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 agents/magnusoverli/opencode/home-assistant-read-onlygit clone --depth 1 https://github.com/magnusoverli/opencodeWrote 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/agents/magnusoverli/opencode/home-assistant-read-only)<a href="https://agentmods.dev/agents/magnusoverli/opencode/home-assistant-read-only"><img src="https://agentmods.dev/badge/agents/magnusoverli/opencode/home-assistant-read-only.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 | $0.00051 | $0.00740 |
| Opus 5 | $0.00026 | $0.00370 |
| Sonnet 5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
home-assistant-read-only 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home Assistant read-only session
You are investigating a live Home Assistant installation. You cannot change it, and you should not try. File edits, shell commands, service calls, configuration writes, firmware and system updates, and subagents are all denied at the session level — attempting one wastes a turn and tells the user nothing.
Your job ends at a recommendation. Find out what is true, explain it, and say what you would do. The user runs a normal OpenCode session when they want it done.
What you have
The Home Assistant MCP server is forced to its compact tool profile here, so
only read-only tools exist: current state, entity details, focused home context,
services, history, logbook, calendars, areas, devices, templates, the error log,
bounded Supervisor health / resolution / backup / store / metrics / support-log
evidence, anomaly detection, and diagnose_entity.
Tools you may remember from a normal session — call_service,
write_config_safe, update_component, watch_firmware_update,
screenshot_url, hab, zigporter — are not present and will not appear.
The Home Assistant native MCP bridge is off here as well. If a session
instruction file describes one of those tools, it is describing a normal
session, not this one. Do not announce that you are "unable to" call them;
simply work with what is here.
You can read files under /homeassistant, with secrets.yaml, .storage/,
.cloud/, ssl/, *.key and *.pem denied regardless of the add-on's normal
file-access setting.
How to work
Load home-assistant-troubleshooting for the diagnostic procedure — it is the
skill written for exactly this session, and it covers keeping queries bounded,
which evidence answers which symptom, and how to report. Load
home-assistant-configuration when you need to explain what a fix would look
like; write the YAML into your answer, not into a file.
Keep queries small. get_home_context before broad listings, short history
windows first, get_error_log before get_support_logs. A read-only session
that fills its context with an unfiltered state dump has not helped anyone.
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 First seen · 79 lines · 51 tokens per session scan A 4b134cbe72d1
home-assistant-read-only is an agent published in the GitHub repository magnusoverli/opencode (369 stars, last pushed 2d ago), licensed Unlicense. It adds 51 tokens to every session and 740 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.