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/dashdevil/claude-hawin/claude-mdgit clone --depth 1 https://github.com/dashdevil/claude-hawinWrote 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/dashdevil/claude-hawin/claude-md)<a href="https://agentmods.dev/instructions/dashdevil/claude-hawin/claude-md"><img src="https://agentmods.dev/badge/instructions/dashdevil/claude-hawin/claude-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 | $0.00546 | $0.00546 |
| Opus 5 | $0.00273 | $0.00273 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
claude-hawin CLAUDE.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.
What it actually says
Home Assistant -- Claude Code Context
HA 2025.x | Bewohner: BEWOHNER_1 & BEWOHNER_2
Regeln
- Alles in Packages -- niemals
automations.yaml,scripts.yamloder GUI - Keine HA-Scenes -- ausschliesslich Scripts verwenden
- MCP nur zum Pruefen -- Coding in YAML-Packages, Deployment per SSH
- Validation ist Pflicht -- Hooks laufen automatisch, Pre-Push blockiert bei Fehlern
- Vor KNX-Aufgaben immer
KNX_group_addresses_xml.csvlesen - NIEMALS
.storage/-Dateien manipulieren -- nur HA-UI, MCP oder REST API - Vor groesseren Umbauten Backup erstellen (
bash ha backup)
Entity-ID Umlaute
HA slugifiziert Umlaute ohne ae/oe/ue-Ersetzung:
| Zeichen | Entity-ID | Falsch |
|---|---|---|
| ae | prasenz |
praesenz |
| oe | scholl |
schoell |
| ue | kuche |
kueche |
| ss | strasse |
-- |
Zugang
ssh [email protected] # TODO: Dein HA-Host
# Packages: /config/packages/
# Secrets: /config/secrets.yaml # NIE ausgeben!
Workflow
bash ha pull # Packages vom Server holen
bash ha push <datei.yaml> # Validieren + pushen
bash ha push-all # Alle Packages pushen
bash ha test # Validatoren lokal ausfuehren
bash ha check # Config-Check auf dem Server
bash ha errors # ERROR-Zeilen aus HA-Log
bash ha backup # Timestamped Backup
Nach Push: Reload via MCP (automation.reload / script.reload). Nicht ha core reload!
Schluessel-Entities
notify.mobile_app_DEIN_HANDY # TODO: Haupt-Benachrichtigung
# notify.mobile_app_PARTNER # TODO: Partner
# switch.tag_nacht # Tag/Nacht
# binary_sensor.jemand_zuhause # Praesenz
Namensschema
- Alias:
[Gewerk]: [Ort --] Funktion - ID: slugifizierter Alias (
alarm_kueche_wassermelder) - Gewerke: Alarm, Beleuchtung, Beschattung, Heizung, ...
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 · 62 lines · 546 tokens per session scan A 534a2a2b1ac1
claude-hawin CLAUDE.md is an instructions file published in the GitHub repository dashdevil/claude-hawin (2 stars, last pushed 6mo ago), licensed MIT. It adds 546 tokens to every session, about $0.0027 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
firmware CLAUDE.md
Claude Code instructions for OpenIPC/firmware, covering claude.md, what this is, before you start: is this the right repository?, build and common tasks.
Tutorial_AwesomeModernCPP AGENTS.md
AGENTS.md instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.
ext-apps CLAUDE.md
Claude Code instructions for modelcontextprotocol/ext-apps, a project described as: Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers.