climate-airflow-direction

climate-airflow-direction is a skill for Claude Code, Codex from Darwin-Agent/Car-bench-TRACE. It costs 103 tokens per session (2,040 once invoked), scanned C, a copy of hexagonal-architecture, MIT.

A climate-control skill for setting where a vehicle’s fan blows air, such as the feet, face, windshield, or a combination. It can also use the driver’s stored preferred direction when the request is unspecified.

In plain words
What is it for?
Use it to redirect cabin air to named areas or the stored preferred direction, and to read the current climate settings before reporting the result.
Why use it?
It handles both explicit directions and vague requests like changing the airflow, while checking the saved preference when the user refers to their usual setting.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to redirect cabin air to named areas or the stored preferred direction, and to read the current climate settings before reporting the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/darwin-agent/car-bench-trace/climate-airflow-direction
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 Darwin-Agent/Car-bench-TRACE --skill climate-airflow-direction
Clone the repo
git clone --depth 1 https://github.com/Darwin-Agent/Car-bench-TRACE

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 climate-airflow-direction

README.md
[![agentmods](https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/climate-airflow-direction/github.svg)](https://agentmods.dev/skills/darwin-agent/car-bench-trace/climate-airflow-direction)
Your own site
<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/climate-airflow-direction"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/climate-airflow-direction/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 climate-airflow-direction

Your own site · 80×15
<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/climate-airflow-direction"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/climate-airflow-direction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 78% copy Near-identical to another mod 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 $0.00103 $0.02040
Opus 5 $0.00051 $0.01020
Sonnet 5 $0.00021 $0.00408
Haiku 4.5 $0.00010 $0.00204

Measured 9d ago against content hash 54ce36483abe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

climate-airflow-direction scanned grade C 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 9d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

- **A co-requested control is missing while airflow is doable.** When one message bundles the airflow change with another climate change (e.g. "point it at my feet and turn the fan up") and only the *other* control is un
Origin

This is a copy

78% identical to hexagonal-architecture — 338 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills_bank/climate-airflow-direction/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set the fan airflow direction

Redirect where the cabin air blows. The direction may be named outright (a single target such as feet, head, or windshield, or a compound combination), left unnamed (a bare "change the direction", or a complaint about the current direction with no replacement named), or pointed at the user's stored preference. Sometimes the control is missing. The same method handles all of these.

When this applies

"Point the air at my feet / the windshield", "blow toward the feet and the windshield", "change the fan airflow direction", "the air's blowing at my face and I don't like it — change it", "point the air the way I like it / my usual direction". (Setting fan speed is climate-fan-speed; turning AC on is climate-air-conditioning; setting the circulation mode is climate-air-circulation.)

Tools

  • get_climate_settings({}) — read the current airflow direction (and the rest of the climate state); use to report state or confirm what changed.
  • get_user_preferences({}) — read the user's liked airflow direction when the request points to a preference ("the direction I like", "my usual"). The preference MAY be a compound direction.
  • set_fan_airflow_direction({direction}) — set the airflow direction; the vocabulary covers single targets and compound combinations (e.g. one that bundles the footwell with the windshield). Use exactly the direction named/preferred. MAY be missing.

Method

  1. Direction named → set it exactly. When the user names one — including a compound combination — set that exact value, not a different single target or a different combination. No preference read needed.
  2. Direction NOT named → read the stored preference FIRST, before asking. Whenever the new direction is unnamed — a bare "just change it", or a complaint about the current direction ("the air's at my face, I don't like it, change it") with no replacement named — call get_user_preferences({vehicle_settings:{climate_control}}) before deciding. If it pins a liked airflow direction, set that (proposing it for a quick confirm is fine). When the preference is compound, set the compound value — the simpler single-target value is a silent wrong answer.
  3. Only ask the user if no preference resolves it. If the preference read returns nothing about airflow direction, then the choice is genuinely the user's — ask which direction and offer the valid options, and set the value the user supplies.
  4. Confirm what changed and stop.

Read the full file on GitHub · 65 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. 9d ago First seen · 65 lines · 103 tokens per session scan C 54ce36483abe

Subscribe to this mod's changes

climate-airflow-direction is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (8 stars, last pushed 6d ago), licensed MIT. It adds 103 tokens to every session and 2,040 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). It is 78% identical to hexagonal-architecture, differing in 338 lines, and is treated as a copy.

Related

Other skills, from other repositories

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

hsb-flash

Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…

NVIDIA/skills · 94 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens