Borrowing it
Nothing to install: this file belongs to artem-sedykh/mini-humidifier. 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/artem-sedykh/mini-humidifier/master/AGENTS.mdgit clone --depth 1 https://github.com/artem-sedykh/mini-humidifierWrote 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/artem-sedykh/mini-humidifier/agents-md)<a href="https://agentmods.dev/instructions/artem-sedykh/mini-humidifier/agents-md"><img src="https://agentmods.dev/badge/instructions/artem-sedykh/mini-humidifier/agents-md.svg" alt="Measured on agentmods" 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 | $0.12419 | $0.12419 |
| Opus 5 | $0.06209 | $0.06209 |
| Sonnet 5 | $0.02484 | $0.02484 |
| Haiku 4.5 | $0.01242 | $0.01242 |
Grade A, and why
mini-humidifier 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 — 929 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working on this repository. Human contributors are welcome to read it too - it is the short version of how this card is put together and what breaks it.
What this is
mini-humidifier is a custom Lovelace card for Home Assistant: a single
JavaScript bundle that Home Assistant loads in the browser. There is no server
side, no Python, and no Home Assistant integration in this repository. The card
reads entity state out of the hass object and calls Home Assistant services
back.
Distribution is HACS: users get mini-humidifier-bundle.js as a release asset,
so the release asset is the product. A change is not shipped until it is in
a tagged release.
The bundled models are presets, not the product
What this card is, is a kit: every control can be described in YAML - which
indicators exist and what each one reads, which buttons appear, what icon each
takes, what service each one calls, when each is disabled.
src/configurations/ holds a dozen devices; the market has hundreds, and the
card is built this way so that a humidifier nobody here has heard of can go on a
dashboard without a pull request and without waiting for one.
That is a constraint on what may be changed, not just a description of what is:
- A
model:the registry does not know is supported. It starts from the default configuration and warns in the console. Do not turn it into an error. #112 is a complete configuration for adeerma.humidifier.jsq2w- written by a user, posted with a screenshot, copied since - and refusing unknown ids would break it and every card copied from it. - The configuration is open at the leaves. Indicator and button ids are chosen by the user, and their options are templates the user wrote. Anything that validates a configuration (#178) or edits one (#179) has to carry through what it does not recognise rather than dropping it. An editor that round-trips a hand-written card through a form and silently loses the half it does not model is worse than no editor.
- Those templates are source text, not functions. That is what forces several of the build constraints below - see "Why the model configurations stay JavaScript".
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 Changed · +15 lines · +268 tokens per session 3fe54dc96e5c
- 8d ago First seen · 914 lines · 12,151 tokens per session scan A 2be0f59a8e51
mini-humidifier AGENTS.md is an instructions file published in the GitHub repository artem-sedykh/mini-humidifier (161 stars, last pushed 6d ago), licensed MIT. It adds 12,419 tokens to every session, about $0.0621 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 2026-08-30.
Other instructions, from other repositories
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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.