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/vypdev/homeassistant-gateway/agents-mdgit clone --depth 1 https://github.com/vypdev/homeassistant-gatewayWhat 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 | $0.00654 | $0.00654 |
| Opus 5 | $0.00327 | $0.00327 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
homeassistant-gateway 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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Guide
Non-negotiable quality bar
This repository prioritizes correctness, maintainability, security, and verifiable behavior over implementation speed.
A change is incomplete until:
- the behavior is covered by focused tests, including relevant denial/error paths;
- domain/application code remains independent of Home Assistant, MCP, HTTP, filesystem, subprocess, and framework details;
- external calls have bounded timeouts and sanitized errors;
- secrets are absent from source, fixtures, logs, exceptions, audit events, and test output;
- documentation and contracts match the implementation;
- local quality checks and CI pass;
- the final diff is reviewed and free of generated artifacts.
Architecture rules
Layers point inward:
presentation -> application -> domain
infrastructure -> application/domain ports
composition -> wires concrete adapters
- Domain code contains policies, capabilities, identifiers, and decisions.
- Application code orchestrates use cases through injected ports.
- Infrastructure adapts Home Assistant, Supervisor, MCP, storage, and transports.
- Presentation maps external requests/responses and must not contain authorization policy.
- Composition is the only place that constructs concrete adapters.
Do not import Home Assistant, MCP SDKs, HTTP clients, or environment/config readers into domain modules.
Development workflow
- Record the current contract and assumptions.
- Write a focused failing test.
- Run the test and confirm the failure is meaningful.
- Implement the smallest production change.
- Run the focused test, then the complete suite.
- Add integration/contract coverage at the boundary.
- Update documentation and review the full diff.
- Run all quality gates before publishing.
Security rules
- Observer is read-only.
- Operator is never enabled implicitly by a prompt, model, or tool name.
- Every mutation requires identity, capability, target policy, validation, approval, idempotency, and audit.
- Do not read or expose raw Home Assistant configuration directories by default.
- Do not add Docker socket, SSH, shell, or arbitrary filesystem capabilities.
- Never commit real credentials, tokens, cookies, topology secrets, or private identifiers.
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.
- 2d ago First seen · 80 lines · 654 tokens per session scan A 258d6b626293
homeassistant-gateway AGENTS.md is an instructions file published in the GitHub repository vypdev/homeassistant-gateway (2 stars, last pushed 6d ago), licensed MIT. It adds 654 tokens to every session, about $0.0033 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.