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-release/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-release)<a href="https://agentmods.dev/skills/jpawlowski/hacs.integration_blueprint/ha-release"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/ha-release/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-release"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/ha-release.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 | $0.00217 | $0.01559 |
| Opus 5.5 | $0.00087 | $0.00624 |
| Sonnet 5.5 | $0.00043 | $0.00312 |
| Haiku 4.5 | $0.00022 | $0.00156 |
Grade A, and why
ha-release 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releases and commit messages
Releases are driven entirely by commit messages. A sloppy commit subject is not a cosmetic issue here — it decides the version number and what users read in the changelog.
Commit rules for agents (non-negotiable)
- Never commit automatically. Only commit when the developer explicitly asks, in that message.
- A previous commit request is not standing permission. Each commit needs a fresh instruction.
- Never push, and never offer to. The developer handles
git push. - Always run
git diff(andgit status) before writing a message. Describe what is actually staged, not what you remember doing.
Commit message format
The format, the allowed types and scopes, the rules commitlint enforces, and the scope-versus-type trap are all in
blueprint.commit-message.instructions.md,
which Copilot loads for every file. Read it before writing a message.
What that file does not tell you is what your choice costs at release time: a user-facing change committed under a
hidden type (refactor, chore, docs, test, ci) never reaches the changelog and never triggers a release —
only feat, fix, perf, and breaking changes do. If a change matters to a user, pick one of those honestly instead
of reaching for chore.
When you tell someone which type to use, say this consequence out loud — "X, because Y is hidden from the changelog and never ships a release" — don't just name the type and cite the instructions file's definition of it.
What each type does to the release
| Type | Changelog section | Version effect (pre-1.0) |
|---|---|---|
feat |
Features | patch bump (0.1.0 → 0.1.1) |
fix |
Bug Fixes | patch bump |
perf |
Performance | patch bump |
feat! / BREAKING CHANGE: |
Features + notice | minor bump (0.1.0 → 0.2.0) |
refactor, chore, docs, test, ci |
hidden | no release |
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 · 137 lines · 217 tokens per session scan A 699b13ce91fb
ha-release is a skill published in the GitHub repository jpawlowski/hacs.integration_blueprint (54 stars, last pushed 5d ago), licensed MIT. It adds 217 tokens to every session and 1,559 once invoked, about $0.0009 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-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ha-releasejpawlowski/hacs.integration_blueprint | Skill | 54 | 5d ago | MIT | A | 217 | Claude Code, Codex |
| my-pr-checkerhomeassistant-ai/ha-mcp | Skill | 5.4k | yesterday | MIT | A | 75 | Claude Code |
| contributors-updatehomeassistant-ai/ha-mcp | Skill | 5.4k | yesterday | MIT | A | 17 | Claude Code |
| issue-to-pr-resolverhomeassistant-ai/ha-mcp | Skill | 5.4k | yesterday | MIT | A | 85 | Claude Code |
| wthomeassistant-ai/ha-mcp | Skill | 5.4k | yesterday | MIT | A | 18 | Claude Code |
| homeassistantha-china/ha_claw | Skill | 101 | 3d ago | MIT | A | 15 | Claude Code, Codex |
| releasethedotmack/claude-mem | Skill | 114k | yesterday | Apache-2.0 | A | 13 | Claude Code |