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/ha-service-action/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/ha-service-action)<a href="https://agentmods.dev/skills/jpawlowski/hacs.integration_blueprint/ha-service-action"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/ha-service-action/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/ha-service-action"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/ha-service-action.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.02286 |
| Opus 5.5 | $0.00080 | $0.00914 |
| Sonnet 5.5 | $0.00040 | $0.00457 |
| Haiku 4.5 | $0.00020 | $0.00229 |
Grade A, and why
ha-service-action 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 2mo 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add or change a service action
Terminology: Home Assistant renamed "services" to actions in the UI, but the Python API, the file name
services.yaml, and the translation keys all still say service. Use "action" when talking to users, service in
code.
Read blueprint.service_actions.instructions.md
and blueprint.services_yaml.instructions.md
first — they hold the rules: where registration must happen, the voluptuous schema pattern, which exception type to
raise, the target: field, response-data requirements (including the .isoformat() trap), entity service actions, and
the icons.json shape. This skill is the order of operations and the design decisions.
Decide the shape first
Target the thing the action actually acts on — there are three levels, and picking the wrong one is what makes an action awkward to call:
| Question | Consequence |
|---|---|
| Does it act on one entity? | Add a target: with an entity: selector — do not invent an entity_id field. |
| Does it act on one device? | A required device_id field with a device: selector. |
| Does it act on the whole account/hub? | A required config_entry_id field with a config_entry: selector. |
| Does the caller need data back? | SupportsResponse.ONLY or .OPTIONAL and return a ServiceResponse dict. |
| Could an entity attribute or a button entity do it? | Prefer the entity. Actions are for things that do not map onto entity state. |
A target is never optional and never defaulted. Picking "the only entry" when the caller named none makes every
automation break the day a second entry is added. The one exception is single_config_entry: true in the manifest,
where there can only ever be one.
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.
- 2mo ago First seen · 229 lines · 200 tokens per session scan A f2ca7b4184ad
ha-service-action is a skill published in the GitHub repository jpawlowski/hacs.integration_blueprint (54 stars, last pushed 5d ago), licensed MIT. It adds 200 tokens to every session and 2,286 once invoked, about $0.0008 per session on Opus 5.5. 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.
ha-service-action compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ha-service-actionjpawlowski/hacs.integration_blueprint | Skill | 54 | 5d ago | MIT | A | 200 | Claude Code, Codex |
| API Catalogtonylofgren/aurora-smart-home | Skill | 109 | yesterday | MIT | A | 132 | Claude Code |
| homeassistantha-china/ha_claw | Skill | 101 | 3d ago | MIT | A | 15 | Claude Code, Codex |
| auroratonylofgren/aurora-smart-home | Skill | 109 | yesterday | MIT | A | 133 | Claude Code |
| ESPHometonylofgren/aurora-smart-home | Skill | 109 | yesterday | MIT | A | 192 | Claude Code |
| HA Integration Devtonylofgren/aurora-smart-home | Skill | 109 | yesterday | MIT | A | 55 | Claude Code |
| Node-REDtonylofgren/aurora-smart-home | Skill | 109 | yesterday | MIT | A | 76 | Claude Code |