Borrowing it
Nothing to install: this file belongs to jpawlowski/hacs.integration_blueprint. 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/jpawlowski/hacs.integration_blueprint/main/.agents/skills/blueprint-import/SKILL.mdgit clone --depth 1 https://github.com/jpawlowski/hacs.integration_blueprintWrote 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/skills/jpawlowski/hacs.integration_blueprint/blueprint-import)<a href="https://agentmods.dev/skills/jpawlowski/hacs.integration_blueprint/blueprint-import"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/blueprint-import/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jpawlowski/hacs.integration_blueprint/blueprint-import"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/blueprint-import.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 103 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00200 | $0.03038 |
| Opus 5 | $0.00100 | $0.01519 |
| Sonnet 5 | $0.00040 | $0.00608 |
| Haiku 4.5 | $0.00020 | $0.00304 |
Grade A, and why
blueprint-import 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 11d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Import an existing integration
A published integration has users. Their automations, dashboards, and statistics are bound to entity IDs, unique IDs, state values and action names — none of which the migration is allowed to change. Everything else is negotiable.
The whole procedure is one long behaviour-preserving refactor. Treat any observable difference as a bug in the migration, not as an improvement, unless the developer explicitly asked for it.
Phase 0 — Baseline first, before touching anything
Without a record of the current behaviour, nothing in the later phases is verifiable.
Two records are needed, and they are not the same thing. This phase captures what the code does.
ha-grill captures what the maintainer wants — how many installations are at stake,
what is deliberately unusual in there, what they already know is broken, and whether a breaking release is on the
table at all. Run that interview first: its answers decide how much of phases 3 to 7 is affordable, and an import
planned without them optimises for the wrong constraint.
- Capture the identity of every entity. From a running installation, export the entity IDs and unique IDs of the integration's entities (the entity registry, or the diagnostics download). If no live instance is available, derive them from the code and say so — a derived baseline is weaker.
- Record the contract in a scratch file under
.agents/scratch/:- the domain
- the
unique_idformat for the config entry and for each entity - the keys stored in
entry.dataandentry.options, and the config entryVERSION/MINOR_VERSION - the service action names and their field names
- the
device_class,state_class, unit and attribute names of every entity - any
Store/.storagekey the integration writes
- Note what the integration depends on:
manifest.json→requirements, the minimum Home Assistant version, and whether it uses discovery.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 210 lines · 200 tokens per session scan A d86c34d922a5
blueprint-import is a skill published in the GitHub repository jpawlowski/hacs.integration_blueprint (49 stars, last pushed 3d ago), licensed MIT. It adds 200 tokens to every session and 3,038 once invoked, about $0.0010 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 skills, from other repositories
homeassistant
Source-layer Home Assistant guide material preserved behind the runtime guide.
aurora
Aurora Smart Home orchestrator — routing layer for all smart home skills. Use this skill when the user asks ANY smart home question and you need to decide which skill to invoke, or when a task spans multiple skills (e.g., "build a sensor that shows on a dashboard and triggers automations"). Invoke aurora FIRST before…
ESPHome
ESPHome device configuration, firmware, and IoT product development. Covers ESP32, ESP32-S3, ESP32-C3, ESP32-C6, ESP32-H2, ESP32-P4, ESP8266, RP2040, RP2350, nRF52, LibreTiny, Shelly, Sonoff, Tuya, BLE proxy, Matter firmware, Thread, Zigbee, GPIO, sensor YAML, LVGL displays, LED strips, voice assistant hardware…
HA Integration Dev
Home Assistant custom integration development in Python. Covers customcomponents, DataUpdateCoordinator, configflow, OAuth2, conversation agent, HACS publishing, device registry, entity platforms, services, repair issues, diagnostics, Bluetooth integrations, and multi-coordinator patterns.
Node-RED
Node-RED visual automation flows for Home Assistant. Covers visual automation, flow JSON, trigger-state, api-call-service, function nodes, context storage, timer patterns, error handling, and node-red-contrib-home-assistant-websocket nodes. Use when user mentions "Node-RED", "flow", "visual automation", or…
API Catalog
Reference guide for connecting popular APIs to Home Assistant via Node-RED, YAML, or custom integrations. Covers authentication, endpoints, and complete working examples for: energy APIs (Tibber, Nordpool), weather (SMHI, OpenWeatherMap, yr.no), transport (SL, Trafikverket, Resrobot), smart home clouds (Shelly, Tuya…