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-update/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-update)<a href="https://agentmods.dev/skills/jpawlowski/hacs.integration_blueprint/blueprint-update"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/blueprint-update/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-update"><img src="https://agentmods.dev/badge/skills/jpawlowski/hacs.integration_blueprint/blueprint-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00214 | $0.01022 |
| Opus 5.5 | $0.00086 | $0.00409 |
| Sonnet 5.5 | $0.00043 | $0.00204 |
| Haiku 4.5 | $0.00021 | $0.00102 |
Grade A, and why
blueprint-update 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 4d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Updating from the blueprint
Read first: blueprint-tooling § Template sync, for what the sync does and what
.templatesyncignore keeps out of it. This skill is the other half: what the sync leaves for a person.
This only applies in an integration repository made from the blueprint. In the blueprint itself, or in a copy that
still has initialize.sh, there is nothing to update from — script/blueprint-update refuses, and so should you.
| File | When to read |
|---|---|
references/manual-steps.md |
Step 2 — the list of steps, each with how to check it |
Procedure
- Merge the open template sync pull request first, after reviewing it as usual. It brings this skill, the
manual-steps list and
script/blueprint-updateup to date; working from an older copy misses the newest steps. - Go through the manual steps. For each entry in
references/manual-steps.md, run its check. A step whose check passes is done, and so is one listed underskippedin.agents/blueprint-update.json. Present the remaining ones to the developer one at a time — what it does and why, in their words rather than the blueprint's — and apply what they accept. A step they decline goes intoskippedwith its id, so the next run does not ask again. - Review the watched files.
script/blueprint-updateprints, per file, what the blueprint changed since the commit this repository last went through, already spelled with this repository's domain, title, class prefix and repository name — the onesinitialize.shrecorded in.agents/blueprint-update.json. The first run has no record yet and shows the whole difference to the blueprint instead, which includes everything the project changed on purpose — read it as a list of candidates, not as a patch. - Merge each change into the project's file, never over it. These files are excluded from the sync because the project owns them. Port a hunk where it fits the project, adapt its wording to what the project already says, and leave out what the project decided differently. When a hunk is unclear, ask; when it conflicts with something the project wrote, show both and let the developer choose.
- Validate with the loop in
AGENTS.md—script/lintand, if code or configuration changed,script/test. - Record the blueprint commit with
script/blueprint-update --record, so the next run shows only what is new. Commit the record together with the changes, aschore(template): carry over blueprint changeswith one bullet per file or step in the body — and only when the developer asks for the commit, asAGENTS.md§ Commits says.
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.
- 4d ago First seen · 57 lines · 214 tokens per session scan A 6b481e5337b8
blueprint-update is a skill published in the GitHub repository jpawlowski/hacs.integration_blueprint (54 stars, last pushed 5d ago), licensed MIT. It adds 214 tokens to every session and 1,022 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 2026-11-02.
blueprint-update compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blueprint-updatejpawlowski/hacs.integration_blueprint | Skill | 54 | 5d ago | MIT | A | 214 | Claude Code, Codex |
| homeassistantha-china/ha_claw | Skill | 101 | 3d ago | MIT | A | 15 | Claude Code, Codex |
| bat-story-evalhomeassistant-ai/ha-mcp | Skill | 5.4k | yesterday | MIT | A | 26 | Claude Code |
| contrib-pr-reviewhomeassistant-ai/ha-mcp | Skill | 5.4k | yesterday | MIT | A | 39 | Claude Code |
| bat-adhochomeassistant-ai/ha-mcp | Skill | 5.4k | yesterday | MIT | A | 48 | Claude Code |
| 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 |