in-band (local /dev/ipmi0) or out-of-band over LAN (-I lanplus -H -U -P, creds from OpenBao apps/idrac).
  • Key principles: Functional patterns, Pydantic for data validation, asynchronous tool execution, action-routed MCP tools.

Architecture & Deliberate Simplicity

Fan Manager is a small local tool, so it deliberately avoids a full domain/adapter/port hexagonal split — that would be over-engineering for a two-concept package. The design makes exactly the highest-value seam instead:

  • Adapter seam (DI): CommandRunner (a Protocol in fan_manager.fan_manager) abstracts the sensors/ipmitool shell-out; SubprocessCommandRunner is the production implementation. Tests inject a fake runner rather than monkeypatching subprocess globally.
  • Service layer (DI): fan_manager/services/FanControlService composes the injected CommandRunner + runtime config and exposes the temperature (CONCEPT:FM-OS.governance.service-reads-temperature-through) and fan-control (CONCEPT:FM-OS.governance.service-writes-fan-level) operations. The Api facade composes this service.
  • Model layer: fan_manager/models.py holds the Pydantic envelopes.

Anything beyond this (separate domain/, ports/, adapters/ packages) is intentionally not added — it would add indirection without value at this size.

Architecture Diagram

graph TD
    User([User/A2A]) --> Agent[Pydantic AI Agent]
    Agent --> MCP[MCP Server / FastMCP]
    MCP --> Temp[temperature tool — CONCEPT:FM-OS.governance.service-reads-temperature-through]
    MCP --> Fan[fan-control tool — CONCEPT:FM-OS.governance.service-writes-fan-level]
    MCP --> Ipmi[ipmi tools — CONCEPT:FM-OS.governance.power-chassis..008]
    Temp --> Service[FanControlService - DI]
    Fan --> Service
    Service --> Runner[CommandRunner adapter]
    Ipmi --> Runner
    Runner --> Sensors([lm-sensors])
    Runner --> IPMI([BMC via ipmitool: in-band /dev/ipmi0 or lanplus])

Read the full file on GitHub · 303 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. 3d ago First seen · 303 lines · 3,892 tokens per session scan A e0e95b7b2437

Subscribe to this mod's changes

fan-manager AGENTS.md is an instructions file published in the GitHub repository Knuckles-Team/fan-manager (2 stars, last pushed 6d ago), licensed MIT. It adds 3,892 tokens to every session, about $0.0195 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.