hacs.integration_blueprint: Skill for Claude Code

.agents/skills/ha-grill/SKILL.md

ha-grill is a skill for Claude Code, Codex from jpawlowski/hacs.integration_blueprint. It costs 221 tokens per session (2,924 once invoked), scanned A, original, MIT.

An interview procedure for clarifying the requirements of a Home Assistant integration change before coding begins.

In plain words
What is it for?
Use it when starting an integration, adding a platform, entity set, service action, or flow step, especially when the request leaves important choices open.
Why use it?
It exposes decisions about identifiers, stored configuration, data shape, and behavior that are costly to change after users install the integration.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is jpawlowski/hacs.integration_blueprint's own configuration. It tells Claude Code and Codex how to work on hacs.integration_blueprint itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hacs.integration_blueprint configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/jpawlowski/hacs.integration_blueprint/main/.agents/skills/ha-grill/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jpawlowski/hacs.integration_blueprint

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ha-grill

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/ha-grill/github.svg)](https://agentmods.dev/skills/jpawlowski/hacs.integration_blueprint/ha-grill)
Your own site
<a href="https://agentmods.dev/skills/jpawlowski/hacs.integration_blueprint/ha-grill"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/ha-grill/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.

agentmods 80×15 button for ha-grill

Your own site · 80×15
<a href="https://agentmods.dev/skills/jpawlowski/hacs.integration_blueprint/ha-grill"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/ha-grill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 221 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,924 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, 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 28
    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 Prompt Injection · line 34
    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 Prompt Injection · line 71
    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
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00221 $0.02924
Opus 5 $0.00111 $0.01462
Sonnet 5 $0.00044 $0.00585
Haiku 4.5 $0.00022 $0.00292

Measured 11d ago against content hash 409a44b3215e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ha-grill 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.

.agents/skills/ha-grill/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill the developer before writing code

An agent that builds exactly what was asked builds the wrong thing surprisingly often. The request is the tip of a decision tree, and every branch left unasked gets guessed.

Here the guesses are expensive in a specific way: unique IDs, entity IDs, entry.data and the coordinator's data shape reach users with the first release and are breaking to change afterwards (ha-breaking-changes). A question costs a minute now; the same question answered by a migration costs a release. Interrogate first — that is the whole point of this skill.

When to run it

Situation Grill?
Fresh blueprint, no real code yet Yes — it produces the facts blueprint-scaffold demands
An existing integration about to be imported Yes — before its baseline is taken; the install base decides how much of the import is affordable
First real feature after an import or migration Yes — the imported code answers less than it looks like
A new platform, entity set, service action or flow step Yes, once more than two or three decisions are open
A one-line request whose scope you cannot state back in one sentence Yes
A bug with a known cause No — debug it (ha-coordinator-debug)
A complete spec is already on the table No. Say so, name the two or three real gaps, ask only those.

Read the full file on GitHub · 198 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 198 lines · 221 tokens per session scan A 409a44b3215e

Subscribe to this mod's changes

ha-grill is a skill published in the GitHub repository jpawlowski/hacs.integration_blueprint (49 stars, last pushed 4d ago), licensed MIT. It adds 221 tokens to every session and 2,924 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

homeassistant

Source-layer Home Assistant guide material preserved behind the runtime guide.

ha-china/ha_claw · 15 tokens

bat-story-eval

Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage.

homeassistant-ai/ha-mcp · 26 tokens

contrib-pr-review

Review a contribution PR for safety, quality, and readiness. Checks for security concerns, test coverage, size appropriateness, and intent alignment. Use when reviewing external contributions.

homeassistant-ai/ha-mcp · 39 tokens

bat-adhoc

Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. Use when testing PRs, detecting regressions, or verifying tool changes end-to-end with Claude/Gemini CLIs.

homeassistant-ai/ha-mcp · 48 tokens

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…

homeassistant-ai/ha-mcp · 85 tokens

my-pr-checker

Manage your own GitHub pull requests — check CI status, inline review comments, PR-level comments, resolve review threads, fix issues, and iterate until all checks pass and threads are resolved. Use for managing your own PRs (not external contributions). Triggers on "check my PR", "check PR", "/my-pr-checker ".

homeassistant-ai/ha-mcp · 75 tokens