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-modern-apis/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-modern-apis)<a href="https://agentmods.dev/skills/jpawlowski/hacs.integration_blueprint/ha-modern-apis"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/ha-modern-apis/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-modern-apis"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/ha-modern-apis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Privilege Escalation · line 106 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Prompt Injection · line 65 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
- medium Excessive Agency · line 123 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00240 | $0.01539 |
| Opus 5 | $0.00120 | $0.00770 |
| Sonnet 5 | $0.00048 | $0.00308 |
| Haiku 4.5 | $0.00024 | $0.00154 |
Grade A, and why
ha-modern-apis 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 13d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keep the integration on current Home Assistant APIs
Home Assistant changes fast enough that any pattern remembered from training data or copied from a blog post is suspect. This skill exists because the most common failure mode is confidently writing a 2023 API.
The rule: check the source, do not recall
The devcontainer has the exact Home Assistant version this integration is developed against. It is the authority.
# Which version are we on?
.venv/bin/python -c "from homeassistant.const import __version__; print(__version__)"
# Does this API still exist, and is it deprecated?
rg -n "def async_get_device_by_identifier" .venv/lib/python*/site-packages/homeassistant/helpers/device_registry.py
rg -n "deprecated|breaks_in_ha_version" .venv/lib/python*/site-packages/homeassistant/helpers/update_coordinator.py
# How do current core integrations do it?
rg -n "runtime_data" .venv/lib/python*/site-packages/homeassistant/components/<similar_integration>/
breaks_in_ha_version= in a @deprecated_function decorator tells you the actual removal deadline. Prefer that over
any secondary source.
When the installed source is not enough — a pattern that is new rather than deprecated — check https://developers.home-assistant.io/blog/ before implementing.
The same rule, generalised: what counts as verified
This applies to any API, tool or configuration key you are about to commit to. Only a primary source settles a question — the installed source you import, or the current documentation of the tool you are configuring. A GitHub issue, a blog post, another tool's convention and your own recall are leads, never answers.
Two traps make a secondary source feel primary:
- Silent failure. Most configuration rejects nothing: an unknown key is ignored, and the resulting default often looks like success. Before believing "X works", ask what a broken X would look like — if the answer is "the same thing", the observation proved nothing. Test the case that can fail: the file that should not match, the entry that should not load.
- A key that belongs to a neighbouring tool. Copilot, Cursor and Claude Code each name the same idea differently
(
applyTo,globs,paths). That a key works in one tool is no evidence for the next, and the wrong one will not complain.
What ships with it
1 file 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.
- 13d ago First seen · 125 lines · 240 tokens per session scan A 659f91f42d21
ha-modern-apis is a skill published in the GitHub repository jpawlowski/hacs.integration_blueprint (49 stars, last pushed 5d ago), licensed MIT. It adds 240 tokens to every session and 1,539 once invoked, about $0.0012 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
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…
homeassistant
Source-layer Home Assistant guide material preserved behind the runtime guide.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
bat-story-eval
Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage.
issue-to-pr-resolver
Implement a GitHub issue end-to-end — create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments until the PR is clean. Use when you need to fully implement a GitHub issue from start to merge-ready. Triggers on "implement issue", "resolve…
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.