fan-manager-development

fan-manager-development is a skill for Claude Code, Codex from Knuckles-Team/fan-manager. It costs 39 tokens per session (1,258 once invoked), scanned A, original, MIT.

A development guide for the fan-manager connector, which reads computer temperature and controls fan speed through local hardware. It also covers its MCP tools, typed telemetry data, tests, and releases.

In plain words
What is it for?
Use it when modifying temperature readings, fan curves, fan-speed limits, MCP tools, telemetry ingestion, packaged skills, or release checks.
Why use it?
It gives coding agents the repository rules and boundaries they need to change hardware control safely without breaking the connector.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it when modifying temperature readings, fan curves, fan-speed limits, MCP tools, telemetry ingestion, packaged skills, or release checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/knuckles-team/fan-manager/fan-manager-development
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.

Any agent
npx skills add Knuckles-Team/fan-manager --skill fan-manager-development
Clone the repo
git clone --depth 1 https://github.com/Knuckles-Team/fan-manager

Made for: Claude Code, Codex.

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-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/knuckles-team/fan-manager/fan-manager-development/github.svg)](https://agentmods.dev/skills/knuckles-team/fan-manager/fan-manager-development)
Your own site
<a href="https://agentmods.dev/skills/knuckles-team/fan-manager/fan-manager-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/fan-manager/fan-manager-development/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 fan-manager-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/knuckles-team/fan-manager/fan-manager-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/fan-manager/fan-manager-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,258 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00039 $0.01258
Opus 5.5 $0.00016 $0.00503
Sonnet 5.5 $0.00008 $0.00252
Haiku 4.5 $0.00004 $0.00126

Measured today against content hash d35955e8e8cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fan-manager-development 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 today.

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.

fan_manager/skills/fan-manager-development/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fan Manager development

Use this skill from a fan-manager checkout before changing the connector. Read AGENTS.md first: it defines the local hardware boundary, worktree discipline, quality gates, version/lock policy, and release ownership.

Repository and runtime map

  • fan_manager/fan_manager.py owns the local sensors -j temperature path, bounded 0-100 fan writes, automatic fan curve, and the injected CommandRunner seam. Fixed argv with shell=False is the hardware boundary.
  • fan_manager/api_client.py is the thin Api facade over FanControlService; fan_manager/services/fan_control_service.py owns dependency-injected temperature and fan-control calls.
  • fan_manager/mcp_server.py builds the MCP surface. Domain registrars in fan_manager/mcp/mcp_temperature.py, fan_manager/mcp/mcp_fan_control.py, and fan_manager/mcp/mcp_kg.py expose one action-routed tool per domain through TOOL_REGISTRY.
  • fan_manager/connector_sources.py declares the live fan-sensors source; fan_manager/kg_ingest.py maps telemetry to typed ManagedHost, FanController, TemperatureReading, FanSpeedSetting, and SensorReading nodes through the SDK ingest stream.
  • Packaged content lives below fan_manager/skills/, prompts/, and ontology/. pyproject.toml must continue to include skills/** in setuptools package data.

Local and security contract

Fan Manager is a local hardware connector. fan_manager/auth.py returns the local Api facade and resolves only IPMITOOL_PATH and SENSORS_PATH; it does not accept a remote URL or credentials. Preserve this boundary when editing code or documentation.

The runtime may read FAN_MANAGER_HOST, FAN_MANAGER_HOSTS, FAN_MANAGER_NODE_API_BIND, FAN_MANAGER_NODE_API_PORT, FAN_MANAGER_NODE_API_TOKEN, FAN_MANAGER_NODE_URL_TEMPLATE, FAN_MANAGER_KG_INGEST, FAN_MANAGER_KG_AGGREGATE_S, FAN_MANAGER_POLICY_FILE, FAN_MANAGER_POLICY_REFRESH, FAN_MANAGER_CURVE, and FAN_MANAGER_NOTIFY_URL. Treat values as runtime configuration, never as secrets to embed in this skill. Keep node reads read-only and require one explicit out-of-band target for write operations. The MCP domains are gated by TEMPERATURETOOL, FAN_CONTROLTOOL, and KGTOOL; preserve the inherited MCP_TOOL_MODE surface and the existing agent_connector_sdk registration path.

Read the full file on GitHub · 109 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. today First seen · 109 lines · 39 tokens per session scan A d35955e8e8cc

Subscribe to this mod's changes

fan-manager-development is a skill published in the GitHub repository Knuckles-Team/fan-manager (2 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,258 once invoked, about $0.0002 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 2026-10-27.

Related

Other skills, from other repositories

unifi-protect

How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…

sirkirby/unifi-mcp · 112 tokens

unifi-access

How to manage UniFi Access door control — locks, credentials, visitors, access policies, and events. Use this skill when the user mentions UniFi Access, door locks, door access, building access, NFC cards, PIN codes, visitor passes, access policies, access schedules, door readers, or any UniFi Access task.

sirkirby/unifi-mcp · 70 tokens

network-health-check

Run a UniFi network health check — diagnose device status, connectivity issues, firmware updates, and system health. Use when asked to check network health, find what's down, diagnose connectivity issues, or get a network status summary.

sirkirby/unifi-mcp · 49 tokens

scienceworld-circuit-builder

This skill constructs a simple electrical circuit by connecting components like batteries, wires, and light bulbs. Use when the agent needs to test electrical conductivity or create a functional circuit for an experiment. The input is a set of available components, and the output is a fully connected circuit ready for…

zjunlp/SkillNet · 64 tokens

browser-609362ee

A Web Bluetooth skill for discovering nearby Bluetooth devices and connecting to them from a browser. Bluetooth is a short-range wireless connection used by devices such as sensors and accessories.

FuRongJun-1999/dsh-memory · 66 tokens

qmclaw-workbench

A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.

xi-zhao/OpenQuantum · 124 tokens