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/bradsjm/hassio-addons/agents-mdgit clone --depth 1 https://github.com/bradsjm/hassio-addonsWrote 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/bradsjm/hassio-addons/agents-md)<a href="https://agentmods.dev/instructions/bradsjm/hassio-addons/agents-md"><img src="https://agentmods.dev/badge/instructions/bradsjm/hassio-addons/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 | $0.01543 | $0.01543 |
| Opus 5 | $0.00772 | $0.00772 |
| Sonnet 5 | $0.00309 | $0.00309 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
hassio-addons AGENTS.md scanned grade A 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Prefer existing tools: `curl`, `jq`, `tar`, `gzip`. How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository contains Home Assistant add-ons for Hyperion.NG, OpenCode, and OpenChamber. Use this file as the primary guide for agentic coding work here.
Repo Overview
- Add-on paths:
addon-hyperion-ng/,addon-opencode/,addon-openchamber/ - Core metadata:
repository.json - Hyperion config:
addon-hyperion-ng/config.yaml - Hyperion container definition:
addon-hyperion-ng/Dockerfile - Hyperion runtime entrypoint:
addon-hyperion-ng/run.sh - OpenCode config:
addon-opencode/config.yaml - OpenCode build metadata:
addon-opencode/build.yaml - OpenCode container definition:
addon-opencode/Dockerfile - OpenCode runtime entrypoint:
addon-opencode/rootfs/etc/services.d/opencode/run - OpenChamber config:
addon-openchamber/config.yaml - OpenChamber build metadata:
addon-openchamber/build.yaml - OpenChamber container definition:
addon-openchamber/Dockerfile - OpenChamber runtime entrypoint:
addon-openchamber/rootfs/etc/services.d/openchamber/run - Helper scripts:
addon-hyperion-ng/download-hyperion.sh,.github/scripts/*
Build / Lint / Test Commands
There are no explicit lint or test frameworks in this repo. Use the scripts below for validation and smoke testing.
Build (local or CI-like)
-
Build the Hyperion image for amd64:
docker buildx build --pull --platform linux/amd64 --build-arg BUILD_VERSION=2.2.1 --build-arg BUILD_ARCH=amd64 --load -t local/addon-hyperion-ng:2.2.1-amd64 addon-hyperion-ng -
Validate the Hyperion aarch64 build:
docker buildx build --pull --platform linux/arm64 --build-arg BUILD_VERSION=2.2.1 --build-arg BUILD_ARCH=aarch64 --output type=cacheonly addon-hyperion-ng -
Build OpenCode add-on image for a single architecture:
./.github/scripts/build-opencode.sh amd64 -
Build all OpenCode architectures:
./.github/scripts/build-opencode.sh all -
Build OpenChamber add-on image for a single architecture:
./.github/scripts/build-openchamber.sh amd64 -
Build all OpenChamber architectures:
./.github/scripts/build-openchamber.sh all
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.
- 6d ago First seen · 166 lines · 1,543 tokens per session scan A a50f098a693c
hassio-addons AGENTS.md is an instructions file published in the GitHub repository bradsjm/hassio-addons (44 stars, last pushed 1mo ago), licensed MIT. It adds 1,543 tokens to every session, about $0.0077 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
hassio-addons CLAUDE.md
Claude Code instructions for alexbelgium/hassio-addons, covering claude.md, repository overview, add-on directory structure, dockerfile convention and config.yaml schema.
ha-mcp AGENTS.md
AGENTS.md instructions for homeassistant-ai/ha-mcp, covering agents.md, instruction structure, repository structure, worktree workflow and project overview.
HomeAssistant-Tapo-Control AGENTS.md
AGENTS.md instructions for JurajNyiri/HomeAssistant-Tapo-Control, covering agent instructions, required user agreement, repository rules and commits and prs.
HomeAssistant-Tapo-Control copilot-instructions.md
Copilot instructions for JurajNyiri/HomeAssistant-Tapo-Control: Follow AGENTS.md and CONTRIBUTING.md for this repository.
HomeAssistant-Tapo-Control CLAUDE.md
Claude Code instructions for JurajNyiri/HomeAssistant-Tapo-Control: Follow AGENTS.md and CONTRIBUTING.md before working in this repository.
mini-climate-card AGENTS.md
AGENTS.md instructions for artem-sedykh/mini-climate-card, covering agents.md, what this is, the card is configured, not coded, the template context and language.